@kryptosai/mcp-observatory 1.33.0 → 1.34.0

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.
Files changed (107) hide show
  1. package/README.md +8 -121
  2. package/dist/src/auth.d.ts +22 -0
  3. package/dist/src/auth.js +140 -0
  4. package/dist/src/auth.js.map +1 -0
  5. package/dist/src/cli.js +48 -3
  6. package/dist/src/cli.js.map +1 -1
  7. package/dist/src/commands/demo.d.ts +2 -0
  8. package/dist/src/commands/demo.js +247 -0
  9. package/dist/src/commands/demo.js.map +1 -0
  10. package/dist/src/commands/helpers.d.ts +11 -0
  11. package/dist/src/commands/helpers.js +26 -0
  12. package/dist/src/commands/helpers.js.map +1 -1
  13. package/dist/src/commands/init-ci.d.ts +1 -0
  14. package/dist/src/commands/init-ci.js +157 -10
  15. package/dist/src/commands/init-ci.js.map +1 -1
  16. package/dist/src/commands/receipt.js +13 -3
  17. package/dist/src/commands/receipt.js.map +1 -1
  18. package/dist/src/commands/scan.js +10 -1
  19. package/dist/src/commands/scan.js.map +1 -1
  20. package/dist/src/commands/setup-ci-conversion.js +4 -4
  21. package/dist/src/commands/setup-ci-conversion.js.map +1 -1
  22. package/dist/src/commands/test.js +9 -1
  23. package/dist/src/commands/test.js.map +1 -1
  24. package/dist/src/commercial.d.ts +3 -0
  25. package/dist/src/commercial.js +12 -1
  26. package/dist/src/commercial.js.map +1 -1
  27. package/dist/src/index.d.ts +1 -1
  28. package/dist/src/index.js +1 -1
  29. package/dist/src/index.js.map +1 -1
  30. package/dist/src/receipt.d.ts +9 -0
  31. package/dist/src/receipt.js +24 -1
  32. package/dist/src/receipt.js.map +1 -1
  33. package/dist/src/telemetry.js +4 -0
  34. package/dist/src/telemetry.js.map +1 -1
  35. package/dist/src/utils/failure-diagnosis.d.ts +7 -0
  36. package/dist/src/utils/failure-diagnosis.js +14 -0
  37. package/dist/src/utils/failure-diagnosis.js.map +1 -1
  38. package/docs/mcp-server-safety-index.md +1 -1
  39. package/docs/safety-index/artifacts/antv-chart-server.json +21 -21
  40. package/docs/safety-index/artifacts/antv-chart-server.md +10 -10
  41. package/docs/safety-index/artifacts/browsermcp-server.json +18 -18
  42. package/docs/safety-index/artifacts/browsermcp-server.md +9 -9
  43. package/docs/safety-index/artifacts/chrome-devtools-mcp-server.json +19 -19
  44. package/docs/safety-index/artifacts/chrome-devtools-mcp-server.md +9 -9
  45. package/docs/safety-index/artifacts/cloudflare-server.json +4 -4
  46. package/docs/safety-index/artifacts/cloudflare-server.md +4 -4
  47. package/docs/safety-index/artifacts/context7-server.json +18 -18
  48. package/docs/safety-index/artifacts/context7-server.md +10 -10
  49. package/docs/safety-index/artifacts/cyanheads-git-mcp-server.json +34 -34
  50. package/docs/safety-index/artifacts/cyanheads-git-mcp-server.md +15 -15
  51. package/docs/safety-index/artifacts/everything-server.json +18 -18
  52. package/docs/safety-index/artifacts/everything-server.md +11 -11
  53. package/docs/safety-index/artifacts/executeautomation-playwright-server.json +19 -19
  54. package/docs/safety-index/artifacts/executeautomation-playwright-server.md +11 -11
  55. package/docs/safety-index/artifacts/filesystem-mcp-server.json +19 -19
  56. package/docs/safety-index/artifacts/filesystem-mcp-server.md +10 -10
  57. package/docs/safety-index/artifacts/filesystem-server.json +19 -19
  58. package/docs/safety-index/artifacts/filesystem-server.md +10 -10
  59. package/docs/safety-index/artifacts/github-mcp-server.json +18 -18
  60. package/docs/safety-index/artifacts/github-mcp-server.md +9 -9
  61. package/docs/safety-index/artifacts/google-drive-server.json +4 -4
  62. package/docs/safety-index/artifacts/google-drive-server.md +4 -4
  63. package/docs/safety-index/artifacts/kubernetes-server.json +23 -23
  64. package/docs/safety-index/artifacts/kubernetes-server.md +15 -15
  65. package/docs/safety-index/artifacts/memory-server.json +18 -18
  66. package/docs/safety-index/artifacts/memory-server.md +10 -10
  67. package/docs/safety-index/artifacts/mongodb-server.json +4 -4
  68. package/docs/safety-index/artifacts/mongodb-server.md +4 -4
  69. package/docs/safety-index/artifacts/opentofu-server.json +18 -18
  70. package/docs/safety-index/artifacts/opentofu-server.md +9 -9
  71. package/docs/safety-index/artifacts/playwright-mcp-server.json +18 -18
  72. package/docs/safety-index/artifacts/playwright-mcp-server.md +9 -9
  73. package/docs/safety-index/artifacts/promptopia-server.json +21 -21
  74. package/docs/safety-index/artifacts/promptopia-server.md +11 -11
  75. package/docs/safety-index/artifacts/puppeteer-server.json +18 -18
  76. package/docs/safety-index/artifacts/puppeteer-server.md +9 -9
  77. package/docs/safety-index/artifacts/qdrant-server.json +4 -4
  78. package/docs/safety-index/artifacts/qdrant-server.md +4 -4
  79. package/docs/safety-index/artifacts/ref-tools-server.json +18 -18
  80. package/docs/safety-index/artifacts/ref-tools-server.md +10 -10
  81. package/docs/safety-index/artifacts/sequential-thinking-server.json +18 -18
  82. package/docs/safety-index/artifacts/sequential-thinking-server.md +8 -8
  83. package/docs/safety-index/artifacts/slack-server.json +3 -3
  84. package/docs/safety-index/artifacts/slack-server.md +2 -2
  85. package/docs/safety-index/artifacts/ui5-mcp-server.json +18 -18
  86. package/docs/safety-index/artifacts/ui5-mcp-server.md +9 -9
  87. package/docs/safety-index/artifacts/vercel-ai-server.json +4 -4
  88. package/docs/safety-index/artifacts/vercel-ai-server.md +4 -4
  89. package/package.json +2 -2
  90. package/dist/src/adapters/base.d.ts +0 -14
  91. package/dist/src/adapters/base.js +0 -2
  92. package/dist/src/adapters/base.js.map +0 -1
  93. package/dist/src/checks/semantics.d.ts +0 -2
  94. package/dist/src/checks/semantics.js +0 -48
  95. package/dist/src/checks/semantics.js.map +0 -1
  96. package/dist/src/diff/diff.d.ts +0 -2
  97. package/dist/src/diff/diff.js +0 -81
  98. package/dist/src/diff/diff.js.map +0 -1
  99. package/dist/src/reporters/json.d.ts +0 -2
  100. package/dist/src/reporters/json.js +0 -4
  101. package/dist/src/reporters/json.js.map +0 -1
  102. package/dist/src/runner/runner.d.ts +0 -2
  103. package/dist/src/runner/runner.js +0 -135
  104. package/dist/src/runner/runner.js.map +0 -1
  105. package/dist/src/storage/filesystem.d.ts +0 -6
  106. package/dist/src/storage/filesystem.js +0 -21
  107. package/dist/src/storage/filesystem.js.map +0 -1
@@ -2,9 +2,9 @@
2
2
  "artifactType": "run",
3
3
  "schemaVersion": "1.0.0",
4
4
  "gate": "pass",
5
- "runId": "run_2026-07-15T223319237Z_baafc299",
6
- "createdAt": "2026-07-15T22:33:19.237Z",
7
- "toolVersion": "1.32.1",
5
+ "runId": "run_2026-07-17T003623563Z_bf28dbdf",
6
+ "createdAt": "2026-07-17T00:36:23.563Z",
7
+ "toolVersion": "1.33.0",
8
8
  "target": {
9
9
  "targetId": "promptopia-server",
10
10
  "adapter": "local-process",
@@ -43,7 +43,7 @@
43
43
  "id": "tools",
44
44
  "capability": "tools",
45
45
  "status": "pass",
46
- "durationMs": 2.1864580000001297,
46
+ "durationMs": 5.427625000000262,
47
47
  "message": "Advertised capability responded with the minimal expected shape (7 items).",
48
48
  "evidence": [
49
49
  {
@@ -62,7 +62,7 @@
62
62
  "add_multi_message_prompt"
63
63
  ],
64
64
  "diagnostics": [
65
- "Watching for changes in prompts directory: /Users/williamweishuhn/Documents/New project/mcp-observatory/examples/promptopia-prompts",
65
+ "Watching for changes in prompts directory: /Users/williamweishuhn/Documents/GitHub/mcp-observatory/examples/promptopia-prompts",
66
66
  "promptopia-mcp MCP server running (v1.1.0)"
67
67
  ],
68
68
  "schemas": {
@@ -267,7 +267,7 @@
267
267
  "id": "prompts",
268
268
  "capability": "prompts",
269
269
  "status": "pass",
270
- "durationMs": 1.1239580000001297,
270
+ "durationMs": 1.8686659999993935,
271
271
  "message": "Advertised capability responded with the minimal expected shape (1 item).",
272
272
  "evidence": [
273
273
  {
@@ -280,7 +280,7 @@
280
280
  "demo_welcome"
281
281
  ],
282
282
  "diagnostics": [
283
- "Watching for changes in prompts directory: /Users/williamweishuhn/Documents/New project/mcp-observatory/examples/promptopia-prompts",
283
+ "Watching for changes in prompts directory: /Users/williamweishuhn/Documents/GitHub/mcp-observatory/examples/promptopia-prompts",
284
284
  "promptopia-mcp MCP server running (v1.1.0)"
285
285
  ]
286
286
  }
@@ -290,7 +290,7 @@
290
290
  "id": "resources",
291
291
  "capability": "resources",
292
292
  "status": "unsupported",
293
- "durationMs": 0.0029999999997016857,
293
+ "durationMs": 0.0031249999992724042,
294
294
  "message": "Resources are not advertised by the target.",
295
295
  "evidence": [
296
296
  {
@@ -306,7 +306,7 @@
306
306
  "id": "security-lite",
307
307
  "capability": "security-lite",
308
308
  "status": "pass",
309
- "durationMs": 0.026875000000472937,
309
+ "durationMs": 0.02679199999965931,
310
310
  "message": "No security issues detected (lightweight scan).",
311
311
  "evidence": [
312
312
  {
@@ -322,7 +322,7 @@
322
322
  "id": "runtime-profile",
323
323
  "capability": "runtime-profile",
324
324
  "status": "pass",
325
- "durationMs": 0.0796249999993961,
325
+ "durationMs": 0.07820800000081363,
326
326
  "message": "Detected 0 potential egress target(s) and 4 potential state mutation(s) with low confidence.",
327
327
  "evidence": [
328
328
  {
@@ -369,7 +369,7 @@
369
369
  "id": "conformance",
370
370
  "capability": "conformance",
371
371
  "status": "pass",
372
- "durationMs": 1.8100000000004002,
372
+ "durationMs": 1.9656669999994847,
373
373
  "message": "All 7 conformance checks passed.",
374
374
  "evidence": [
375
375
  {
@@ -395,7 +395,7 @@
395
395
  "id": "schema-quality",
396
396
  "capability": "schema-quality",
397
397
  "status": "partial",
398
- "durationMs": 0.902791999999863,
398
+ "durationMs": 0.6250829999999041,
399
399
  "message": "Found 1 quality finding(s) across 8 item(s): 0 warnings, 1 info.",
400
400
  "evidence": [
401
401
  {
@@ -425,7 +425,7 @@
425
425
  "id": "security",
426
426
  "capability": "security",
427
427
  "status": "pass",
428
- "durationMs": 0.2141249999995125,
428
+ "durationMs": 0.22325000000000728,
429
429
  "message": "No security issues detected.",
430
430
  "evidence": [
431
431
  {
@@ -441,7 +441,7 @@
441
441
  "id": "attack-sim",
442
442
  "capability": "attack-sim",
443
443
  "status": "pass",
444
- "durationMs": 0.4345000000002983,
444
+ "durationMs": 0.53387500000008,
445
445
  "message": "Safe attack simulation found no high-risk MCP attack-readiness findings.",
446
446
  "evidence": [
447
447
  {
@@ -500,17 +500,17 @@
500
500
  "weight": 0.1,
501
501
  "score": 100,
502
502
  "details": [
503
- "Connect: 1036ms",
504
- "p95 latency: 2ms (3 operations)"
503
+ "Connect: 847ms",
504
+ "p95 latency: 5ms (3 operations)"
505
505
  ]
506
506
  }
507
507
  ]
508
508
  },
509
509
  "performanceMetrics": {
510
- "connectMs": 1035.784208,
511
- "toolsListMs": 2.1864580000001297,
512
- "promptsListMs": 1.1239580000001297,
513
- "resourcesListMs": 0.0029999999997016857
510
+ "connectMs": 846.9272500000006,
511
+ "toolsListMs": 5.427625000000262,
512
+ "promptsListMs": 1.8686659999993935,
513
+ "resourcesListMs": 0.0031249999992724042
514
514
  },
515
515
  "runtimeProfile": {
516
516
  "stateMutations": [
@@ -539,7 +539,7 @@
539
539
  "source": "description_analysis"
540
540
  }
541
541
  ],
542
- "analyzedAt": "2026-07-15T22:33:20.276Z",
542
+ "analyzedAt": "2026-07-17T00:36:24.418Z",
543
543
  "confidence": "medium"
544
544
  }
545
545
  }
@@ -1,6 +1,6 @@
1
1
  # MCP Observatory Run Report
2
2
 
3
- Generated at 2026-07-15T22:33:19.237Z
3
+ Generated at 2026-07-17T00:36:23.563Z
4
4
 
5
5
  ## Target and Environment Metadata
6
6
 
@@ -58,7 +58,7 @@ The following state-modifying operations were identified from tool schemas:
58
58
  | filesystem | write | working_directory | description_analysis |
59
59
  | filesystem | delete | working_directory | description_analysis |
60
60
 
61
- _Analyzed at 2026-07-15T22:33:20.276Z_
61
+ _Analyzed at 2026-07-17T00:36:24.418Z_
62
62
 
63
63
  ## Regressions and Recoveries
64
64
 
@@ -68,14 +68,14 @@ _Use the `diff` command against another run artifact to classify regressions and
68
68
 
69
69
  | Focus | Check | Status | Duration (ms) | Message |
70
70
  | --- | --- | --- | --- | --- |
71
- | healthy | attack-sim | pass | 0.43 | Safe attack simulation found no high-risk MCP attack-readiness findings. |
72
- | healthy | conformance | pass | 1.81 | All 7 conformance checks passed. |
73
- | healthy | prompts | pass | 1.12 | Advertised capability responded with the minimal expected shape (1 item). |
71
+ | healthy | attack-sim | pass | 0.53 | Safe attack simulation found no high-risk MCP attack-readiness findings. |
72
+ | healthy | conformance | pass | 1.97 | All 7 conformance checks passed. |
73
+ | healthy | prompts | pass | 1.87 | Advertised capability responded with the minimal expected shape (1 item). |
74
74
  | healthy | runtime-profile | pass | 0.08 | Detected 0 potential egress target(s) and 4 potential state mutation(s) with low confidence. |
75
- | healthy | security | pass | 0.21 | No security issues detected. |
75
+ | healthy | security | pass | 0.22 | No security issues detected. |
76
76
  | healthy | security-lite | pass | 0.03 | No security issues detected (lightweight scan). |
77
- | healthy | tools | pass | 2.19 | Advertised capability responded with the minimal expected shape (7 items). |
78
- | review | schema-quality | partial | 0.90 | Found 1 quality finding(s) across 8 item(s): 0 warnings, 1 info. |
77
+ | healthy | tools | pass | 5.43 | Advertised capability responded with the minimal expected shape (7 items). |
78
+ | review | schema-quality | partial | 0.63 | Found 1 quality finding(s) across 8 item(s): 0 warnings, 1 info. |
79
79
  | confirm intent | resources | unsupported | 0.00 | Resources are not advertised by the target. |
80
80
 
81
81
  ## Evidence Snippets
@@ -114,7 +114,7 @@ Summary: Advertised capability responded with the minimal expected shape (1 item
114
114
  - Minimal shape present: `true`
115
115
  - Item count: `1`
116
116
  - Identifiers: demo_welcome
117
- - Diagnostics: Watching for changes in prompts directory: /Users/williamweishuhn/Documents/New project/mcp-observatory/examples/promptopia-prompts, promptopia-mcp MCP server running (v1.1.0)
117
+ - Diagnostics: Watching for changes in prompts directory: /Users/williamweishuhn/Documents/GitHub/mcp-observatory/examples/promptopia-prompts, promptopia-mcp MCP server running (v1.1.0)
118
118
 
119
119
  ### runtime-profile — pass
120
120
 
@@ -162,7 +162,7 @@ Summary: Advertised capability responded with the minimal expected shape (7 item
162
162
  - Minimal shape present: `true`
163
163
  - Item count: `7`
164
164
  - Identifiers: add_prompt, update_prompt, get_prompt, list_prompts, delete_prompt (+2 more)
165
- - Diagnostics: Watching for changes in prompts directory: /Users/williamweishuhn/Documents/New project/mcp-observatory/examples/promptopia-prompts, promptopia-mcp MCP server running (v1.1.0)
165
+ - Diagnostics: Watching for changes in prompts directory: /Users/williamweishuhn/Documents/GitHub/mcp-observatory/examples/promptopia-prompts, promptopia-mcp MCP server running (v1.1.0)
166
166
 
167
167
  ### schema-quality — partial
168
168
 
@@ -199,5 +199,5 @@ npm run cli -- report --run <path-to-run-artifact.json> --format markdown
199
199
 
200
200
  - Artifact type: `run`
201
201
  - Schema version: `1.0.0`
202
- - Run ID: `run_2026-07-15T223319237Z_baafc299`
202
+ - Run ID: `run_2026-07-17T003623563Z_bf28dbdf`
203
203
  - Gate: `pass`
@@ -2,9 +2,9 @@
2
2
  "artifactType": "run",
3
3
  "schemaVersion": "1.0.0",
4
4
  "gate": "fail",
5
- "runId": "run_2026-07-15T223327249Z_cf6d1b10",
6
- "createdAt": "2026-07-15T22:33:27.249Z",
7
- "toolVersion": "1.32.1",
5
+ "runId": "run_2026-07-17T003630838Z_79c90307",
6
+ "createdAt": "2026-07-17T00:36:30.838Z",
7
+ "toolVersion": "1.33.0",
8
8
  "target": {
9
9
  "targetId": "puppeteer-server",
10
10
  "adapter": "local-process",
@@ -43,7 +43,7 @@
43
43
  "id": "tools",
44
44
  "capability": "tools",
45
45
  "status": "pass",
46
- "durationMs": 0.443875000000844,
46
+ "durationMs": 0.9452080000010028,
47
47
  "message": "Advertised capability responded with the minimal expected shape (8 items).",
48
48
  "evidence": [
49
49
  {
@@ -192,7 +192,7 @@
192
192
  "id": "prompts",
193
193
  "capability": "prompts",
194
194
  "status": "unsupported",
195
- "durationMs": 0.0008330000000569271,
195
+ "durationMs": 0.0009579999987181509,
196
196
  "message": "Prompts are not advertised by the target.",
197
197
  "evidence": [
198
198
  {
@@ -208,7 +208,7 @@
208
208
  "id": "resources",
209
209
  "capability": "resources",
210
210
  "status": "pass",
211
- "durationMs": 0.6427500000008877,
211
+ "durationMs": 0.7948749999995925,
212
212
  "message": "Advertised capability responded with the minimal expected shape, but one optional resource endpoint appears unsupported.",
213
213
  "evidence": [
214
214
  {
@@ -237,7 +237,7 @@
237
237
  "id": "security-lite",
238
238
  "capability": "security-lite",
239
239
  "status": "pass",
240
- "durationMs": 0.03874999999970896,
240
+ "durationMs": 0.040333999999347725,
241
241
  "message": "No security issues detected (lightweight scan).",
242
242
  "evidence": [
243
243
  {
@@ -253,7 +253,7 @@
253
253
  "id": "runtime-profile",
254
254
  "capability": "runtime-profile",
255
255
  "status": "partial",
256
- "durationMs": 0.06541699999979755,
256
+ "durationMs": 0.06991700000071432,
257
257
  "message": "Detected 3 potential egress target(s) and 2 potential state mutation(s) with high confidence.",
258
258
  "evidence": [
259
259
  {
@@ -306,7 +306,7 @@
306
306
  "id": "conformance",
307
307
  "capability": "conformance",
308
308
  "status": "pass",
309
- "durationMs": 1002.0719170000011,
309
+ "durationMs": 989.7696660000001,
310
310
  "message": "All 7 conformance checks passed.",
311
311
  "evidence": [
312
312
  {
@@ -332,7 +332,7 @@
332
332
  "id": "schema-quality",
333
333
  "capability": "schema-quality",
334
334
  "status": "partial",
335
- "durationMs": 1.2140829999989364,
335
+ "durationMs": 0.39787499999874854,
336
336
  "message": "Found 2 quality finding(s) across 9 item(s): 1 warnings, 1 info.",
337
337
  "evidence": [
338
338
  {
@@ -370,7 +370,7 @@
370
370
  "id": "security",
371
371
  "capability": "security",
372
372
  "status": "pass",
373
- "durationMs": 0.15841700000055425,
373
+ "durationMs": 0.11245899999994435,
374
374
  "message": "No security issues detected.",
375
375
  "evidence": [
376
376
  {
@@ -386,7 +386,7 @@
386
386
  "id": "attack-sim",
387
387
  "capability": "attack-sim",
388
388
  "status": "fail",
389
- "durationMs": 1.7770409999993717,
389
+ "durationMs": 0.44720799999959127,
390
390
  "message": "Safe attack simulation found 1 finding(s): 1 high, 0 medium, 0 low.",
391
391
  "evidence": [
392
392
  {
@@ -468,17 +468,17 @@
468
468
  "weight": 0.1,
469
469
  "score": 100,
470
470
  "details": [
471
- "Connect: 823ms",
471
+ "Connect: 748ms",
472
472
  "p95 latency: 1ms (3 operations)"
473
473
  ]
474
474
  }
475
475
  ]
476
476
  },
477
477
  "performanceMetrics": {
478
- "connectMs": 823.1811669999988,
479
- "toolsListMs": 0.443875000000844,
480
- "promptsListMs": 0.0008330000000569271,
481
- "resourcesListMs": 0.6427500000008877
478
+ "connectMs": 747.8179999999993,
479
+ "toolsListMs": 0.9452080000010028,
480
+ "promptsListMs": 0.0009579999987181509,
481
+ "resourcesListMs": 0.7948749999995925
482
482
  },
483
483
  "runtimeProfile": {
484
484
  "egress": [
@@ -515,7 +515,7 @@
515
515
  "source": "description_analysis"
516
516
  }
517
517
  ],
518
- "analyzedAt": "2026-07-15T22:33:28.074Z",
518
+ "analyzedAt": "2026-07-17T00:36:31.588Z",
519
519
  "confidence": "high"
520
520
  }
521
521
  }
@@ -1,6 +1,6 @@
1
1
  # MCP Observatory Run Report
2
2
 
3
- Generated at 2026-07-15T22:33:27.249Z
3
+ Generated at 2026-07-17T00:36:30.838Z
4
4
 
5
5
  ## Target and Environment Metadata
6
6
 
@@ -66,7 +66,7 @@ The following state-modifying operations were identified from tool schemas:
66
66
  | filesystem | write | working_directory | description_analysis |
67
67
  | filesystem | write | working_directory | description_analysis |
68
68
 
69
- _Analyzed at 2026-07-15T22:33:28.074Z_
69
+ _Analyzed at 2026-07-17T00:36:31.588Z_
70
70
 
71
71
  ## Regressions and Recoveries
72
72
 
@@ -76,15 +76,15 @@ _Use the `diff` command against another run artifact to classify regressions and
76
76
 
77
77
  | Focus | Check | Status | Duration (ms) | Message |
78
78
  | --- | --- | --- | --- | --- |
79
- | healthy | conformance | pass | 1002.07 | All 7 conformance checks passed. |
80
- | healthy | resources | pass | 0.64 | Advertised capability responded with the minimal expected shape, but one optional resource endpoint appears unsupported. |
81
- | healthy | security | pass | 0.16 | No security issues detected. |
79
+ | healthy | conformance | pass | 989.77 | All 7 conformance checks passed. |
80
+ | healthy | resources | pass | 0.79 | Advertised capability responded with the minimal expected shape, but one optional resource endpoint appears unsupported. |
81
+ | healthy | security | pass | 0.11 | No security issues detected. |
82
82
  | healthy | security-lite | pass | 0.04 | No security issues detected (lightweight scan). |
83
- | healthy | tools | pass | 0.44 | Advertised capability responded with the minimal expected shape (8 items). |
83
+ | healthy | tools | pass | 0.95 | Advertised capability responded with the minimal expected shape (8 items). |
84
84
  | review | runtime-profile | partial | 0.07 | Detected 3 potential egress target(s) and 2 potential state mutation(s) with high confidence. |
85
- | review | schema-quality | partial | 1.21 | Found 2 quality finding(s) across 9 item(s): 1 warnings, 1 info. |
85
+ | review | schema-quality | partial | 0.40 | Found 2 quality finding(s) across 9 item(s): 1 warnings, 1 info. |
86
86
  | confirm intent | prompts | unsupported | 0.00 | Prompts are not advertised by the target. |
87
- | act now | attack-sim | fail | 1.78 | Safe attack simulation found 1 finding(s): 1 high, 0 medium, 0 low. |
87
+ | act now | attack-sim | fail | 0.45 | Safe attack simulation found 1 finding(s): 1 high, 0 medium, 0 low. |
88
88
 
89
89
  ## Evidence Snippets
90
90
 
@@ -214,5 +214,5 @@ npm run cli -- report --run <path-to-run-artifact.json> --format markdown
214
214
 
215
215
  - Artifact type: `run`
216
216
  - Schema version: `1.0.0`
217
- - Run ID: `run_2026-07-15T223327249Z_cf6d1b10`
217
+ - Run ID: `run_2026-07-17T003630838Z_79c90307`
218
218
  - Gate: `fail`
@@ -2,9 +2,9 @@
2
2
  "artifactType": "run",
3
3
  "schemaVersion": "1.0.0",
4
4
  "gate": "fail",
5
- "runId": "run_2026-07-15T223338620Z_bd59b18c",
6
- "createdAt": "2026-07-15T22:33:38.620Z",
7
- "toolVersion": "1.32.1",
5
+ "runId": "run_2026-07-17T003642256Z_e23961d6",
6
+ "createdAt": "2026-07-17T00:36:42.256Z",
7
+ "toolVersion": "1.33.0",
8
8
  "target": {
9
9
  "targetId": "qdrant-server",
10
10
  "adapter": "local-process",
@@ -62,5 +62,5 @@
62
62
  "evidence": []
63
63
  }
64
64
  ],
65
- "fatalError": "Could not establish a plain stdio MCP session for target `qdrant-server`.\nCommand: npx -y @anthropic/mcp-server-qdrant\nDiagnosis: The process exited or detached before MCP initialization completed.\nRaw error: MCP error -32000: Connection closed\nLikely causes:\n- The package may expect extra startup arguments or environment variables.\n- The package may not behave like a plain local-process stdio target under this invocation.\n- The server may be crashing immediately and only leaving clues on stderr.\nNext steps:\n- Run the command manually and look for usage output, auth prompts, or crash text.\n- Check whether the package expects a different transport or an app-oriented startup flow.\n- Use the recent stderr lines below before assuming this is a harness bug.\nRecent stderr:\n- npm error 404 '@anthropic/mcp-server-qdrant@*' is not in this registry.\n- npm error 404\n- npm error 404 Note that you can also install from a\n- npm error 404 tarball, folder, http url, or git url.\n- npm error A complete log of this run can be found in: /Users/williamweishuhn/.npm/_logs/2026-07-15T22_33_38_693Z-debug-0.log"
65
+ "fatalError": "Could not establish a plain stdio MCP session for target `qdrant-server`.\nCommand: npx -y @anthropic/mcp-server-qdrant\nDiagnosis: The process exited or detached before MCP initialization completed.\nRaw error: MCP error -32000: Connection closed\nLikely causes:\n- The package may expect extra startup arguments or environment variables.\n- The package may not behave like a plain local-process stdio target under this invocation.\n- The server may be crashing immediately and only leaving clues on stderr.\nNext steps:\n- Run the command manually and look for usage output, auth prompts, or crash text.\n- Check whether the package expects a different transport or an app-oriented startup flow.\n- Use the recent stderr lines below before assuming this is a harness bug.\nRecent stderr:\n- npm error 404 The requested resource '@anthropic/mcp-server-qdrant@*' could not be found or you do not have permission to access it.\n- npm error 404\n- npm error 404 Note that you can also install from a\n- npm error 404 tarball, folder, http url, or git url.\n- npm error A complete log of this run can be found in: /Users/williamweishuhn/.npm/_logs/2026-07-17T00_36_42_327Z-debug-0.log"
66
66
  }
@@ -1,6 +1,6 @@
1
1
  # MCP Observatory Run Report
2
2
 
3
- Generated at 2026-07-15T22:33:38.620Z
3
+ Generated at 2026-07-17T00:36:42.256Z
4
4
 
5
5
  ## Target and Environment Metadata
6
6
 
@@ -56,11 +56,11 @@ Next steps:
56
56
  - Check whether the package expects a different transport or an app-oriented startup flow.
57
57
  - Use the recent stderr lines below before assuming this is a harness bug.
58
58
  Recent stderr:
59
- - npm error 404 '@anthropic/mcp-server-qdrant@*' is not in this registry.
59
+ - npm error 404 The requested resource '@anthropic/mcp-server-qdrant@*' could not be found or you do not have permission to access it.
60
60
  - npm error 404
61
61
  - npm error 404 Note that you can also install from a
62
62
  - npm error 404 tarball, folder, http url, or git url.
63
- - npm error A complete log of this run can be found in: /Users/williamweishuhn/.npm/_logs/2026-07-15T22_33_38_693Z-debug-0.log
63
+ - npm error A complete log of this run can be found in: /Users/williamweishuhn/.npm/_logs/2026-07-17T00_36_42_327Z-debug-0.log
64
64
  ```
65
65
 
66
66
  ## Full Capability Status Table
@@ -102,5 +102,5 @@ npm run cli -- report --run <path-to-run-artifact.json> --format markdown
102
102
 
103
103
  - Artifact type: `run`
104
104
  - Schema version: `1.0.0`
105
- - Run ID: `run_2026-07-15T223338620Z_bd59b18c`
105
+ - Run ID: `run_2026-07-17T003642256Z_e23961d6`
106
106
  - Gate: `fail`
@@ -2,9 +2,9 @@
2
2
  "artifactType": "run",
3
3
  "schemaVersion": "1.0.0",
4
4
  "gate": "pass",
5
- "runId": "run_2026-07-15T223322301Z_3fb8821d",
6
- "createdAt": "2026-07-15T22:33:22.302Z",
7
- "toolVersion": "1.32.1",
5
+ "runId": "run_2026-07-17T003626429Z_130951f0",
6
+ "createdAt": "2026-07-17T00:36:26.429Z",
7
+ "toolVersion": "1.33.0",
8
8
  "target": {
9
9
  "targetId": "ref-tools-server",
10
10
  "adapter": "local-process",
@@ -43,7 +43,7 @@
43
43
  "id": "tools",
44
44
  "capability": "tools",
45
45
  "status": "pass",
46
- "durationMs": 1.3943750000016735,
46
+ "durationMs": 1.037916999999652,
47
47
  "message": "Advertised capability responded with the minimal expected shape (2 items).",
48
48
  "evidence": [
49
49
  {
@@ -92,7 +92,7 @@
92
92
  "id": "prompts",
93
93
  "capability": "prompts",
94
94
  "status": "pass",
95
- "durationMs": 0.23954200000116543,
95
+ "durationMs": 0.28758299999935844,
96
96
  "message": "Advertised capability responded with the minimal expected shape (2 items).",
97
97
  "evidence": [
98
98
  {
@@ -115,7 +115,7 @@
115
115
  "id": "resources",
116
116
  "capability": "resources",
117
117
  "status": "unsupported",
118
- "durationMs": 0.002917000001616543,
118
+ "durationMs": 0.0032499999997526174,
119
119
  "message": "Resources are not advertised by the target.",
120
120
  "evidence": [
121
121
  {
@@ -131,7 +131,7 @@
131
131
  "id": "security-lite",
132
132
  "capability": "security-lite",
133
133
  "status": "pass",
134
- "durationMs": 0.01841700000113633,
134
+ "durationMs": 0.01900000000023283,
135
135
  "message": "No security issues detected (lightweight scan).",
136
136
  "evidence": [
137
137
  {
@@ -147,7 +147,7 @@
147
147
  "id": "runtime-profile",
148
148
  "capability": "runtime-profile",
149
149
  "status": "partial",
150
- "durationMs": 0.11679199999889534,
150
+ "durationMs": 0.10537499999918509,
151
151
  "message": "Detected 4 potential egress target(s) and 0 potential state mutation(s) with high confidence.",
152
152
  "evidence": [
153
153
  {
@@ -194,7 +194,7 @@
194
194
  "id": "conformance",
195
195
  "capability": "conformance",
196
196
  "status": "pass",
197
- "durationMs": 0.5142089999990276,
197
+ "durationMs": 0.4587499999997817,
198
198
  "message": "All 7 conformance checks passed.",
199
199
  "evidence": [
200
200
  {
@@ -220,7 +220,7 @@
220
220
  "id": "schema-quality",
221
221
  "capability": "schema-quality",
222
222
  "status": "pass",
223
- "durationMs": 0.5241670000013983,
223
+ "durationMs": 0.4734169999992446,
224
224
  "message": "All 4 item(s) have good schema quality.",
225
225
  "evidence": [
226
226
  {
@@ -237,7 +237,7 @@
237
237
  "id": "security",
238
238
  "capability": "security",
239
239
  "status": "pass",
240
- "durationMs": 0.19254199999886623,
240
+ "durationMs": 0.14400000000023283,
241
241
  "message": "No security issues detected.",
242
242
  "evidence": [
243
243
  {
@@ -253,7 +253,7 @@
253
253
  "id": "attack-sim",
254
254
  "capability": "attack-sim",
255
255
  "status": "pass",
256
- "durationMs": 0.26929200000085984,
256
+ "durationMs": 0.2027909999997064,
257
257
  "message": "Safe attack simulation found no high-risk MCP attack-readiness findings.",
258
258
  "evidence": [
259
259
  {
@@ -312,17 +312,17 @@
312
312
  "weight": 0.1,
313
313
  "score": 100,
314
314
  "details": [
315
- "Connect: 726ms",
315
+ "Connect: 579ms",
316
316
  "p95 latency: 1ms (3 operations)"
317
317
  ]
318
318
  }
319
319
  ]
320
320
  },
321
321
  "performanceMetrics": {
322
- "connectMs": 725.896999999999,
323
- "toolsListMs": 1.3943750000016735,
324
- "promptsListMs": 0.23954200000116543,
325
- "resourcesListMs": 0.002917000001616543
322
+ "connectMs": 579.0261249999994,
323
+ "toolsListMs": 1.037916999999652,
324
+ "promptsListMs": 0.28758299999935844,
325
+ "resourcesListMs": 0.0032499999997526174
326
326
  },
327
327
  "runtimeProfile": {
328
328
  "egress": [
@@ -351,7 +351,7 @@
351
351
  "confidence": "low"
352
352
  }
353
353
  ],
354
- "analyzedAt": "2026-07-15T22:33:23.029Z",
354
+ "analyzedAt": "2026-07-17T00:36:27.010Z",
355
355
  "confidence": "high"
356
356
  }
357
357
  }
@@ -1,6 +1,6 @@
1
1
  # MCP Observatory Run Report
2
2
 
3
- Generated at 2026-07-15T22:33:22.302Z
3
+ Generated at 2026-07-17T00:36:26.429Z
4
4
 
5
5
  ## Target and Environment Metadata
6
6
 
@@ -57,7 +57,7 @@ The following targets were identified as potentially reachable by this server (c
57
57
  | The URL of the webpage to read. | unknown | description_analysis | medium |
58
58
  | ref_read_url | unknown | description_analysis | low |
59
59
 
60
- _Analyzed at 2026-07-15T22:33:23.029Z_
60
+ _Analyzed at 2026-07-17T00:36:27.010Z_
61
61
 
62
62
  ## Regressions and Recoveries
63
63
 
@@ -67,14 +67,14 @@ _Use the `diff` command against another run artifact to classify regressions and
67
67
 
68
68
  | Focus | Check | Status | Duration (ms) | Message |
69
69
  | --- | --- | --- | --- | --- |
70
- | healthy | attack-sim | pass | 0.27 | Safe attack simulation found no high-risk MCP attack-readiness findings. |
71
- | healthy | conformance | pass | 0.51 | All 7 conformance checks passed. |
72
- | healthy | prompts | pass | 0.24 | Advertised capability responded with the minimal expected shape (2 items). |
73
- | healthy | schema-quality | pass | 0.52 | All 4 item(s) have good schema quality. |
74
- | healthy | security | pass | 0.19 | No security issues detected. |
70
+ | healthy | attack-sim | pass | 0.20 | Safe attack simulation found no high-risk MCP attack-readiness findings. |
71
+ | healthy | conformance | pass | 0.46 | All 7 conformance checks passed. |
72
+ | healthy | prompts | pass | 0.29 | Advertised capability responded with the minimal expected shape (2 items). |
73
+ | healthy | schema-quality | pass | 0.47 | All 4 item(s) have good schema quality. |
74
+ | healthy | security | pass | 0.14 | No security issues detected. |
75
75
  | healthy | security-lite | pass | 0.02 | No security issues detected (lightweight scan). |
76
- | healthy | tools | pass | 1.39 | Advertised capability responded with the minimal expected shape (2 items). |
77
- | review | runtime-profile | partial | 0.12 | Detected 4 potential egress target(s) and 0 potential state mutation(s) with high confidence. |
76
+ | healthy | tools | pass | 1.04 | Advertised capability responded with the minimal expected shape (2 items). |
77
+ | review | runtime-profile | partial | 0.11 | Detected 4 potential egress target(s) and 0 potential state mutation(s) with high confidence. |
78
78
  | confirm intent | resources | unsupported | 0.00 | Resources are not advertised by the target. |
79
79
 
80
80
  ## Evidence Snippets
@@ -198,5 +198,5 @@ npm run cli -- report --run <path-to-run-artifact.json> --format markdown
198
198
 
199
199
  - Artifact type: `run`
200
200
  - Schema version: `1.0.0`
201
- - Run ID: `run_2026-07-15T223322301Z_3fb8821d`
201
+ - Run ID: `run_2026-07-17T003626429Z_130951f0`
202
202
  - Gate: `pass`