@last9/mcp-server 0.2.0 → 0.5.0

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/dist/README.md DELETED
@@ -1,604 +0,0 @@
1
- # Last9 MCP Server
2
-
3
- ![last9 mcp demo](mcp-demo.gif)
4
-
5
- A [Model Context Protocol](https://modelcontextprotocol.io/) server
6
- implementation for [Last9](https://last9.io/mcp/) that enables AI agents to
7
- seamlessly bring real-time production context — logs, metrics, and traces — into
8
- your local environment to auto-fix code faster.
9
-
10
- - [View demo](https://www.youtube.com/watch?v=AQH5xq6qzjI)
11
- - Read our
12
- [announcement blog post](https://last9.io/blog/launching-last9-mcp-server/)
13
-
14
- ## Status
15
-
16
- Works with Claude desktop app, or Cursor, Windsurf, and VSCode (Github Copilot)
17
- IDEs. Implements the following MCP
18
- [tools](https://modelcontextprotocol.io/docs/concepts/tools):
19
-
20
- **Observability & APM Tools:**
21
-
22
- - `get_exceptions`: Get the list of exceptions.
23
- - `get_service_summary`: Get service summary with throughput, error rate, and response time.
24
- - `get_service_environments`: Get available environments for services.
25
- - `get_service_performance_details`: Get detailed performance metrics for a service.
26
- - `get_service_operations_summary`: Get operations summary for a service.
27
- - `get_service_dependency_graph`: Get service dependency graph showing incoming/outgoing dependencies.
28
-
29
- **Prometheus/PromQL Tools:**
30
-
31
- - `promptheus_range_query`: Execute PromQL range queries for metrics data.
32
- - `prometheus_instant_query`: Execute PromQL instant queries for metrics data.
33
- - `prometheus_label_values`: Get label values for PromQL queries.
34
- - `prometheus_labels`: Get available labels for PromQL queries.
35
-
36
- **Logs Management:**
37
-
38
- - `get_logs`: Get logs filtered by service name and/or severity level.
39
- - `get_drop_rules`: Get drop rules for logs that determine what logs get
40
- filtered out at [Last9 Control Plane](https://last9.io/control-plane)
41
- - `add_drop_rule`: Create a drop rule for logs at
42
- [Last9 Control Plane](https://last9.io/control-plane)
43
- - `get_service_logs`: Get raw log entries for a specific service over a time range. Can apply filters on severity and body.
44
-
45
- **Traces Management:**
46
-
47
- - `get_service_traces`: Query traces for a specific service with filtering options for span kinds, status codes, and other trace attributes.
48
-
49
- **Alert Management:**
50
-
51
- - `get_alert_config`: Get alert configurations (alert rules) from Last9.
52
- - `get_alerts`: Get currently active alerts from Last9 monitoring system.
53
-
54
- ## Tools Documentation
55
-
56
- ### get_exceptions
57
-
58
- Retrieves server-side exceptions over a specified time range.
59
-
60
- Parameters:
61
-
62
- - `limit` (integer, optional): Maximum number of exceptions to return.
63
- Default: 20.
64
- - `lookback_minutes` (integer, recommended): Number of minutes to look back from
65
- now. Default: 60. Examples: 60, 30, 15.
66
- - `start_time_iso` (string, optional): Start time in ISO format (YYYY-MM-DD
67
- HH:MM:SS). Leave empty to use lookback_minutes.
68
- - `end_time_iso` (string, optional): End time in ISO format (YYYY-MM-DD
69
- HH:MM:SS). Leave empty to default to current time.
70
- - `span_name` (string, optional): Name of the span to filter by.
71
-
72
- ### get_service_summary
73
-
74
- Get service summary over a given time range. Includes service name, environment, throughput, error rate, and response time. All values are p95 quantiles over the time range.
75
-
76
- Parameters:
77
-
78
- - `start_time_iso` (string, optional): Start time in ISO format (YYYY-MM-DD HH:MM:SS). Leave empty to default to end_time_iso - 1 hour.
79
- - `end_time_iso` (string, optional): End time in ISO format (YYYY-MM-DD HH:MM:SS). Leave empty to default to current time.
80
- - `env` (string, optional): Environment to filter by. Defaults to 'prod'.
81
-
82
- ### get_service_environments
83
-
84
- Get available environments for services. Returns an array of environments that can be used with other APM tools.
85
-
86
- Parameters:
87
-
88
- - `start_time_iso` (string, optional): Start time in ISO format (YYYY-MM-DD HH:MM:SS). Leave empty to default to end_time_iso - 1 hour.
89
- - `end_time_iso` (string, optional): End time in ISO format (YYYY-MM-DD HH:MM:SS). Leave empty to default to current time.
90
-
91
- Note: All other APM tools that retrieve service information (like `get_service_performance_details`, `get_service_dependency_graph`, `get_service_operations_summary`, `get_service_summary`) require an `env` parameter. This parameter must be one of the environments returned by this tool. If this tool returns an empty array, use an empty string `""` for the env parameter.
92
-
93
- ### get_service_performance_details
94
-
95
- Get detailed performance metrics for a specific service over a given time range.
96
-
97
- Parameters:
98
-
99
- - `service_name` (string, required): Name of the service to get performance details for.
100
- - `start_time_iso` (string, optional): Start time in ISO format (YYYY-MM-DD HH:MM:SS). Leave empty to default to now - 60 minutes.
101
- - `end_time_iso` (string, optional): End time in ISO format (YYYY-MM-DD HH:MM:SS). Leave empty to default to current time.
102
- - `env` (string, optional): Environment to filter by. Defaults to 'prod'.
103
-
104
- ### get_service_operations_summary
105
-
106
- Get a summary of operations inside a service over a given time range. Returns operations like HTTP endpoints, database queries, messaging producer and HTTP client calls.
107
-
108
- Parameters:
109
-
110
- - `service_name` (string, required): Name of the service to get operations summary for.
111
- - `start_time_iso` (string, optional): Start time in ISO format (YYYY-MM-DD HH:MM:SS). Leave empty to default to now - 60 minutes.
112
- - `end_time_iso` (string, optional): End time in ISO format (YYYY-MM-DD HH:MM:SS). Leave empty to default to current time.
113
- - `env` (string, optional): Environment to filter by. Defaults to 'prod'.
114
-
115
- ### get_service_dependency_graph
116
-
117
- Get details of the throughput, response times and error rates of incoming, outgoing and infrastructure components of a service. Useful for analyzing cascading effects of errors and performance issues.
118
-
119
- Parameters:
120
-
121
- - `service_name` (string, optional): Name of the service to get the dependency graph for.
122
- - `start_time_iso` (string, optional): Start time in ISO format (YYYY-MM-DD HH:MM:SS). Leave empty to default to now - 60 minutes.
123
- - `end_time_iso` (string, optional): End time in ISO format (YYYY-MM-DD HH:MM:SS). Leave empty to default to current time.
124
- - `env` (string, optional): Environment to filter by. Defaults to 'prod'.
125
-
126
- ### promptheus_range_query
127
-
128
- Perform a Prometheus range query to get metrics data over a specified time range. Recommended to check available labels first using `prometheus_labels` tool.
129
-
130
- Parameters:
131
-
132
- - `query` (string, required): The range query to execute.
133
- - `start_time_iso` (string, optional): Start time in ISO format (YYYY-MM-DD HH:MM:SS). Leave empty to default to now - 60 minutes.
134
- - `end_time_iso` (string, optional): End time in ISO format (YYYY-MM-DD HH:MM:SS). Leave empty to default to current time.
135
-
136
- ### prometheus_instant_query
137
-
138
- Perform a Prometheus instant query to get metrics data at a specific point in time. Typically should use rollup functions like sum_over_time, avg_over_time, quantile_over_time over a time window.
139
-
140
- Parameters:
141
-
142
- - `query` (string, required): The instant query to execute.
143
- - `time_iso` (string, optional): Time in ISO format (YYYY-MM-DD HH:MM:SS). Leave empty to default to current time.
144
-
145
- ### prometheus_label_values
146
-
147
- Return the label values for a particular label and PromQL filter query. Similar to Prometheus /label_values call.
148
-
149
- Parameters:
150
-
151
- - `match_query` (string, required): A valid PromQL filter query.
152
- - `label` (string, required): The label to get values for.
153
- - `start_time_iso` (string, optional): Start time in ISO format (YYYY-MM-DD HH:MM:SS). Leave empty to default to now - 60 minutes.
154
- - `end_time_iso` (string, optional): End time in ISO format (YYYY-MM-DD HH:MM:SS). Leave empty to default to current time.
155
-
156
- ### prometheus_labels
157
-
158
- Return the labels for a given PromQL match query. Similar to Prometheus /labels call.
159
-
160
- Parameters:
161
-
162
- - `match_query` (string, required): A valid PromQL filter query.
163
- - `start_time_iso` (string, optional): Start time in ISO format (YYYY-MM-DD HH:MM:SS). Leave empty to default to now - 60 minutes.
164
- - `end_time_iso` (string, optional): End time in ISO format (YYYY-MM-DD HH:MM:SS). Leave empty to default to current time.
165
-
166
- ### get_logs
167
-
168
- Gets logs filtered by service name and/or severity level within a specified time range. This tool now uses the advanced v2 logs API with physical index optimization for better performance.
169
-
170
- **Note**: This tool now requires a `service_name` parameter and internally uses the same advanced infrastructure as `get_service_logs`.
171
-
172
- Parameters:
173
-
174
- - `service_name` (string, required): Name of the service to get logs for.
175
- - `severity` (string, optional): Severity of the logs to get (automatically converted to severity_filters format).
176
- - `lookback_minutes` (integer, recommended): Number of minutes to look back from now. Default: 60. Examples: 60, 30, 15.
177
- - `start_time_iso` (string, optional): Start time in ISO format (YYYY-MM-DD HH:MM:SS). Leave empty to use lookback_minutes.
178
- - `end_time_iso` (string, optional): End time in ISO format (YYYY-MM-DD HH:MM:SS). Leave empty to default to current time.
179
- - `limit` (integer, optional): Maximum number of logs to return. Default: 20.
180
- - `env` (string, optional): Environment to filter by. Use "get_service_environments" tool to get available environments.
181
-
182
- ### get_drop_rules
183
-
184
- Gets drop rules for logs, which determine what logs get filtered out from
185
- reaching Last9.
186
-
187
- ### add_drop_rule
188
-
189
- Adds a new drop rule to filter out specific logs at
190
- [Last9 Control Plane](https://last9.io/control-plane)
191
-
192
- Parameters:
193
-
194
- - `name` (string, required): Name of the drop rule.
195
- - `filters` (array, required): List of filter conditions to apply. Each filter
196
- has:
197
- - `key` (string, required): The key to filter on. Only attributes and
198
- resource.attributes keys are supported. For resource attributes, use format:
199
- resource.attributes[key_name] and for log attributes, use format:
200
- attributes[key_name] Double quotes in key names must be escaped.
201
- - `value` (string, required): The value to filter against.
202
- - `operator` (string, required): The operator used for filtering. Valid
203
- values:
204
- - "equals"
205
- - "not_equals"
206
- - `conjunction` (string, required): The logical conjunction between filters.
207
- Valid values:
208
- - "and"
209
-
210
- ### get_alert_config
211
-
212
- Get alert configurations (alert rules) from Last9. Returns all configured alert rules including their conditions, labels, and annotations.
213
-
214
- Parameters:
215
-
216
- None - This tool retrieves all available alert configurations.
217
-
218
- Returns information about:
219
-
220
- - Alert rule ID and name
221
- - Primary indicator being monitored
222
- - Current state and severity
223
- - Algorithm used for alerting
224
- - Entity ID and organization details
225
- - Properties and configuration
226
- - Creation and update timestamps
227
- - Group timeseries notification settings
228
-
229
- ### get_alerts
230
-
231
- Get currently active alerts from Last9 monitoring system. Returns all alerts that are currently firing or have fired recently within the specified time window.
232
-
233
- Parameters:
234
-
235
- - `timestamp` (integer, optional): Unix timestamp for the query time. Leave empty to default to current time.
236
- - `window` (integer, optional): Time window in seconds to look back for alerts. Defaults to 900 seconds (15 minutes). Range: 60-86400 seconds.
237
-
238
- Returns information about:
239
-
240
- - Alert rule details (ID, name, group, type)
241
- - Current state and severity
242
- - Last fired timestamp and duration
243
- - Rule properties and configuration
244
- - Alert instances with current values
245
- - Metric degradation information
246
- - Group labels and annotations for each instance
247
-
248
- ### get_service_logs
249
-
250
- Get raw log entries for a specific service over a time range. This tool retrieves actual log entries including log messages, timestamps, severity levels, and other metadata. Useful for debugging issues, monitoring service behavior, and analyzing specific log patterns.
251
-
252
- Parameters:
253
-
254
- - `service_name` (string, required): Name of the service to get logs for.
255
- - `lookback_minutes` (integer, optional): Number of minutes to look back from now. Default: 60 minutes. Examples: 60, 30, 15.
256
- - `limit` (integer, optional): Maximum number of log entries to return. Default: 20.
257
- - `env` (string, optional): Environment to filter by. Use "get_service_environments" tool to get available environments.
258
- - `severity_filters` (array, optional): Array of severity patterns to filter logs (e.g., ["error", "warn"]). Uses OR logic.
259
- - `body_filters` (array, optional): Array of message content patterns to filter logs (e.g., ["timeout", "failed"]). Uses OR logic.
260
- - `start_time_iso` (string, optional): Start time in ISO format (YYYY-MM-DD HH:MM:SS). Leave empty to default to now - lookback_minutes.
261
- - `end_time_iso` (string, optional): End time in ISO format (YYYY-MM-DD HH:MM:SS). Leave empty to default to current time.
262
-
263
- Filtering behavior:
264
- - Multiple filter types are combined with AND logic (service AND severity AND body)
265
- - Each filter array uses OR logic (matches any pattern in the array)
266
-
267
- Examples:
268
- - service_name="api" + severity_filters=["error"] + body_filters=["timeout"] → finds error logs containing "timeout"
269
- - service_name="web" + body_filters=["timeout", "failed", "error 500"] → finds logs containing any of these patterns
270
-
271
- ### get_service_traces
272
-
273
- Query traces for a specific service with filtering options for span kinds, status codes, and other trace attributes. This tool retrieves distributed tracing data for debugging performance issues, understanding request flows, and analyzing service interactions.
274
-
275
- Parameters:
276
-
277
- - `service_name` (string, required): Name of the service to get traces for.
278
- - `lookback_minutes` (integer, optional): Number of minutes to look back from now. Default: 60 minutes. Examples: 60, 30, 15.
279
- - `limit` (integer, optional): Maximum number of traces to return. Default: 10.
280
- - `env` (string, optional): Environment to filter by. Use "get_service_environments" tool to get available environments.
281
- - `span_kind` (array, optional): Filter by span types (server, client, internal, consumer, producer).
282
- - `span_name` (string, optional): Filter by specific span name.
283
- - `status_code` (array, optional): Filter by trace status (ok, error, unset, success).
284
- - `order` (string, optional): Field to order traces by. Default: "Duration". Options: Duration, Timestamp.
285
- - `direction` (string, optional): Sort direction. Default: "backward". Options: forward, backward.
286
- - `start_time_iso` (string, optional): Start time in ISO format (YYYY-MM-DD HH:MM:SS). Leave empty to default to now - lookback_minutes.
287
- - `end_time_iso` (string, optional): End time in ISO format (YYYY-MM-DD HH:MM:SS). Leave empty to default to current time.
288
-
289
- Filtering options:
290
- - Combine multiple filters to narrow down specific traces of interest
291
- - Use time range filters with lookback_minutes or explicit start/end times
292
-
293
- Examples:
294
- - service_name="api" + span_kind=["server"] + status_code=["error"] → finds failed server-side traces
295
- - service_name="payment" + span_name="process_payment" + lookback_minutes=30 → finds payment processing traces from last 30 minutes
296
-
297
- ## Installation
298
-
299
- You can install the Last9 Observability MCP server using either:
300
-
301
- ### Homebrew
302
-
303
- ```bash
304
- # Add the Last9 tap
305
- brew tap last9/tap
306
-
307
- # Install the Last9 MCP CLI
308
- brew install last9-mcp
309
- ```
310
-
311
- ### NPM
312
-
313
- ```bash
314
- # Install globally
315
- npm install -g @last9/mcp-server
316
-
317
- # Or run directly with npx
318
- npx @last9/mcp-server
319
- ```
320
-
321
- ## Configuration
322
-
323
- ### Environment Variables
324
-
325
- The Last9 MCP server requires the following environment variables:
326
-
327
- - `LAST9_BASE_URL`: (required) Last9 API URL from
328
- [OTel integration](https://app.last9.io/integrations?integration=OpenTelemetry)
329
- - `LAST9_AUTH_TOKEN`: (required) Authentication token for Last9 MCP server from
330
- [OTel integration](https://app.last9.io/integrations?integration=OpenTelemetry)
331
- - `LAST9_REFRESH_TOKEN`: (required) Refresh Token with Write permissions, needed
332
- for accessing control plane APIs from
333
- [API Access](https://app.last9.io/settings/api-access)
334
-
335
- ## Usage with Claude Desktop
336
-
337
- Configure the Claude app to use the MCP server:
338
-
339
- 1. Open the Claude Desktop app, go to Settings, then Developer
340
- 2. Click Edit Config
341
- 3. Open the `claude_desktop_config.json` file
342
- 4. Copy and paste the server config to your existing file, then save
343
- 5. Restart Claude
344
-
345
- ### If installed via Homebrew:
346
- ```json
347
- {
348
- "mcpServers": {
349
- "last9": {
350
- "command": "/opt/homebrew/bin/last9-mcp",
351
- "env": {
352
- "LAST9_BASE_URL": "<last9_otlp_host>",
353
- "LAST9_AUTH_TOKEN": "<last9_otlp_auth_token>",
354
- "LAST9_REFRESH_TOKEN": "<last9_write_refresh_token>"
355
- }
356
- }
357
- }
358
- }
359
- ```
360
-
361
- ### If installed via NPM:
362
- ```json
363
- {
364
- "mcpServers": {
365
- "last9": {
366
- "command": "npx",
367
- "args": ["-y", "@last9/mcp-server"],
368
- "env": {
369
- "LAST9_BASE_URL": "<last9_otlp_host>",
370
- "LAST9_AUTH_TOKEN": "<last9_otlp_auth_token>",
371
- "LAST9_REFRESH_TOKEN": "<last9_write_refresh_token>"
372
- }
373
- }
374
- }
375
- }
376
- ```
377
-
378
- ## Usage with Cursor
379
-
380
- Configure Cursor to use the MCP server:
381
-
382
- 1. Open Cursor, go to Settings, then Cursor Settings
383
- 2. Select MCP on the left
384
- 3. Click Add "New Global MCP Server" at the top right
385
- 4. Copy and paste the server config to your existing file, then save
386
- 5. Restart Cursor
387
-
388
- ### If installed via Homebrew:
389
- ```json
390
- {
391
- "mcpServers": {
392
- "last9": {
393
- "command": "/opt/homebrew/bin/last9-mcp",
394
- "env": {
395
- "LAST9_BASE_URL": "<last9_otlp_host>",
396
- "LAST9_AUTH_TOKEN": "<last9_otlp_auth_token>",
397
- "LAST9_REFRESH_TOKEN": "<last9_write_refresh_token>"
398
- }
399
- }
400
- }
401
- }
402
- ```
403
-
404
- ### If installed via NPM:
405
- ```json
406
- {
407
- "mcpServers": {
408
- "last9": {
409
- "command": "npx",
410
- "args": ["-y", "@last9/mcp-server"],
411
- "env": {
412
- "LAST9_BASE_URL": "<last9_otlp_host>",
413
- "LAST9_AUTH_TOKEN": "<last9_otlp_auth_token>",
414
- "LAST9_REFRESH_TOKEN": "<last9_write_refresh_token>"
415
- }
416
- }
417
- }
418
- }
419
- ```
420
-
421
- ## Usage with Windsurf
422
-
423
- Configure Windsurf to use the MCP server:
424
-
425
- 1. Open Windsurf, go to Settings, then Developer
426
- 2. Click Edit Config
427
- 3. Open the `windsurf_config.json` file
428
- 4. Copy and paste the server config to your existing file, then save
429
- 5. Restart Windsurf
430
-
431
- ### If installed via Homebrew:
432
- ```json
433
- {
434
- "mcpServers": {
435
- "last9": {
436
- "command": "/opt/homebrew/bin/last9-mcp",
437
- "env": {
438
- "LAST9_BASE_URL": "<last9_otlp_host>",
439
- "LAST9_AUTH_TOKEN": "<last9_otlp_auth_token>",
440
- "LAST9_REFRESH_TOKEN": "<last9_write_refresh_token>"
441
- }
442
- }
443
- }
444
- }
445
- ```
446
-
447
- ### If installed via NPM:
448
- ```json
449
- {
450
- "mcpServers": {
451
- "last9": {
452
- "command": "npx",
453
- "args": ["-y", "@last9/mcp-server"],
454
- "env": {
455
- "LAST9_BASE_URL": "<last9_otlp_host>",
456
- "LAST9_AUTH_TOKEN": "<last9_otlp_auth_token>",
457
- "LAST9_REFRESH_TOKEN": "<last9_write_refresh_token>"
458
- }
459
- }
460
- }
461
- }
462
- ```
463
-
464
- ## Usage with VS Code
465
-
466
- > Note: MCP support in VS Code is available starting v1.99 and is currently in
467
- > preview. For advanced configuration options and alternative setup methods,
468
- > [view the VS Code MCP documentation](https://code.visualstudio.com/docs/copilot/chat/mcp-servers).
469
-
470
- 1. Open VS Code, go to Settings, select the User tab, then Features, then Chat
471
- 2. Click "Edit settings.json"
472
- 3. Copy and paste the server config to your existing file, then save
473
- 4. Restart VS Code
474
-
475
- ### If installed via Homebrew:
476
- ```json
477
- {
478
- "mcp": {
479
- "servers": {
480
- "last9": {
481
- "type": "stdio",
482
- "command": "/opt/homebrew/bin/last9-mcp",
483
- "env": {
484
- "LAST9_BASE_URL": "<last9_otlp_host>",
485
- "LAST9_AUTH_TOKEN": "<last9_otlp_auth_token>",
486
- "LAST9_REFRESH_TOKEN": "<last9_write_refresh_token>"
487
- }
488
- }
489
- }
490
- }
491
- }
492
- ```
493
-
494
- ### If installed via NPM:
495
- ```json
496
- {
497
- "mcp": {
498
- "servers": {
499
- "last9": {
500
- "type": "stdio",
501
- "command": "npx",
502
- "args": ["-y", "@last9/mcp-server"],
503
- "env": {
504
- "LAST9_BASE_URL": "<last9_otlp_host>",
505
- "LAST9_AUTH_TOKEN": "<last9_otlp_auth_token>",
506
- "LAST9_REFRESH_TOKEN": "<last9_write_refresh_token>"
507
- }
508
- }
509
- }
510
- }
511
- }
512
- ```
513
-
514
- ## Development
515
-
516
- For local development and testing, you can run the MCP server in HTTP mode which makes it easier to debug requests and responses.
517
-
518
- ### Running in HTTP Mode
519
-
520
- Set the `HTTP_MODE` environment variable to enable HTTP server mode:
521
-
522
- ```bash
523
- # Export required environment variables
524
- export LAST9_API_TOKEN="your_api_token"
525
- export LAST9_BASE_URL="https://your-last9-endpoint" # Your Last9 endpoint
526
- export HTTP_MODE=true
527
- export HTTP_PORT=8080 # Optional, defaults to 8080
528
-
529
- # Run the server
530
- ./last9-mcp-server
531
- ```
532
-
533
- The server will start on `http://localhost:8080/mcp` and you can test it with curl:
534
-
535
- ### Testing with curl
536
-
537
- ```bash
538
- # Test get_service_logs
539
- curl -X POST http://localhost:8080/mcp \
540
- -H "Content-Type: application/json" \
541
- -H "Mcp-Session-Id: session_$(date +%s)000000000" \
542
- -d '{
543
- "jsonrpc": "2.0",
544
- "id": 1,
545
- "method": "tools/call",
546
- "params": {
547
- "name": "get_service_logs",
548
- "arguments": {
549
- "service_name": "your-service-name",
550
- "lookback_minutes": 30,
551
- "limit": 10
552
- }
553
- }
554
- }'
555
-
556
- # Test get_service_traces
557
- curl -X POST http://localhost:8080/mcp \
558
- -H "Content-Type: application/json" \
559
- -H "Mcp-Session-Id: session_$(date +%s)000000000" \
560
- -d '{
561
- "jsonrpc": "2.0",
562
- "id": 2,
563
- "method": "tools/call",
564
- "params": {
565
- "name": "get_service_traces",
566
- "arguments": {
567
- "service_name": "your-service-name",
568
- "lookback_minutes": 60,
569
- "limit": 5
570
- }
571
- }
572
- }'
573
-
574
- # List available tools
575
- curl -X POST http://localhost:8080/mcp \
576
- -H "Content-Type: application/json" \
577
- -H "Mcp-Session-Id: session_$(date +%s)000000000" \
578
- -d '{
579
- "jsonrpc": "2.0",
580
- "id": 3,
581
- "method": "tools/list",
582
- "params": {}
583
- }'
584
- ```
585
-
586
- ### Building from Source
587
-
588
- ```bash
589
- # Clone the repository
590
- git clone https://github.com/last9/last9-mcp-server.git
591
- cd last9-mcp-server
592
-
593
- # Build the binary
594
- go build -o last9-mcp-server
595
-
596
- # Run in development mode
597
- HTTP_MODE=true ./last9-mcp-server
598
- ```
599
-
600
- **Note**: HTTP mode is for development and testing only. When integrating with Claude Desktop or other MCP clients, use the default STDIO mode (without `HTTP_MODE=true`).
601
-
602
- ## Badges
603
-
604
- [![MseeP.ai Security Assessment Badge](https://mseep.net/pr/last9-last9-mcp-server-badge.png)](https://mseep.ai/app/last9-last9-mcp-server)
Binary file