converse-mcp-server 2.26.1 โ†’ 2.27.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/docs/EXAMPLES.md CHANGED
@@ -1,1113 +1,1113 @@
1
- # Converse MCP Server - Usage Examples
2
-
3
- ## ๐Ÿš€ Getting Started Examples
4
-
5
- ### Basic Chat Interaction
6
-
7
- ```json
8
- {
9
- "tool": "chat",
10
- "arguments": {
11
- "prompt": "Hello! Can you help me understand JavaScript promises?"
12
- }
13
- }
14
- ```
15
-
16
- **Response:**
17
- ```json
18
- {
19
- "content": "I'd be happy to help you understand JavaScript promises! Promises are objects that represent the eventual completion or failure of an asynchronous operation...",
20
- "continuation": {
21
- "id": "conv_abc123",
22
- "provider": "openai",
23
- "model": "o4-mini",
24
- "messageCount": 2
25
- },
26
- "metadata": {
27
- "model": "o4-mini",
28
- "usage": {
29
- "input_tokens": 15,
30
- "output_tokens": 145,
31
- "total_tokens": 160
32
- },
33
- "response_time_ms": 1200,
34
- "provider": "openai"
35
- },
36
- "title": "Understanding JavaScript Promises", // When summarization enabled
37
- "final_summary": "Explained JavaScript promises as objects for handling asynchronous operations with practical examples." // When summarization enabled
38
- }
39
- ```
40
-
41
- ### Continuing a Conversation
42
-
43
- ```json
44
- {
45
- "tool": "chat",
46
- "arguments": {
47
- "prompt": "Can you show me a practical example?",
48
- "continuation_id": "conv_abc123"
49
- }
50
- }
51
- ```
52
-
53
- ## โฑ๏ธ Asynchronous Execution Examples
54
-
55
- ### Basic Async Chat
56
-
57
- For long-running tasks, use async mode to get immediate response and monitor progress:
58
-
59
- ```json
60
- {
61
- "tool": "chat",
62
- "arguments": {
63
- "prompt": "Analyze this large codebase and provide comprehensive optimization recommendations",
64
- "model": "gpt-5",
65
- "files": ["/path/to/large-project"],
66
- "async": true,
67
- "continuation_id": "analysis-task-001"
68
- }
69
- }
70
- ```
71
-
72
- **Immediate Response:**
73
- ```json
74
- {
75
- "content": "โณ PROCESSING | CHAT | analysis-task-001 | 1/1 | Started: 2023-12-01 10:30:00 | openai/gpt-5",
76
- "continuation": {
77
- "id": "analysis-task-001",
78
- "status": "processing"
79
- },
80
- "async_execution": true
81
- }
82
- ```
83
-
84
- ### Monitoring Async Progress
85
-
86
- ```json
87
- {
88
- "tool": "check_status",
89
- "arguments": {
90
- "continuation_id": "analysis-task-001"
91
- }
92
- }
93
- ```
94
-
95
- **While Processing (with summarization enabled):**
96
- ```json
97
- {
98
- "content": {
99
- "id": "analysis-task-001",
100
- "status": "processing",
101
- "tool": "chat",
102
- "title": "Codebase Optimization Analysis", // AI-generated title
103
- "streaming_summary": "Analyzing codebase structure and dependencies. Currently examining performance bottlenecks in the API layer.", // Summary based on partially streamed response
104
- "progress": {
105
- "completed": 1,
106
- "total": 1,
107
- "percentage": 100
108
- },
109
- "elapsed_seconds": 12.5
110
- }
111
- }
112
- ```
113
-
114
- **When Complete (with summarization enabled):**
115
- ```json
116
- {
117
- "content": {
118
- "id": "analysis-task-001",
119
- "status": "completed",
120
- "tool": "chat",
121
- "title": "Codebase Optimization Analysis", // AI-generated title
122
- "final_summary": "Identified 5 critical performance bottlenecks and provided refactoring recommendations for improved scalability.", // Final summary
123
- "result": {
124
- "content": "# Codebase Analysis Results\n\nAfter analyzing your codebase, here are the key optimization opportunities...",
125
- "metadata": {
126
- "provider": "openai",
127
- "model": "gpt-5",
128
- "usage": {
129
- "input_tokens": 15420,
130
- "output_tokens": 2340
131
- }
132
- }
133
- },
134
- "elapsed_seconds": 45.2,
135
- "completed_at": "2023-12-01T10:30:45.200Z"
136
- }
137
- }
138
- ```
139
-
140
- ### Async Consensus Example
141
-
142
- ```json
143
- {
144
- "tool": "consensus",
145
- "arguments": {
146
- "prompt": "Design a scalable microservices architecture for our e-commerce platform",
147
- "models": ["gpt-5", "gemini-2.5-pro", "claude-sonnet-4"],
148
- "files": ["/docs/requirements.md", "/docs/current-architecture.md"],
149
- "async": true,
150
- "enable_cross_feedback": true
151
- }
152
- }
153
- ```
154
-
155
- **Immediate Response:**
156
- ```json
157
- {
158
- "content": "โณ PROCESSING | CONSENSUS | consensus_xyz789 | 0/3 | Started: 2023-12-01 10:30:00 | gpt-5,gemini-2.5-pro,claude-sonnet-4",
159
- "continuation": {
160
- "id": "consensus_xyz789",
161
- "status": "processing"
162
- },
163
- "async_execution": true,
164
- "metadata": {
165
- "total_models": 3,
166
- "successful_models": 0,
167
- "models_list": "gpt-5,gemini-2.5-pro,claude-sonnet-4"
168
- }
169
- }
170
- ```
171
-
172
- ### Cancelling Long-Running Jobs
173
-
174
- ```json
175
- {
176
- "tool": "cancel_job",
177
- "arguments": {
178
- "continuation_id": "analysis-task-001"
179
- }
180
- }
181
- ```
182
-
183
- **Response:**
184
- ```json
185
- {
186
- "content": {
187
- "status": "cancelled",
188
- "message": "Job analysis-task-001 cancelled successfully",
189
- "job_id": "analysis-task-001",
190
- "elapsed_seconds": 15.3,
191
- "cancelled_at": "2023-12-01T10:30:15.300Z"
192
- }
193
- }
194
- ```
195
-
196
- ### Listing Recent Jobs
197
-
198
- ```json
199
- {
200
- "tool": "check_status",
201
- "arguments": {}
202
- }
203
- ```
204
-
205
- **Response (with summarization enabled):**
206
- ```json
207
- {
208
- "content": {
209
- "jobs": [
210
- {
211
- "id": "analysis-task-001",
212
- "status": "completed",
213
- "tool": "chat",
214
- "title": "Codebase Optimization Analysis", // AI-generated title
215
- "final_summary": "Identified 5 critical performance bottlenecks and provided refactoring recommendations.", // Summary shown in listing
216
- "elapsed_seconds": 45.2,
217
- "completed_at": "2023-12-01T10:30:45.200Z"
218
- },
219
- {
220
- "id": "consensus_xyz789",
221
- "status": "processing",
222
- "tool": "consensus",
223
- "title": "E-commerce Architecture Design", // AI-generated title
224
- "progress": {
225
- "completed": 2,
226
- "total": 3,
227
- "percentage": 67
228
- },
229
- "elapsed_seconds": 28.7
230
- }
231
- ]
232
- }
233
- }
234
- ```
235
-
236
- ## ๐Ÿš€ GPT-5 Advanced Features
237
-
238
- ### Using Minimal Reasoning for Fast Responses
239
-
240
- ```json
241
- {
242
- "tool": "chat",
243
- "arguments": {
244
- "prompt": "Write a simple SQL query to get all users created today",
245
- "model": "gpt-5",
246
- "reasoning_effort": "minimal",
247
- "verbosity": "low"
248
- }
249
- }
250
- ```
251
-
252
- ### High Verbosity for Detailed Explanations
253
-
254
- ```json
255
- {
256
- "tool": "chat",
257
- "arguments": {
258
- "prompt": "Explain the architecture of this authentication system and suggest improvements",
259
- "model": "gpt-5",
260
- "files": ["/c/Users/username/project/src/auth.js"],
261
- "reasoning_effort": "high",
262
- "verbosity": "high"
263
- }
264
- }
265
- ```
266
-
267
- ### Cost-Efficient with GPT-5-nano
268
-
269
- ```json
270
- {
271
- "tool": "chat",
272
- "arguments": {
273
- "prompt": "Summarize the main points from this document",
274
- "model": "gpt-5-nano",
275
- "files": ["/c/Users/username/docs/report.md"],
276
- "verbosity": "low"
277
- }
278
- }
279
- ```
280
-
281
- ## ๐Ÿ”ง Code Analysis Examples
282
-
283
- ### Single File Analysis
284
-
285
- ```json
286
- {
287
- "tool": "chat",
288
- "arguments": {
289
- "prompt": "Review this function for potential bugs and improvements",
290
- "model": "gpt-5",
291
- "files": ["/c/Users/username/project/src/auth.js"],
292
- "reasoning_effort": "high",
293
- "temperature": 0.1
294
- }
295
- }
296
- ```
297
-
298
- ### Multi-File Architecture Review
299
-
300
- ```json
301
- {
302
- "tool": "chat",
303
- "arguments": {
304
- "prompt": "Analyze the overall architecture and suggest improvements for scalability",
305
- "model": "gemini-2.5-pro",
306
- "files": [
307
- "/c/Users/username/project/src/server.js",
308
- "/c/Users/username/project/src/routes/index.js",
309
- "/c/Users/username/project/src/middleware/auth.js",
310
- "/c/Users/username/project/config/database.js"
311
- ],
312
- "temperature": 0.2
313
- }
314
- }
315
- ```
316
-
317
- ## ๐ŸŽฏ Model-Specific Examples
318
-
319
- ### Using GPT-5 for Complex Reasoning
320
-
321
- ```json
322
- {
323
- "tool": "chat",
324
- "arguments": {
325
- "prompt": "Design a distributed caching strategy for a social media platform with 10M+ users",
326
- "model": "gpt-5",
327
- "reasoning_effort": "max",
328
- "temperature": 0.1
329
- }
330
- }
331
- ```
332
-
333
- ### Using Flash for Quick Responses
334
-
335
- ```json
336
- {
337
- "tool": "chat",
338
- "arguments": {
339
- "prompt": "What's the syntax for async/await in JavaScript?",
340
- "model": "gemini-2.5-flash",
341
- "temperature": 0.3
342
- }
343
- }
344
- ```
345
-
346
- ### Using Grok for Creative Solutions
347
-
348
- ```json
349
- {
350
- "tool": "chat",
351
- "arguments": {
352
- "prompt": "Brainstorm creative ways to gamify a productivity app",
353
- "model": "grok-4",
354
- "temperature": 0.7
355
- }
356
- }
357
- ```
358
-
359
- ## ๐Ÿค– Codex Examples
360
-
361
- Codex is an agentic coding assistant that runs locally with direct filesystem access.
362
-
363
- ### Basic Code Analysis
364
-
365
- ```json
366
- {
367
- "tool": "chat",
368
- "arguments": {
369
- "prompt": "Explain what this function does",
370
- "model": "codex",
371
- "files": ["/path/to/src/utils.js"]
372
- }
373
- }
374
- ```
375
-
376
- ### Thread Continuation
377
-
378
- Codex maintains conversation history through threads:
379
-
380
- ```json
381
- // First request
382
- {
383
- "tool": "chat",
384
- "arguments": {
385
- "prompt": "Review this authentication module",
386
- "model": "codex",
387
- "files": ["/path/to/auth.js"]
388
- }
389
- }
390
- // Response includes: "continuation": { "id": "conv_abc123" }
391
-
392
- // Follow-up request (maintains context)
393
- {
394
- "tool": "chat",
395
- "arguments": {
396
- "prompt": "Now add rate limiting to the login endpoint",
397
- "model": "codex",
398
- "continuation_id": "conv_abc123"
399
- }
400
- }
401
- ```
402
-
403
- ### Async Mode for Long Tasks
404
-
405
- Codex responses can take several minutes for complex tasks:
406
-
407
- ```json
408
- {
409
- "tool": "chat",
410
- "arguments": {
411
- "prompt": "Analyze this entire codebase and suggest refactoring opportunities",
412
- "model": "codex",
413
- "files": ["/path/to/project"],
414
- "async": true
415
- }
416
- }
417
- // Response: { "job_id": "conv_xyz789", "status": "SUBMITTED" }
418
-
419
- // Check progress
420
- {
421
- "tool": "check_status",
422
- "arguments": {
423
- "continuation_id": "conv_xyz789"
424
- }
425
- }
426
- ```
427
-
428
- ### Sandbox Modes
429
-
430
- Control filesystem access through `CODEX_SANDBOX_MODE`:
431
-
432
- ```bash
433
- # Read-only mode (default) - safe for exploration
434
- CODEX_SANDBOX_MODE=read-only
435
-
436
- # Workspace-write - allow modifications in project directory
437
- CODEX_SANDBOX_MODE=workspace-write
438
-
439
- # Full access - use only in containers with proper isolation
440
- CODEX_SANDBOX_MODE=danger-full-access
441
- ```
442
-
443
- ## ๐Ÿค Consensus Examples
444
-
445
- ### Simple Technical Decision
446
-
447
- ```json
448
- {
449
- "tool": "consensus",
450
- "arguments": {
451
- "prompt": "Should we use PostgreSQL or MongoDB for our e-commerce inventory system?",
452
- "models": ["gpt-5", "gemini-2.5-pro", "grok-4"],
453
- "temperature": 0.2
454
- }
455
- }
456
- ```
457
-
458
- **Response Structure:**
459
- ```json
460
- {
461
- "status": "consensus_complete",
462
- "models_consulted": 3,
463
- "successful_initial_responses": 3,
464
- "refined_responses": 3,
465
- "phases": {
466
- "initial": [
467
- {
468
- "model": "gpt-5",
469
- "status": "success",
470
- "response": "For an e-commerce inventory system, I recommend PostgreSQL because...",
471
- "metadata": {"input_tokens": 50, "output_tokens": 180}
472
- }
473
- ],
474
- "refined": [
475
- {
476
- "model": "gpt-5",
477
- "status": "success",
478
- "initial_response": "For an e-commerce inventory system, I recommend PostgreSQL...",
479
- "refined_response": "After considering the other perspectives on MongoDB's flexibility, I still lean towards PostgreSQL but acknowledge that MongoDB could work well if..."
480
- }
481
- ]
482
- }
483
- }
484
- ```
485
-
486
- ### Architecture Decision with Context
487
-
488
- ```json
489
- {
490
- "tool": "consensus",
491
- "arguments": {
492
- "prompt": "Given our current system architecture, what's the best approach for implementing real-time notifications?",
493
- "models": [
494
- "gpt-5", // Most intelligent: Superior reasoning
495
- "grok-4", // Most intelligent: Advanced analysis
496
- "gemini-2.5-pro" // Most intelligent: Deep thinking
497
- ],
498
- "files": [
499
- "/c/Users/username/docs/current_architecture.md",
500
- "/c/Users/username/src/server.js",
501
- "/c/Users/username/package.json"
502
- ],
503
- "enable_cross_feedback": true,
504
- "temperature": 0.15
505
- }
506
- }
507
- ```
508
-
509
- ### Fast Consensus (No Cross-Feedback)
510
-
511
- ```json
512
- {
513
- "tool": "consensus",
514
- "arguments": {
515
- "prompt": "What's the best CSS framework for rapid prototyping in 2024?",
516
- "models": ["gemini-2.5-flash", "o4-mini", "grok-4"],
517
- "enable_cross_feedback": false,
518
- "temperature": 0.3
519
- }
520
- }
521
- ```
522
-
523
- ## ๐Ÿ”„ Conversation (Round-Table) Examples
524
-
525
- The `conversation` tool runs a turn-based round-table: models respond **in the order given**, and each model sees the full running transcript of every turn before it. One call = one lap. Pass the returned `continuation_id` to run another lap; every lap appends to one shared transcript. This differs from `consensus`, where all models answer the same prompt in parallel.
526
-
527
- ### Basic Two-Model Round-Table
528
-
529
- ```json
530
- {
531
- "tool": "conversation",
532
- "arguments": {
533
- "prompt": "Should we adopt event sourcing for the order service?",
534
- "models": ["codex", "gemini"]
535
- }
536
- }
537
- ```
538
-
539
- On this lap, `codex` opens, then `gemini` responds having seen codex's turn. The response contains both labeled turns in order plus a `continuation_id`.
540
-
541
- ### Continuing the Round-Table (More Laps)
542
-
543
- ```json
544
- // Lap 1 returns: "continuation": { "id": "conv_abc123" }
545
-
546
- // Lap 2 โ€” every model again sees the full accumulated transcript
547
- {
548
- "tool": "conversation",
549
- "arguments": {
550
- "prompt": "Now focus specifically on the migration path from the current design.",
551
- "models": ["codex", "gemini"],
552
- "continuation_id": "conv_abc123"
553
- }
554
- }
555
- ```
556
-
557
- You may also change the model list on a resuming lap (e.g. drop a participant or add one); the shared transcript persists regardless of who ran in earlier laps:
558
-
559
- ```json
560
- {
561
- "tool": "conversation",
562
- "arguments": {
563
- "prompt": "Bring in a third perspective on testability.",
564
- "models": ["codex", "gemini", "claude"],
565
- "continuation_id": "conv_abc123"
566
- }
567
- }
568
- ```
569
-
570
- ### Round-Table with Files and a Custom Per-Turn Instruction
571
-
572
- ```json
573
- {
574
- "tool": "conversation",
575
- "arguments": {
576
- "prompt": "Review this module design and push back on weak assumptions.",
577
- "models": ["codex", "gemini", "claude"],
578
- "files": ["/c/Users/username/project/src/orders/design.md"],
579
- "turn_prompt": "Call out concrete failure modes you would test for."
580
- }
581
- }
582
- ```
583
-
584
- ### Async Round-Table with Progress Monitoring
585
-
586
- ```json
587
- {
588
- "tool": "conversation",
589
- "arguments": {
590
- "prompt": "Design a rollout plan for the new pricing engine.",
591
- "models": ["codex", "gemini", "claude"],
592
- "async": true
593
- }
594
- }
595
- ```
596
-
597
- **Immediate Response:**
598
- ```json
599
- {
600
- "content": "โณ SUBMITTED | CONVERSATION | conv_xyz789 | 1/1 | Started: 01/12/2023 10:30:00 | \"Pricing Engine Rollout\" | codex, gemini, claude",
601
- "continuation": {
602
- "id": "conv_xyz789",
603
- "status": "processing"
604
- },
605
- "async_execution": true
606
- }
607
- ```
608
-
609
- **Monitor per-turn progress, then read the full transcript on completion:**
610
- ```json
611
- {
612
- "tool": "check_status",
613
- "arguments": {
614
- "continuation_id": "conv_xyz789"
615
- }
616
- }
617
- ```
618
-
619
- While running, the status line shows turn progress (e.g. `2/3 turns`) and the accumulating transcript. When complete, `check_status` renders the full lap transcript along with the AI-generated title and final summary.
620
-
621
- ## ๐Ÿ–ผ๏ธ Image Analysis Examples
622
-
623
- ### Screenshot Analysis
624
-
625
- ```json
626
- {
627
- "tool": "chat",
628
- "arguments": {
629
- "prompt": "Analyze this UI design and suggest improvements for user experience",
630
- "model": "gpt-4.1",
631
- "images": ["/c/Users/username/designs/dashboard_mockup.png"],
632
- "temperature": 0.3
633
- }
634
- }
635
- ```
636
-
637
- ### Multi-Image Comparison
638
-
639
- ```json
640
- {
641
- "tool": "consensus",
642
- "arguments": {
643
- "prompt": "Compare these three design options and recommend the best one for our mobile app",
644
- "models": ["gpt-4.1", "gemini-2.5-pro", "grok-4"],
645
- "images": [
646
- "/c/Users/username/designs/option_a.png",
647
- "/c/Users/username/designs/option_b.png",
648
- "/c/Users/username/designs/option_c.png"
649
- ],
650
- "temperature": 0.2
651
- }
652
- }
653
- ```
654
-
655
- ### Code + Diagram Analysis
656
-
657
- ```json
658
- {
659
- "tool": "chat",
660
- "arguments": {
661
- "prompt": "Review the implementation against the architecture diagram. Are we following the design correctly?",
662
- "model": "gpt-5",
663
- "files": ["/c/Users/username/src/services/payment.js", "/c/Users/username/src/models/transaction.js"],
664
- "images": ["/c/Users/username/docs/payment_flow_diagram.png"],
665
- "reasoning_effort": "high"
666
- }
667
- }
668
- ```
669
-
670
- ## ๐Ÿ” Debugging & Problem Solving
671
-
672
- ### Error Investigation
673
-
674
- ```json
675
- {
676
- "tool": "chat",
677
- "arguments": {
678
- "prompt": "Help me debug this error. The application crashes intermittently with this stack trace.",
679
- "model": "gpt-5",
680
- "files": [
681
- "/c/Users/username/src/server.js",
682
- "/c/Users/username/logs/error.log",
683
- "/c/Users/username/src/middleware/error-handler.js"
684
- ],
685
- "reasoning_effort": "high",
686
- "temperature": 0.1
687
- }
688
- }
689
- ```
690
-
691
- ### Performance Analysis
692
-
693
- ```json
694
- {
695
- "tool": "consensus",
696
- "arguments": {
697
- "prompt": "Our API response times are degrading. What could be the root causes?",
698
- "models": [
699
- "gemini-2.5-flash", // Fast: Quick analysis
700
- "o4-mini", // Fast: Rapid responses
701
- "gpt-4.1" // Fast: Efficient processing
702
- ],
703
- "files": [
704
- "/c/Users/username/monitoring/performance_report.json",
705
- "/c/Users/username/src/database/queries.js",
706
- "/c/Users/username/src/api/routes.js"
707
- ],
708
- "cross_feedback_prompt": "Focus on the most likely performance bottlenecks based on the data"
709
- }
710
- }
711
- ```
712
-
713
- ## ๐Ÿ“š Learning & Documentation
714
-
715
- ### Concept Explanation
716
-
717
- ```json
718
- {
719
- "tool": "chat",
720
- "arguments": {
721
- "prompt": "Explain microservices architecture with pros, cons, and when to use it",
722
- "model": "gemini-2.5-pro",
723
- "temperature": 0.4
724
- }
725
- }
726
- ```
727
-
728
- ### Code Review & Learning
729
-
730
- ```json
731
- {
732
- "tool": "chat",
733
- "arguments": {
734
- "prompt": "Review this code and explain what it does, then suggest best practices improvements",
735
- "model": "gpt-5",
736
- "files": ["/c/Users/username/src/utils/encryption.js"],
737
- "reasoning_effort": "medium",
738
- "temperature": 0.2
739
- }
740
- }
741
- ```
742
-
743
- ### Technology Comparison
744
-
745
- ```json
746
- {
747
- "tool": "consensus",
748
- "arguments": {
749
- "prompt": "Compare Next.js, Nuxt.js, and SvelteKit for our new web application project",
750
- "models": ["gpt-5", "gemini-2.5-flash", "grok-4"],
751
- "files": ["/c/Users/username/docs/project_requirements.md"],
752
- "temperature": 0.25
753
- }
754
- }
755
- ```
756
-
757
- ## ๐Ÿ› ๏ธ Development Workflows
758
-
759
- ### Feature Planning
760
-
761
- ```json
762
- {
763
- "tool": "consensus",
764
- "arguments": {
765
- "prompt": "Plan the implementation of user authentication with social login support",
766
- "models": ["gpt-5", "gemini-2.5-pro", "grok-4"],
767
- "files": [
768
- "/c/Users/username/docs/user_requirements.md",
769
- "/c/Users/username/src/models/user.js"
770
- ],
771
- "cross_feedback_prompt": "Consider security, scalability, and user experience in your refinement"
772
- }
773
- }
774
- ```
775
-
776
- ### Code Generation
777
-
778
- ```json
779
- {
780
- "tool": "chat",
781
- "arguments": {
782
- "prompt": "Generate a React component for a responsive image gallery with lazy loading",
783
- "model": "gemini-2.5-flash",
784
- "files": ["/c/Users/username/src/styles/globals.css"],
785
- "temperature": 0.3
786
- }
787
- }
788
- ```
789
-
790
- ### Refactoring Guidance
791
-
792
- ```json
793
- {
794
- "tool": "chat",
795
- "arguments": {
796
- "prompt": "Help me refactor this legacy code to use modern ES6+ features and improve readability",
797
- "model": "gpt-5",
798
- "files": ["/c/Users/username/src/legacy/data-processor.js"],
799
- "reasoning_effort": "medium",
800
- "temperature": 0.2
801
- }
802
- }
803
- ```
804
-
805
- ## ๐Ÿš€ Advanced Use Cases
806
-
807
- ### Multi-Step Problem Solving
808
-
809
- ```json
810
- {
811
- "tool": "chat",
812
- "arguments": {
813
- "prompt": "I need to migrate our monolith to microservices. What's the step-by-step approach?",
814
- "model": "gpt-5",
815
- "files": ["/c/Users/username/src/app.js", "/c/Users/username/docs/current_architecture.md"],
816
- "reasoning_effort": "max",
817
- "temperature": 0.1
818
- }
819
- }
820
- ```
821
-
822
- ### Cross-Technology Analysis
823
-
824
- ```json
825
- {
826
- "tool": "consensus",
827
- "arguments": {
828
- "prompt": "Should we migrate from Python Django to Node.js Express for better performance?",
829
- "models": ["gpt-5", "gemini-2.5-pro", "grok-4"],
830
- "files": [
831
- "/c/Users/username/backend/requirements.txt",
832
- "/c/Users/username/monitoring/performance_metrics.json",
833
- "/c/Users/username/docs/team_skills.md"
834
- ],
835
- "cross_feedback_prompt": "Consider team expertise, migration costs, and long-term maintainability"
836
- }
837
- }
838
- ```
839
-
840
- ### Research & Investigation
841
-
842
- ```json
843
- {
844
- "tool": "chat",
845
- "arguments": {
846
- "prompt": "Research the latest trends in web development for 2024 and how they apply to our project",
847
- "model": "grok-4",
848
- "use_websearch": true,
849
- "temperature": 0.5
850
- }
851
- }
852
- ```
853
-
854
- ## ๐ŸŽ›๏ธ Configuration Examples
855
-
856
- ### Custom Temperature Settings
857
-
858
- ```json
859
- {
860
- "tool": "chat",
861
- "arguments": {
862
- "prompt": "Generate creative marketing copy for our new product launch",
863
- "model": "grok-4",
864
- "temperature": 0.8
865
- }
866
- }
867
- ```
868
-
869
- ```json
870
- {
871
- "tool": "chat",
872
- "arguments": {
873
- "prompt": "Fix this bug in my authentication logic",
874
- "model": "gpt-5",
875
- "files": ["/c/Users/username/src/auth.js"],
876
- "temperature": 0.0,
877
- "reasoning_effort": "high"
878
- }
879
- }
880
- ```
881
-
882
- ### Different Reasoning Levels
883
-
884
- ```json
885
- {
886
- "tool": "chat",
887
- "arguments": {
888
- "prompt": "Quick syntax check - is this JavaScript valid?",
889
- "model": "gpt-5",
890
- "reasoning_effort": "minimal",
891
- "temperature": 0.1
892
- }
893
- }
894
- ```
895
-
896
- ```json
897
- {
898
- "tool": "chat",
899
- "arguments": {
900
- "prompt": "Design a comprehensive testing strategy for this complex system",
901
- "model": "gpt-5",
902
- "files": ["/src/", "/tests/"],
903
- "reasoning_effort": "max",
904
- "temperature": 0.1
905
- }
906
- }
907
- ```
908
-
909
- ## ๐Ÿ”„ Continuation Examples
910
-
911
- ### Long Research Session
912
-
913
- ```json
914
- // First request
915
- {
916
- "tool": "chat",
917
- "arguments": {
918
- "prompt": "I'm building a real-time chat application. What architecture should I consider?",
919
- "model": "gpt-5"
920
- }
921
- }
922
-
923
- // Response includes: "continuation": {"id": "conv_research_123"}
924
-
925
- // Follow-up questions
926
- {
927
- "tool": "chat",
928
- "arguments": {
929
- "prompt": "What about handling file uploads in real-time?",
930
- "continuation_id": "conv_research_123"
931
- }
932
- }
933
-
934
- {
935
- "tool": "chat",
936
- "arguments": {
937
- "prompt": "How would you implement message encryption?",
938
- "continuation_id": "conv_research_123"
939
- }
940
- }
941
- ```
942
-
943
- ### Iterative Development
944
-
945
- ```json
946
- // Initial code review
947
- {
948
- "tool": "chat",
949
- "arguments": {
950
- "prompt": "Review this API endpoint implementation",
951
- "model": "gpt-5",
952
- "files": ["/c/Users/username/src/api/users.js"]
953
- }
954
- }
955
-
956
- // Implementation improvement
957
- {
958
- "tool": "chat",
959
- "arguments": {
960
- "prompt": "Now help me implement the error handling you suggested",
961
- "continuation_id": "conv_dev_456",
962
- "files": ["/c/Users/username/src/api/users.js"]
963
- }
964
- }
965
-
966
- // Testing guidance
967
- {
968
- "tool": "chat",
969
- "arguments": {
970
- "prompt": "What unit tests should I write for this endpoint?",
971
- "continuation_id": "conv_dev_456"
972
- }
973
- }
974
- ```
975
-
976
- ## ๐ŸŽจ Creative & Brainstorming
977
-
978
- ### Feature Ideation
979
-
980
- ```json
981
- {
982
- "tool": "consensus",
983
- "arguments": {
984
- "prompt": "Brainstorm innovative features for a fitness tracking app that would differentiate us from competitors",
985
- "models": ["grok-4", "gemini-2.5-pro", "gpt-4.1"],
986
- "temperature": 0.7,
987
- "cross_feedback_prompt": "Build on each other's ideas and suggest combinations"
988
- }
989
- }
990
- ```
991
-
992
- ### UI/UX Improvements
993
-
994
- ```json
995
- {
996
- "tool": "chat",
997
- "arguments": {
998
- "prompt": "Suggest creative ways to improve user onboarding for this interface",
999
- "model": "grok-4",
1000
- "images": ["/c/Users/username/designs/current_onboarding.png"],
1001
- "temperature": 0.6
1002
- }
1003
- }
1004
- ```
1005
-
1006
- ## ๐Ÿงช Testing Examples
1007
-
1008
- ### Test Strategy Planning
1009
-
1010
- ```json
1011
- {
1012
- "tool": "consensus",
1013
- "arguments": {
1014
- "prompt": "What testing strategy should we implement for this e-commerce checkout flow?",
1015
- "models": ["gpt-5", "gemini-2.5-pro", "gemini-2.5-flash"],
1016
- "files": [
1017
- "/c/Users/username/src/checkout/payment.js",
1018
- "/c/Users/username/src/checkout/validation.js",
1019
- "/c/Users/username/docs/business_requirements.md"
1020
- ],
1021
- "temperature": 0.2
1022
- }
1023
- }
1024
- ```
1025
-
1026
- ### Test Generation
1027
-
1028
- ```json
1029
- {
1030
- "tool": "chat",
1031
- "arguments": {
1032
- "prompt": "Generate comprehensive unit tests for this user authentication module",
1033
- "model": "gemini-2.5-flash",
1034
- "files": ["/c/Users/username/src/auth/index.js"],
1035
- "temperature": 0.3
1036
- }
1037
- }
1038
- ```
1039
-
1040
- ## ๐Ÿ“Š Error Handling Examples
1041
-
1042
- ### Graceful Degradation
1043
-
1044
- ```json
1045
- {
1046
- "tool": "consensus",
1047
- "arguments": {
1048
- "prompt": "One of our models is unavailable, but we still need consensus",
1049
- "models": ["available-model-1", "available-model-2"],
1050
- "temperature": 0.2
1051
- }
1052
- }
1053
- ```
1054
-
1055
- ### Partial Success Response
1056
-
1057
- ```json
1058
- {
1059
- "status": "consensus_partial",
1060
- "models_consulted": 2,
1061
- "successful_initial_responses": 2,
1062
- "failed_responses": 1,
1063
- "failed_models": ["unavailable-model"],
1064
- "phases": {
1065
- "initial": [...],
1066
- "refined": [...],
1067
- "failed": [
1068
- {
1069
- "model": "unavailable-model",
1070
- "error": "Provider not available. Check API key configuration.",
1071
- "status": "failed"
1072
- }
1073
- ]
1074
- }
1075
- }
1076
- ```
1077
-
1078
- ## ๐Ÿ”ง Integration Examples
1079
-
1080
- ### CI/CD Pipeline Integration
1081
-
1082
- ```bash
1083
- # Use in GitHub Actions
1084
- - name: Code Review
1085
- run: |
1086
- echo '{
1087
- "tool": "chat",
1088
- "arguments": {
1089
- "prompt": "Review this pull request for security issues and best practices",
1090
- "model": "gpt-5",
1091
- "files": ["/c/Users/username/src/modified-file.js"],
1092
- "reasoning_effort": "high"
1093
- }
1094
- }' | npx converse-mcp-server
1095
- ```
1096
-
1097
- ### Automated Documentation
1098
-
1099
- ```bash
1100
- # Generate documentation
1101
- echo '{
1102
- "tool": "chat",
1103
- "arguments": {
1104
- "prompt": "Generate API documentation for these endpoints",
1105
- "model": "gemini-2.5-flash",
1106
- "files": ["/c/Users/username/src/api/routes.js"]
1107
- }
1108
- }' | npx converse-mcp-server > /c/Users/username/docs/api.md
1109
- ```
1110
-
1111
- ---
1112
-
1
+ # Converse MCP Server - Usage Examples
2
+
3
+ ## ๐Ÿš€ Getting Started Examples
4
+
5
+ ### Basic Chat Interaction
6
+
7
+ ```json
8
+ {
9
+ "tool": "chat",
10
+ "arguments": {
11
+ "prompt": "Hello! Can you help me understand JavaScript promises?"
12
+ }
13
+ }
14
+ ```
15
+
16
+ **Response:**
17
+ ```json
18
+ {
19
+ "content": "I'd be happy to help you understand JavaScript promises! Promises are objects that represent the eventual completion or failure of an asynchronous operation...",
20
+ "continuation": {
21
+ "id": "conv_abc123",
22
+ "provider": "openai",
23
+ "model": "o4-mini",
24
+ "messageCount": 2
25
+ },
26
+ "metadata": {
27
+ "model": "o4-mini",
28
+ "usage": {
29
+ "input_tokens": 15,
30
+ "output_tokens": 145,
31
+ "total_tokens": 160
32
+ },
33
+ "response_time_ms": 1200,
34
+ "provider": "openai"
35
+ },
36
+ "title": "Understanding JavaScript Promises", // When summarization enabled
37
+ "final_summary": "Explained JavaScript promises as objects for handling asynchronous operations with practical examples." // When summarization enabled
38
+ }
39
+ ```
40
+
41
+ ### Continuing a Conversation
42
+
43
+ ```json
44
+ {
45
+ "tool": "chat",
46
+ "arguments": {
47
+ "prompt": "Can you show me a practical example?",
48
+ "continuation_id": "conv_abc123"
49
+ }
50
+ }
51
+ ```
52
+
53
+ ## โฑ๏ธ Asynchronous Execution Examples
54
+
55
+ ### Basic Async Chat
56
+
57
+ For long-running tasks, use async mode to get immediate response and monitor progress:
58
+
59
+ ```json
60
+ {
61
+ "tool": "chat",
62
+ "arguments": {
63
+ "prompt": "Analyze this large codebase and provide comprehensive optimization recommendations",
64
+ "model": "gpt-5",
65
+ "files": ["/path/to/large-project"],
66
+ "async": true,
67
+ "continuation_id": "analysis-task-001"
68
+ }
69
+ }
70
+ ```
71
+
72
+ **Immediate Response:**
73
+ ```json
74
+ {
75
+ "content": "โณ PROCESSING | CHAT | analysis-task-001 | 1/1 | Started: 2023-12-01 10:30:00 | openai/gpt-5",
76
+ "continuation": {
77
+ "id": "analysis-task-001",
78
+ "status": "processing"
79
+ },
80
+ "async_execution": true
81
+ }
82
+ ```
83
+
84
+ ### Monitoring Async Progress
85
+
86
+ ```json
87
+ {
88
+ "tool": "check_status",
89
+ "arguments": {
90
+ "continuation_id": "analysis-task-001"
91
+ }
92
+ }
93
+ ```
94
+
95
+ **While Processing (with summarization enabled):**
96
+ ```json
97
+ {
98
+ "content": {
99
+ "id": "analysis-task-001",
100
+ "status": "processing",
101
+ "tool": "chat",
102
+ "title": "Codebase Optimization Analysis", // AI-generated title
103
+ "streaming_summary": "Analyzing codebase structure and dependencies. Currently examining performance bottlenecks in the API layer.", // Summary based on partially streamed response
104
+ "progress": {
105
+ "completed": 1,
106
+ "total": 1,
107
+ "percentage": 100
108
+ },
109
+ "elapsed_seconds": 12.5
110
+ }
111
+ }
112
+ ```
113
+
114
+ **When Complete (with summarization enabled):**
115
+ ```json
116
+ {
117
+ "content": {
118
+ "id": "analysis-task-001",
119
+ "status": "completed",
120
+ "tool": "chat",
121
+ "title": "Codebase Optimization Analysis", // AI-generated title
122
+ "final_summary": "Identified 5 critical performance bottlenecks and provided refactoring recommendations for improved scalability.", // Final summary
123
+ "result": {
124
+ "content": "# Codebase Analysis Results\n\nAfter analyzing your codebase, here are the key optimization opportunities...",
125
+ "metadata": {
126
+ "provider": "openai",
127
+ "model": "gpt-5",
128
+ "usage": {
129
+ "input_tokens": 15420,
130
+ "output_tokens": 2340
131
+ }
132
+ }
133
+ },
134
+ "elapsed_seconds": 45.2,
135
+ "completed_at": "2023-12-01T10:30:45.200Z"
136
+ }
137
+ }
138
+ ```
139
+
140
+ ### Async Consensus Example
141
+
142
+ ```json
143
+ {
144
+ "tool": "consensus",
145
+ "arguments": {
146
+ "prompt": "Design a scalable microservices architecture for our e-commerce platform",
147
+ "models": ["gpt-5", "gemini-2.5-pro", "claude-sonnet-4-6"],
148
+ "files": ["/docs/requirements.md", "/docs/current-architecture.md"],
149
+ "async": true,
150
+ "enable_cross_feedback": true
151
+ }
152
+ }
153
+ ```
154
+
155
+ **Immediate Response:**
156
+ ```json
157
+ {
158
+ "content": "โณ PROCESSING | CONSENSUS | consensus_xyz789 | 0/3 | Started: 2023-12-01 10:30:00 | gpt-5,gemini-2.5-pro,claude-sonnet-4-6",
159
+ "continuation": {
160
+ "id": "consensus_xyz789",
161
+ "status": "processing"
162
+ },
163
+ "async_execution": true,
164
+ "metadata": {
165
+ "total_models": 3,
166
+ "successful_models": 0,
167
+ "models_list": "gpt-5,gemini-2.5-pro,claude-sonnet-4-6"
168
+ }
169
+ }
170
+ ```
171
+
172
+ ### Cancelling Long-Running Jobs
173
+
174
+ ```json
175
+ {
176
+ "tool": "cancel_job",
177
+ "arguments": {
178
+ "continuation_id": "analysis-task-001"
179
+ }
180
+ }
181
+ ```
182
+
183
+ **Response:**
184
+ ```json
185
+ {
186
+ "content": {
187
+ "status": "cancelled",
188
+ "message": "Job analysis-task-001 cancelled successfully",
189
+ "job_id": "analysis-task-001",
190
+ "elapsed_seconds": 15.3,
191
+ "cancelled_at": "2023-12-01T10:30:15.300Z"
192
+ }
193
+ }
194
+ ```
195
+
196
+ ### Listing Recent Jobs
197
+
198
+ ```json
199
+ {
200
+ "tool": "check_status",
201
+ "arguments": {}
202
+ }
203
+ ```
204
+
205
+ **Response (with summarization enabled):**
206
+ ```json
207
+ {
208
+ "content": {
209
+ "jobs": [
210
+ {
211
+ "id": "analysis-task-001",
212
+ "status": "completed",
213
+ "tool": "chat",
214
+ "title": "Codebase Optimization Analysis", // AI-generated title
215
+ "final_summary": "Identified 5 critical performance bottlenecks and provided refactoring recommendations.", // Summary shown in listing
216
+ "elapsed_seconds": 45.2,
217
+ "completed_at": "2023-12-01T10:30:45.200Z"
218
+ },
219
+ {
220
+ "id": "consensus_xyz789",
221
+ "status": "processing",
222
+ "tool": "consensus",
223
+ "title": "E-commerce Architecture Design", // AI-generated title
224
+ "progress": {
225
+ "completed": 2,
226
+ "total": 3,
227
+ "percentage": 67
228
+ },
229
+ "elapsed_seconds": 28.7
230
+ }
231
+ ]
232
+ }
233
+ }
234
+ ```
235
+
236
+ ## ๐Ÿš€ GPT-5 Advanced Features
237
+
238
+ ### Using Minimal Reasoning for Fast Responses
239
+
240
+ ```json
241
+ {
242
+ "tool": "chat",
243
+ "arguments": {
244
+ "prompt": "Write a simple SQL query to get all users created today",
245
+ "model": "gpt-5",
246
+ "reasoning_effort": "minimal",
247
+ "verbosity": "low"
248
+ }
249
+ }
250
+ ```
251
+
252
+ ### High Verbosity for Detailed Explanations
253
+
254
+ ```json
255
+ {
256
+ "tool": "chat",
257
+ "arguments": {
258
+ "prompt": "Explain the architecture of this authentication system and suggest improvements",
259
+ "model": "gpt-5",
260
+ "files": ["/c/Users/username/project/src/auth.js"],
261
+ "reasoning_effort": "high",
262
+ "verbosity": "high"
263
+ }
264
+ }
265
+ ```
266
+
267
+ ### Cost-Efficient with GPT-5-nano
268
+
269
+ ```json
270
+ {
271
+ "tool": "chat",
272
+ "arguments": {
273
+ "prompt": "Summarize the main points from this document",
274
+ "model": "gpt-5-nano",
275
+ "files": ["/c/Users/username/docs/report.md"],
276
+ "verbosity": "low"
277
+ }
278
+ }
279
+ ```
280
+
281
+ ## ๐Ÿ”ง Code Analysis Examples
282
+
283
+ ### Single File Analysis
284
+
285
+ ```json
286
+ {
287
+ "tool": "chat",
288
+ "arguments": {
289
+ "prompt": "Review this function for potential bugs and improvements",
290
+ "model": "gpt-5",
291
+ "files": ["/c/Users/username/project/src/auth.js"],
292
+ "reasoning_effort": "high",
293
+ "temperature": 0.1
294
+ }
295
+ }
296
+ ```
297
+
298
+ ### Multi-File Architecture Review
299
+
300
+ ```json
301
+ {
302
+ "tool": "chat",
303
+ "arguments": {
304
+ "prompt": "Analyze the overall architecture and suggest improvements for scalability",
305
+ "model": "gemini-2.5-pro",
306
+ "files": [
307
+ "/c/Users/username/project/src/server.js",
308
+ "/c/Users/username/project/src/routes/index.js",
309
+ "/c/Users/username/project/src/middleware/auth.js",
310
+ "/c/Users/username/project/config/database.js"
311
+ ],
312
+ "temperature": 0.2
313
+ }
314
+ }
315
+ ```
316
+
317
+ ## ๐ŸŽฏ Model-Specific Examples
318
+
319
+ ### Using GPT-5 for Complex Reasoning
320
+
321
+ ```json
322
+ {
323
+ "tool": "chat",
324
+ "arguments": {
325
+ "prompt": "Design a distributed caching strategy for a social media platform with 10M+ users",
326
+ "model": "gpt-5",
327
+ "reasoning_effort": "max",
328
+ "temperature": 0.1
329
+ }
330
+ }
331
+ ```
332
+
333
+ ### Using Flash for Quick Responses
334
+
335
+ ```json
336
+ {
337
+ "tool": "chat",
338
+ "arguments": {
339
+ "prompt": "What's the syntax for async/await in JavaScript?",
340
+ "model": "gemini-2.5-flash",
341
+ "temperature": 0.3
342
+ }
343
+ }
344
+ ```
345
+
346
+ ### Using Grok for Creative Solutions
347
+
348
+ ```json
349
+ {
350
+ "tool": "chat",
351
+ "arguments": {
352
+ "prompt": "Brainstorm creative ways to gamify a productivity app",
353
+ "model": "grok-4",
354
+ "temperature": 0.7
355
+ }
356
+ }
357
+ ```
358
+
359
+ ## ๐Ÿค– Codex Examples
360
+
361
+ Codex is an agentic coding assistant that runs locally with direct filesystem access.
362
+
363
+ ### Basic Code Analysis
364
+
365
+ ```json
366
+ {
367
+ "tool": "chat",
368
+ "arguments": {
369
+ "prompt": "Explain what this function does",
370
+ "model": "codex",
371
+ "files": ["/path/to/src/utils.js"]
372
+ }
373
+ }
374
+ ```
375
+
376
+ ### Thread Continuation
377
+
378
+ Codex maintains conversation history through threads:
379
+
380
+ ```json
381
+ // First request
382
+ {
383
+ "tool": "chat",
384
+ "arguments": {
385
+ "prompt": "Review this authentication module",
386
+ "model": "codex",
387
+ "files": ["/path/to/auth.js"]
388
+ }
389
+ }
390
+ // Response includes: "continuation": { "id": "conv_abc123" }
391
+
392
+ // Follow-up request (maintains context)
393
+ {
394
+ "tool": "chat",
395
+ "arguments": {
396
+ "prompt": "Now add rate limiting to the login endpoint",
397
+ "model": "codex",
398
+ "continuation_id": "conv_abc123"
399
+ }
400
+ }
401
+ ```
402
+
403
+ ### Async Mode for Long Tasks
404
+
405
+ Codex responses can take several minutes for complex tasks:
406
+
407
+ ```json
408
+ {
409
+ "tool": "chat",
410
+ "arguments": {
411
+ "prompt": "Analyze this entire codebase and suggest refactoring opportunities",
412
+ "model": "codex",
413
+ "files": ["/path/to/project"],
414
+ "async": true
415
+ }
416
+ }
417
+ // Response: { "job_id": "conv_xyz789", "status": "SUBMITTED" }
418
+
419
+ // Check progress
420
+ {
421
+ "tool": "check_status",
422
+ "arguments": {
423
+ "continuation_id": "conv_xyz789"
424
+ }
425
+ }
426
+ ```
427
+
428
+ ### Sandbox Modes
429
+
430
+ Control filesystem access through `CODEX_SANDBOX_MODE`:
431
+
432
+ ```bash
433
+ # Read-only mode (default) - safe for exploration
434
+ CODEX_SANDBOX_MODE=read-only
435
+
436
+ # Workspace-write - allow modifications in project directory
437
+ CODEX_SANDBOX_MODE=workspace-write
438
+
439
+ # Full access - use only in containers with proper isolation
440
+ CODEX_SANDBOX_MODE=danger-full-access
441
+ ```
442
+
443
+ ## ๐Ÿค Consensus Examples
444
+
445
+ ### Simple Technical Decision
446
+
447
+ ```json
448
+ {
449
+ "tool": "consensus",
450
+ "arguments": {
451
+ "prompt": "Should we use PostgreSQL or MongoDB for our e-commerce inventory system?",
452
+ "models": ["gpt-5", "gemini-2.5-pro", "grok-4"],
453
+ "temperature": 0.2
454
+ }
455
+ }
456
+ ```
457
+
458
+ **Response Structure:**
459
+ ```json
460
+ {
461
+ "status": "consensus_complete",
462
+ "models_consulted": 3,
463
+ "successful_initial_responses": 3,
464
+ "refined_responses": 3,
465
+ "phases": {
466
+ "initial": [
467
+ {
468
+ "model": "gpt-5",
469
+ "status": "success",
470
+ "response": "For an e-commerce inventory system, I recommend PostgreSQL because...",
471
+ "metadata": {"input_tokens": 50, "output_tokens": 180}
472
+ }
473
+ ],
474
+ "refined": [
475
+ {
476
+ "model": "gpt-5",
477
+ "status": "success",
478
+ "initial_response": "For an e-commerce inventory system, I recommend PostgreSQL...",
479
+ "refined_response": "After considering the other perspectives on MongoDB's flexibility, I still lean towards PostgreSQL but acknowledge that MongoDB could work well if..."
480
+ }
481
+ ]
482
+ }
483
+ }
484
+ ```
485
+
486
+ ### Architecture Decision with Context
487
+
488
+ ```json
489
+ {
490
+ "tool": "consensus",
491
+ "arguments": {
492
+ "prompt": "Given our current system architecture, what's the best approach for implementing real-time notifications?",
493
+ "models": [
494
+ "gpt-5", // Most intelligent: Superior reasoning
495
+ "grok-4", // Most intelligent: Advanced analysis
496
+ "gemini-2.5-pro" // Most intelligent: Deep thinking
497
+ ],
498
+ "files": [
499
+ "/c/Users/username/docs/current_architecture.md",
500
+ "/c/Users/username/src/server.js",
501
+ "/c/Users/username/package.json"
502
+ ],
503
+ "enable_cross_feedback": true,
504
+ "temperature": 0.15
505
+ }
506
+ }
507
+ ```
508
+
509
+ ### Fast Consensus (No Cross-Feedback)
510
+
511
+ ```json
512
+ {
513
+ "tool": "consensus",
514
+ "arguments": {
515
+ "prompt": "What's the best CSS framework for rapid prototyping in 2024?",
516
+ "models": ["gemini-2.5-flash", "o4-mini", "grok-4"],
517
+ "enable_cross_feedback": false,
518
+ "temperature": 0.3
519
+ }
520
+ }
521
+ ```
522
+
523
+ ## ๐Ÿ”„ Conversation (Round-Table) Examples
524
+
525
+ The `conversation` tool runs a turn-based round-table: models respond **in the order given**, and each model sees the full running transcript of every turn before it. One call = one lap. Pass the returned `continuation_id` to run another lap; every lap appends to one shared transcript. This differs from `consensus`, where all models answer the same prompt in parallel.
526
+
527
+ ### Basic Two-Model Round-Table
528
+
529
+ ```json
530
+ {
531
+ "tool": "conversation",
532
+ "arguments": {
533
+ "prompt": "Should we adopt event sourcing for the order service?",
534
+ "models": ["codex", "gemini"]
535
+ }
536
+ }
537
+ ```
538
+
539
+ On this lap, `codex` opens, then `gemini` responds having seen codex's turn. The response contains both labeled turns in order plus a `continuation_id`.
540
+
541
+ ### Continuing the Round-Table (More Laps)
542
+
543
+ ```json
544
+ // Lap 1 returns: "continuation": { "id": "conv_abc123" }
545
+
546
+ // Lap 2 โ€” every model again sees the full accumulated transcript
547
+ {
548
+ "tool": "conversation",
549
+ "arguments": {
550
+ "prompt": "Now focus specifically on the migration path from the current design.",
551
+ "models": ["codex", "gemini"],
552
+ "continuation_id": "conv_abc123"
553
+ }
554
+ }
555
+ ```
556
+
557
+ You may also change the model list on a resuming lap (e.g. drop a participant or add one); the shared transcript persists regardless of who ran in earlier laps:
558
+
559
+ ```json
560
+ {
561
+ "tool": "conversation",
562
+ "arguments": {
563
+ "prompt": "Bring in a third perspective on testability.",
564
+ "models": ["codex", "gemini", "claude"],
565
+ "continuation_id": "conv_abc123"
566
+ }
567
+ }
568
+ ```
569
+
570
+ ### Round-Table with Files and a Custom Per-Turn Instruction
571
+
572
+ ```json
573
+ {
574
+ "tool": "conversation",
575
+ "arguments": {
576
+ "prompt": "Review this module design and push back on weak assumptions.",
577
+ "models": ["codex", "gemini", "claude"],
578
+ "files": ["/c/Users/username/project/src/orders/design.md"],
579
+ "turn_prompt": "Call out concrete failure modes you would test for."
580
+ }
581
+ }
582
+ ```
583
+
584
+ ### Async Round-Table with Progress Monitoring
585
+
586
+ ```json
587
+ {
588
+ "tool": "conversation",
589
+ "arguments": {
590
+ "prompt": "Design a rollout plan for the new pricing engine.",
591
+ "models": ["codex", "gemini", "claude"],
592
+ "async": true
593
+ }
594
+ }
595
+ ```
596
+
597
+ **Immediate Response:**
598
+ ```json
599
+ {
600
+ "content": "โณ SUBMITTED | CONVERSATION | conv_xyz789 | 1/1 | Started: 01/12/2023 10:30:00 | \"Pricing Engine Rollout\" | codex, gemini, claude",
601
+ "continuation": {
602
+ "id": "conv_xyz789",
603
+ "status": "processing"
604
+ },
605
+ "async_execution": true
606
+ }
607
+ ```
608
+
609
+ **Monitor per-turn progress, then read the full transcript on completion:**
610
+ ```json
611
+ {
612
+ "tool": "check_status",
613
+ "arguments": {
614
+ "continuation_id": "conv_xyz789"
615
+ }
616
+ }
617
+ ```
618
+
619
+ While running, the status line shows turn progress (e.g. `2/3 turns`) and the accumulating transcript. When complete, `check_status` renders the full lap transcript along with the AI-generated title and final summary.
620
+
621
+ ## ๐Ÿ–ผ๏ธ Image Analysis Examples
622
+
623
+ ### Screenshot Analysis
624
+
625
+ ```json
626
+ {
627
+ "tool": "chat",
628
+ "arguments": {
629
+ "prompt": "Analyze this UI design and suggest improvements for user experience",
630
+ "model": "gpt-4.1",
631
+ "images": ["/c/Users/username/designs/dashboard_mockup.png"],
632
+ "temperature": 0.3
633
+ }
634
+ }
635
+ ```
636
+
637
+ ### Multi-Image Comparison
638
+
639
+ ```json
640
+ {
641
+ "tool": "consensus",
642
+ "arguments": {
643
+ "prompt": "Compare these three design options and recommend the best one for our mobile app",
644
+ "models": ["gpt-4.1", "gemini-2.5-pro", "grok-4"],
645
+ "images": [
646
+ "/c/Users/username/designs/option_a.png",
647
+ "/c/Users/username/designs/option_b.png",
648
+ "/c/Users/username/designs/option_c.png"
649
+ ],
650
+ "temperature": 0.2
651
+ }
652
+ }
653
+ ```
654
+
655
+ ### Code + Diagram Analysis
656
+
657
+ ```json
658
+ {
659
+ "tool": "chat",
660
+ "arguments": {
661
+ "prompt": "Review the implementation against the architecture diagram. Are we following the design correctly?",
662
+ "model": "gpt-5",
663
+ "files": ["/c/Users/username/src/services/payment.js", "/c/Users/username/src/models/transaction.js"],
664
+ "images": ["/c/Users/username/docs/payment_flow_diagram.png"],
665
+ "reasoning_effort": "high"
666
+ }
667
+ }
668
+ ```
669
+
670
+ ## ๐Ÿ” Debugging & Problem Solving
671
+
672
+ ### Error Investigation
673
+
674
+ ```json
675
+ {
676
+ "tool": "chat",
677
+ "arguments": {
678
+ "prompt": "Help me debug this error. The application crashes intermittently with this stack trace.",
679
+ "model": "gpt-5",
680
+ "files": [
681
+ "/c/Users/username/src/server.js",
682
+ "/c/Users/username/logs/error.log",
683
+ "/c/Users/username/src/middleware/error-handler.js"
684
+ ],
685
+ "reasoning_effort": "high",
686
+ "temperature": 0.1
687
+ }
688
+ }
689
+ ```
690
+
691
+ ### Performance Analysis
692
+
693
+ ```json
694
+ {
695
+ "tool": "consensus",
696
+ "arguments": {
697
+ "prompt": "Our API response times are degrading. What could be the root causes?",
698
+ "models": [
699
+ "gemini-2.5-flash", // Fast: Quick analysis
700
+ "o4-mini", // Fast: Rapid responses
701
+ "gpt-4.1" // Fast: Efficient processing
702
+ ],
703
+ "files": [
704
+ "/c/Users/username/monitoring/performance_report.json",
705
+ "/c/Users/username/src/database/queries.js",
706
+ "/c/Users/username/src/api/routes.js"
707
+ ],
708
+ "cross_feedback_prompt": "Focus on the most likely performance bottlenecks based on the data"
709
+ }
710
+ }
711
+ ```
712
+
713
+ ## ๐Ÿ“š Learning & Documentation
714
+
715
+ ### Concept Explanation
716
+
717
+ ```json
718
+ {
719
+ "tool": "chat",
720
+ "arguments": {
721
+ "prompt": "Explain microservices architecture with pros, cons, and when to use it",
722
+ "model": "gemini-2.5-pro",
723
+ "temperature": 0.4
724
+ }
725
+ }
726
+ ```
727
+
728
+ ### Code Review & Learning
729
+
730
+ ```json
731
+ {
732
+ "tool": "chat",
733
+ "arguments": {
734
+ "prompt": "Review this code and explain what it does, then suggest best practices improvements",
735
+ "model": "gpt-5",
736
+ "files": ["/c/Users/username/src/utils/encryption.js"],
737
+ "reasoning_effort": "medium",
738
+ "temperature": 0.2
739
+ }
740
+ }
741
+ ```
742
+
743
+ ### Technology Comparison
744
+
745
+ ```json
746
+ {
747
+ "tool": "consensus",
748
+ "arguments": {
749
+ "prompt": "Compare Next.js, Nuxt.js, and SvelteKit for our new web application project",
750
+ "models": ["gpt-5", "gemini-2.5-flash", "grok-4"],
751
+ "files": ["/c/Users/username/docs/project_requirements.md"],
752
+ "temperature": 0.25
753
+ }
754
+ }
755
+ ```
756
+
757
+ ## ๐Ÿ› ๏ธ Development Workflows
758
+
759
+ ### Feature Planning
760
+
761
+ ```json
762
+ {
763
+ "tool": "consensus",
764
+ "arguments": {
765
+ "prompt": "Plan the implementation of user authentication with social login support",
766
+ "models": ["gpt-5", "gemini-2.5-pro", "grok-4"],
767
+ "files": [
768
+ "/c/Users/username/docs/user_requirements.md",
769
+ "/c/Users/username/src/models/user.js"
770
+ ],
771
+ "cross_feedback_prompt": "Consider security, scalability, and user experience in your refinement"
772
+ }
773
+ }
774
+ ```
775
+
776
+ ### Code Generation
777
+
778
+ ```json
779
+ {
780
+ "tool": "chat",
781
+ "arguments": {
782
+ "prompt": "Generate a React component for a responsive image gallery with lazy loading",
783
+ "model": "gemini-2.5-flash",
784
+ "files": ["/c/Users/username/src/styles/globals.css"],
785
+ "temperature": 0.3
786
+ }
787
+ }
788
+ ```
789
+
790
+ ### Refactoring Guidance
791
+
792
+ ```json
793
+ {
794
+ "tool": "chat",
795
+ "arguments": {
796
+ "prompt": "Help me refactor this legacy code to use modern ES6+ features and improve readability",
797
+ "model": "gpt-5",
798
+ "files": ["/c/Users/username/src/legacy/data-processor.js"],
799
+ "reasoning_effort": "medium",
800
+ "temperature": 0.2
801
+ }
802
+ }
803
+ ```
804
+
805
+ ## ๐Ÿš€ Advanced Use Cases
806
+
807
+ ### Multi-Step Problem Solving
808
+
809
+ ```json
810
+ {
811
+ "tool": "chat",
812
+ "arguments": {
813
+ "prompt": "I need to migrate our monolith to microservices. What's the step-by-step approach?",
814
+ "model": "gpt-5",
815
+ "files": ["/c/Users/username/src/app.js", "/c/Users/username/docs/current_architecture.md"],
816
+ "reasoning_effort": "max",
817
+ "temperature": 0.1
818
+ }
819
+ }
820
+ ```
821
+
822
+ ### Cross-Technology Analysis
823
+
824
+ ```json
825
+ {
826
+ "tool": "consensus",
827
+ "arguments": {
828
+ "prompt": "Should we migrate from Python Django to Node.js Express for better performance?",
829
+ "models": ["gpt-5", "gemini-2.5-pro", "grok-4"],
830
+ "files": [
831
+ "/c/Users/username/backend/requirements.txt",
832
+ "/c/Users/username/monitoring/performance_metrics.json",
833
+ "/c/Users/username/docs/team_skills.md"
834
+ ],
835
+ "cross_feedback_prompt": "Consider team expertise, migration costs, and long-term maintainability"
836
+ }
837
+ }
838
+ ```
839
+
840
+ ### Research & Investigation
841
+
842
+ ```json
843
+ {
844
+ "tool": "chat",
845
+ "arguments": {
846
+ "prompt": "Research the latest trends in web development for 2024 and how they apply to our project",
847
+ "model": "grok-4",
848
+ "use_websearch": true,
849
+ "temperature": 0.5
850
+ }
851
+ }
852
+ ```
853
+
854
+ ## ๐ŸŽ›๏ธ Configuration Examples
855
+
856
+ ### Custom Temperature Settings
857
+
858
+ ```json
859
+ {
860
+ "tool": "chat",
861
+ "arguments": {
862
+ "prompt": "Generate creative marketing copy for our new product launch",
863
+ "model": "grok-4",
864
+ "temperature": 0.8
865
+ }
866
+ }
867
+ ```
868
+
869
+ ```json
870
+ {
871
+ "tool": "chat",
872
+ "arguments": {
873
+ "prompt": "Fix this bug in my authentication logic",
874
+ "model": "gpt-5",
875
+ "files": ["/c/Users/username/src/auth.js"],
876
+ "temperature": 0.0,
877
+ "reasoning_effort": "high"
878
+ }
879
+ }
880
+ ```
881
+
882
+ ### Different Reasoning Levels
883
+
884
+ ```json
885
+ {
886
+ "tool": "chat",
887
+ "arguments": {
888
+ "prompt": "Quick syntax check - is this JavaScript valid?",
889
+ "model": "gpt-5",
890
+ "reasoning_effort": "minimal",
891
+ "temperature": 0.1
892
+ }
893
+ }
894
+ ```
895
+
896
+ ```json
897
+ {
898
+ "tool": "chat",
899
+ "arguments": {
900
+ "prompt": "Design a comprehensive testing strategy for this complex system",
901
+ "model": "gpt-5",
902
+ "files": ["/src/", "/tests/"],
903
+ "reasoning_effort": "max",
904
+ "temperature": 0.1
905
+ }
906
+ }
907
+ ```
908
+
909
+ ## ๐Ÿ”„ Continuation Examples
910
+
911
+ ### Long Research Session
912
+
913
+ ```json
914
+ // First request
915
+ {
916
+ "tool": "chat",
917
+ "arguments": {
918
+ "prompt": "I'm building a real-time chat application. What architecture should I consider?",
919
+ "model": "gpt-5"
920
+ }
921
+ }
922
+
923
+ // Response includes: "continuation": {"id": "conv_research_123"}
924
+
925
+ // Follow-up questions
926
+ {
927
+ "tool": "chat",
928
+ "arguments": {
929
+ "prompt": "What about handling file uploads in real-time?",
930
+ "continuation_id": "conv_research_123"
931
+ }
932
+ }
933
+
934
+ {
935
+ "tool": "chat",
936
+ "arguments": {
937
+ "prompt": "How would you implement message encryption?",
938
+ "continuation_id": "conv_research_123"
939
+ }
940
+ }
941
+ ```
942
+
943
+ ### Iterative Development
944
+
945
+ ```json
946
+ // Initial code review
947
+ {
948
+ "tool": "chat",
949
+ "arguments": {
950
+ "prompt": "Review this API endpoint implementation",
951
+ "model": "gpt-5",
952
+ "files": ["/c/Users/username/src/api/users.js"]
953
+ }
954
+ }
955
+
956
+ // Implementation improvement
957
+ {
958
+ "tool": "chat",
959
+ "arguments": {
960
+ "prompt": "Now help me implement the error handling you suggested",
961
+ "continuation_id": "conv_dev_456",
962
+ "files": ["/c/Users/username/src/api/users.js"]
963
+ }
964
+ }
965
+
966
+ // Testing guidance
967
+ {
968
+ "tool": "chat",
969
+ "arguments": {
970
+ "prompt": "What unit tests should I write for this endpoint?",
971
+ "continuation_id": "conv_dev_456"
972
+ }
973
+ }
974
+ ```
975
+
976
+ ## ๐ŸŽจ Creative & Brainstorming
977
+
978
+ ### Feature Ideation
979
+
980
+ ```json
981
+ {
982
+ "tool": "consensus",
983
+ "arguments": {
984
+ "prompt": "Brainstorm innovative features for a fitness tracking app that would differentiate us from competitors",
985
+ "models": ["grok-4", "gemini-2.5-pro", "gpt-4.1"],
986
+ "temperature": 0.7,
987
+ "cross_feedback_prompt": "Build on each other's ideas and suggest combinations"
988
+ }
989
+ }
990
+ ```
991
+
992
+ ### UI/UX Improvements
993
+
994
+ ```json
995
+ {
996
+ "tool": "chat",
997
+ "arguments": {
998
+ "prompt": "Suggest creative ways to improve user onboarding for this interface",
999
+ "model": "grok-4",
1000
+ "images": ["/c/Users/username/designs/current_onboarding.png"],
1001
+ "temperature": 0.6
1002
+ }
1003
+ }
1004
+ ```
1005
+
1006
+ ## ๐Ÿงช Testing Examples
1007
+
1008
+ ### Test Strategy Planning
1009
+
1010
+ ```json
1011
+ {
1012
+ "tool": "consensus",
1013
+ "arguments": {
1014
+ "prompt": "What testing strategy should we implement for this e-commerce checkout flow?",
1015
+ "models": ["gpt-5", "gemini-2.5-pro", "gemini-2.5-flash"],
1016
+ "files": [
1017
+ "/c/Users/username/src/checkout/payment.js",
1018
+ "/c/Users/username/src/checkout/validation.js",
1019
+ "/c/Users/username/docs/business_requirements.md"
1020
+ ],
1021
+ "temperature": 0.2
1022
+ }
1023
+ }
1024
+ ```
1025
+
1026
+ ### Test Generation
1027
+
1028
+ ```json
1029
+ {
1030
+ "tool": "chat",
1031
+ "arguments": {
1032
+ "prompt": "Generate comprehensive unit tests for this user authentication module",
1033
+ "model": "gemini-2.5-flash",
1034
+ "files": ["/c/Users/username/src/auth/index.js"],
1035
+ "temperature": 0.3
1036
+ }
1037
+ }
1038
+ ```
1039
+
1040
+ ## ๐Ÿ“Š Error Handling Examples
1041
+
1042
+ ### Graceful Degradation
1043
+
1044
+ ```json
1045
+ {
1046
+ "tool": "consensus",
1047
+ "arguments": {
1048
+ "prompt": "One of our models is unavailable, but we still need consensus",
1049
+ "models": ["available-model-1", "available-model-2"],
1050
+ "temperature": 0.2
1051
+ }
1052
+ }
1053
+ ```
1054
+
1055
+ ### Partial Success Response
1056
+
1057
+ ```json
1058
+ {
1059
+ "status": "consensus_partial",
1060
+ "models_consulted": 2,
1061
+ "successful_initial_responses": 2,
1062
+ "failed_responses": 1,
1063
+ "failed_models": ["unavailable-model"],
1064
+ "phases": {
1065
+ "initial": [...],
1066
+ "refined": [...],
1067
+ "failed": [
1068
+ {
1069
+ "model": "unavailable-model",
1070
+ "error": "Provider not available. Check API key configuration.",
1071
+ "status": "failed"
1072
+ }
1073
+ ]
1074
+ }
1075
+ }
1076
+ ```
1077
+
1078
+ ## ๐Ÿ”ง Integration Examples
1079
+
1080
+ ### CI/CD Pipeline Integration
1081
+
1082
+ ```bash
1083
+ # Use in GitHub Actions
1084
+ - name: Code Review
1085
+ run: |
1086
+ echo '{
1087
+ "tool": "chat",
1088
+ "arguments": {
1089
+ "prompt": "Review this pull request for security issues and best practices",
1090
+ "model": "gpt-5",
1091
+ "files": ["/c/Users/username/src/modified-file.js"],
1092
+ "reasoning_effort": "high"
1093
+ }
1094
+ }' | npx converse-mcp-server
1095
+ ```
1096
+
1097
+ ### Automated Documentation
1098
+
1099
+ ```bash
1100
+ # Generate documentation
1101
+ echo '{
1102
+ "tool": "chat",
1103
+ "arguments": {
1104
+ "prompt": "Generate API documentation for these endpoints",
1105
+ "model": "gemini-2.5-flash",
1106
+ "files": ["/c/Users/username/src/api/routes.js"]
1107
+ }
1108
+ }' | npx converse-mcp-server > /c/Users/username/docs/api.md
1109
+ ```
1110
+
1111
+ ---
1112
+
1113
1113
  These examples demonstrate the flexibility and power of the Converse MCP Server across various development scenarios, from simple queries to complex multi-model consensus gathering.