@kryptosai/mcp-observatory 1.32.1 → 1.33.0

package/docs/safety-index/artifacts/pubmed-mcp-server.md

@@ -0,0 +1,96 @@
+# MCP Observatory Run Report
+
+Generated at 2026-07-15T17:30:08.340Z
+
+## Target and Environment Metadata
+
+- Target: `pubmed-mcp-server`
+- Adapter: `local-process`
+- Command: `npx -y pubmed-mcp-server`
+- Server: `unknown `
+- Platform: `darwin 25.5.0`
+- Node: `v22.22.1`
+
+## Executive Summary
+
+| Gate | Total | Pass | Fail | Partial | Unsupported | Flaky | Skipped |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| fail | 3 | 0 | 0 | 0 | 0 | 0 | 3 |
+
+## At a Glance
+
+- Safety verdict: **Blocked** — One or more checks can break agent dependence and should be fixed before production use.
+- Top risks: startup: server failed to start
+- Regression/schema drift: Run `mcp-observatory diff <previous-run.json> <current-run.json>` to classify regressions and schema drift.
+- Failing checks: none
+- Partial or flaky checks: none
+- Skipped checks: tools, prompts, resources
+- Unsupported checks: none
+- Suggested next step: Run the target command manually, compare stderr with the diagnosis below, and only raise timeoutMs if startup is genuinely slow.
+- CI next step: `Add CI: npx @kryptosai/mcp-observatory setup-ci --all --command "npx -y <server-package>"`
+
+## Regressions and Recoveries
+
+_Use the `diff` command against another run artifact to classify regressions and recoveries over time._
+
+## Failure Diagnosis
+
+```text
+Could not establish a plain stdio MCP session for target `pubmed-mcp-server`.
+Command: npx -y pubmed-mcp-server
+Diagnosis: The process exited or detached before MCP initialization completed.
+Raw error: MCP error -32000: Connection closed
+Likely causes:
+- The package may expect extra startup arguments or environment variables.
+- The package may not behave like a plain local-process stdio target under this invocation.
+- The server may be crashing immediately and only leaving clues on stderr.
+Next steps:
+- Run the command manually and look for usage output, auth prompts, or crash text.
+- Check whether the package expects a different transport or an app-oriented startup flow.
+- Use the recent stderr lines below before assuming this is a harness bug.
+Recent stderr:
+- /Users/williamweishuhn/.npm/_npx/930ee94f2d835167/node_modules/.bin/pubmed-mcp-server: line 1: use strict: command not found
+- /Users/williamweishuhn/.npm/_npx/930ee94f2d835167/node_modules/.bin/pubmed-mcp-server: line 2: //#: No such file or directory
+```
+
+## Full Capability Status Table
+
+| Focus | Check | Status | Duration (ms) | Message |
+| --- | --- | --- | --- | --- |
+| inspect startup | prompts | skipped | 0.00 | Skipped because startup failed before the MCP session initialized. See the failure diagnosis. |
+| inspect startup | resources | skipped | 0.00 | Skipped because startup failed before the MCP session initialized. See the failure diagnosis. |
+| inspect startup | tools | skipped | 0.00 | Skipped because startup failed before the MCP session initialized. See the failure diagnosis. |
+
+## Evidence Snippets
+
+### prompts — skipped
+
+Summary: Skipped because startup failed before the MCP session initialized. See the failure diagnosis.
+
+_No evidence was captured._
+
+### resources — skipped
+
+Summary: Skipped because startup failed before the MCP session initialized. See the failure diagnosis.
+
+_No evidence was captured._
+
+### tools — skipped
+
+Summary: Skipped because startup failed before the MCP session initialized. See the failure diagnosis.
+
+_No evidence was captured._
+
+## Reproduction Commands
+
+```bash
+npm run cli -- run --target <path-to-target-config.json>
+npm run cli -- report --run <path-to-run-artifact.json> --format markdown
+```
+
+## Artifact Provenance
+
+- Artifact type: `run`
+- Schema version: `1.0.0`
+- Run ID: `run_2026-07-15T173008340Z_ec311fa0`
+- Gate: `fail`

package/docs/safety-index/artifacts/punjab-health-mcp.json

@@ -0,0 +1,66 @@
+{
+  "artifactType": "run",
+  "schemaVersion": "1.0.0",
+  "gate": "fail",
+  "runId": "run_2026-07-15T223550180Z_9028920c",
+  "createdAt": "2026-07-15T22:35:50.180Z",
+  "toolVersion": "1.32.1",
+  "target": {
+    "targetId": "punjab-health-mcp",
+    "adapter": "local-process",
+    "command": "npx",
+    "args": [
+      "-y",
+      "punjab-health-mcp"
+    ],
+    "cwd": ".",
+    "metadata": {
+      "package": "punjab-health-mcp",
+      "purpose": "mcp-safety-index",
+      "riskClass": "Provincial health department API access",
+      "failureClass": "Health service/disease surveillance boundary",
+      "whyItMatters": "Punjab Health Department serves 120M+ people across Pakistan's most populous province. MCP servers accessing district health data, disease surveillance, DHIS2 reporting, and digital health services handle population-scale public health data."
+    }
+  },
+  "environment": {
+    "platform": "darwin 25.5.0",
+    "nodeVersion": "v22.22.1"
+  },
+  "summary": {
+    "total": 3,
+    "pass": 0,
+    "fail": 0,
+    "partial": 0,
+    "unsupported": 0,
+    "flaky": 0,
+    "skipped": 3,
+    "gate": "fail"
+  },
+  "checks": [
+    {
+      "id": "tools",
+      "capability": "tools",
+      "status": "skipped",
+      "durationMs": 0,
+      "message": "Skipped because startup failed before the MCP session initialized. See the failure diagnosis.",
+      "evidence": []
+    },
+    {
+      "id": "prompts",
+      "capability": "prompts",
+      "status": "skipped",
+      "durationMs": 0,
+      "message": "Skipped because startup failed before the MCP session initialized. See the failure diagnosis.",
+      "evidence": []
+    },
+    {
+      "id": "resources",
+      "capability": "resources",
+      "status": "skipped",
+      "durationMs": 0,
+      "message": "Skipped because startup failed before the MCP session initialized. See the failure diagnosis.",
+      "evidence": []
+    }
+  ],
+  "fatalError": "Could not establish a plain stdio MCP session for target `punjab-health-mcp`.\nCommand: npx -y punjab-health-mcp\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  'punjab-health-mcp@*' 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_35_50_261Z-debug-0.log"
+}

package/docs/safety-index/artifacts/punjab-health-mcp.md

@@ -0,0 +1,106 @@
+# MCP Observatory Run Report
+
+Generated at 2026-07-15T22:35:50.180Z
+
+## Target and Environment Metadata
+
+- Target: `punjab-health-mcp`
+- Adapter: `local-process`
+- Command: `npx -y punjab-health-mcp`
+- Server: `unknown `
+- Platform: `darwin 25.5.0`
+- Node: `v22.22.1`
+
+## Executive Summary
+
+| Gate | Total | Pass | Fail | Partial | Unsupported | Flaky | Skipped |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| fail | 3 | 0 | 0 | 0 | 0 | 0 | 3 |
+
+## At a Glance
+
+- Safety verdict: **Blocked** — One or more checks can break agent dependence and should be fixed before production use.
+- Top risks: startup: server failed to start
+- Regression/schema drift: Run `mcp-observatory diff <previous-run.json> <current-run.json>` to classify regressions and schema drift.
+- Failing checks: none
+- Partial or flaky checks: none
+- Skipped checks: tools, prompts, resources
+- Unsupported checks: none
+- Suggested next step: Run the target command manually, compare stderr with the diagnosis below, and only raise timeoutMs if startup is genuinely slow.
+- CI next step: `Add CI: npx @kryptosai/mcp-observatory setup-ci --all --command "npx -y <server-package>"`
+
+## What Was Not Tested
+
+- 🔒 network_egress: No outbound network calls were attempted during scan
+- 🔒 filesystem_mutation: Filesystem write operations were not exercised
+- 🔒 credential_access: Credential scanning was not performed
+- ℹ️ destructive_payloads: Destructive payloads were not attempted (safe-mode only)
+
+## Regressions and Recoveries
+
+_Use the `diff` command against another run artifact to classify regressions and recoveries over time._
+
+## Failure Diagnosis
+
+```text
+Could not establish a plain stdio MCP session for target `punjab-health-mcp`.
+Command: npx -y punjab-health-mcp
+Diagnosis: The process exited or detached before MCP initialization completed.
+Raw error: MCP error -32000: Connection closed
+Likely causes:
+- The package may expect extra startup arguments or environment variables.
+- The package may not behave like a plain local-process stdio target under this invocation.
+- The server may be crashing immediately and only leaving clues on stderr.
+Next steps:
+- Run the command manually and look for usage output, auth prompts, or crash text.
+- Check whether the package expects a different transport or an app-oriented startup flow.
+- Use the recent stderr lines below before assuming this is a harness bug.
+Recent stderr:
+- npm error 404  'punjab-health-mcp@*' is not in this registry.
+- npm error 404
+- npm error 404 Note that you can also install from a
+- npm error 404 tarball, folder, http url, or git url.
+- npm error A complete log of this run can be found in: /Users/williamweishuhn/.npm/_logs/2026-07-15T22_35_50_261Z-debug-0.log
+```
+
+## Full Capability Status Table
+
+| Focus | Check | Status | Duration (ms) | Message |
+| --- | --- | --- | --- | --- |
+| inspect startup | prompts | skipped | 0.00 | Skipped because startup failed before the MCP session initialized. See the failure diagnosis. |
+| inspect startup | resources | skipped | 0.00 | Skipped because startup failed before the MCP session initialized. See the failure diagnosis. |
+| inspect startup | tools | skipped | 0.00 | Skipped because startup failed before the MCP session initialized. See the failure diagnosis. |
+
+## Evidence Snippets
+
+### prompts — skipped
+
+Summary: Skipped because startup failed before the MCP session initialized. See the failure diagnosis.
+
+_No evidence was captured._
+
+### resources — skipped
+
+Summary: Skipped because startup failed before the MCP session initialized. See the failure diagnosis.
+
+_No evidence was captured._
+
+### tools — skipped
+
+Summary: Skipped because startup failed before the MCP session initialized. See the failure diagnosis.
+
+_No evidence was captured._
+
+## Reproduction Commands
+
+```bash
+npm run cli -- run --target <path-to-target-config.json>
+npm run cli -- report --run <path-to-run-artifact.json> --format markdown
+```
+
+## Artifact Provenance
+
+- Artifact type: `run`
+- Schema version: `1.0.0`
+- Run ID: `run_2026-07-15T223550180Z_9028920c`
+- Gate: `fail`

package/docs/safety-index/artifacts/puppeteer-server.json

@@ -2,9 +2,9 @@
   "artifactType": "run",
   "schemaVersion": "1.0.0",
   "gate": "fail",
-  "runId": "run_2026-07-12T234407396Z_24f05cfd",
-  "createdAt": "2026-07-12T23:44:07.396Z",
-  "toolVersion": "1.31.0",
+  "runId": "run_2026-07-15T223327249Z_cf6d1b10",
+  "createdAt": "2026-07-15T22:33:27.249Z",
+  "toolVersion": "1.32.1",
   "target": {
     "targetId": "puppeteer-server",
     "adapter": "local-process",
@@ -43,7 +43,7 @@
       "id": "tools",
       "capability": "tools",
       "status": "pass",
-      "durationMs": 0.43404200000077253,
+      "durationMs": 0.443875000000844,
       "message": "Advertised capability responded with the minimal expected shape (8 items).",
       "evidence": [
         {
@@ -192,7 +192,7 @@
       "id": "prompts",
       "capability": "prompts",
       "status": "unsupported",
-      "durationMs": 0.0008749999997235136,
+      "durationMs": 0.0008330000000569271,
       "message": "Prompts are not advertised by the target.",
       "evidence": [
         {
@@ -208,7 +208,7 @@
       "id": "resources",
       "capability": "resources",
       "status": "pass",
-      "durationMs": 0.6497080000008282,
+      "durationMs": 0.6427500000008877,
       "message": "Advertised capability responded with the minimal expected shape, but one optional resource endpoint appears unsupported.",
       "evidence": [
         {
@@ -237,7 +237,7 @@
       "id": "security-lite",
       "capability": "security-lite",
       "status": "pass",
-      "durationMs": 0.03916700000081619,
+      "durationMs": 0.03874999999970896,
       "message": "No security issues detected (lightweight scan).",
       "evidence": [
         {
@@ -253,7 +253,7 @@
       "id": "runtime-profile",
       "capability": "runtime-profile",
       "status": "partial",
-      "durationMs": 0.0698339999999007,
+      "durationMs": 0.06541699999979755,
       "message": "Detected 3 potential egress target(s) and 2 potential state mutation(s) with high confidence.",
       "evidence": [
         {
@@ -306,7 +306,7 @@
       "id": "conformance",
       "capability": "conformance",
       "status": "pass",
-      "durationMs": 1074.559666000001,
+      "durationMs": 1002.0719170000011,
       "message": "All 7 conformance checks passed.",
       "evidence": [
         {
@@ -332,7 +332,7 @@
       "id": "schema-quality",
       "capability": "schema-quality",
       "status": "partial",
-      "durationMs": 0.4976669999996375,
+      "durationMs": 1.2140829999989364,
       "message": "Found 2 quality finding(s) across 9 item(s): 1 warnings, 1 info.",
       "evidence": [
         {
@@ -370,7 +370,7 @@
       "id": "security",
       "capability": "security",
       "status": "pass",
-      "durationMs": 0.1350830000010319,
+      "durationMs": 0.15841700000055425,
       "message": "No security issues detected.",
       "evidence": [
         {
@@ -386,7 +386,7 @@
       "id": "attack-sim",
       "capability": "attack-sim",
       "status": "fail",
-      "durationMs": 0.44333300000107556,
+      "durationMs": 1.7770409999993717,
       "message": "Safe attack simulation found 1 finding(s): 1 high, 0 medium, 0 low.",
       "evidence": [
         {
@@ -468,17 +468,17 @@
         "weight": 0.1,
         "score": 100,
         "details": [
-          "Connect: 891ms",
+          "Connect: 823ms",
           "p95 latency: 1ms (3 operations)"
         ]
       }
     ]
   },
   "performanceMetrics": {
-    "connectMs": 891.2145409999994,
-    "toolsListMs": 0.43404200000077253,
-    "promptsListMs": 0.0008749999997235136,
-    "resourcesListMs": 0.6497080000008282
+    "connectMs": 823.1811669999988,
+    "toolsListMs": 0.443875000000844,
+    "promptsListMs": 0.0008330000000569271,
+    "resourcesListMs": 0.6427500000008877
   },
   "runtimeProfile": {
     "egress": [
@@ -515,7 +515,7 @@
         "source": "description_analysis"
       }
     ],
-    "analyzedAt": "2026-07-12T23:44:08.288Z",
+    "analyzedAt": "2026-07-15T22:33:28.074Z",
     "confidence": "high"
   }
 }

package/docs/safety-index/artifacts/puppeteer-server.md

@@ -1,6 +1,6 @@
 # MCP Observatory Run Report
 
-Generated at 2026-07-12T23:44:07.396Z
+Generated at 2026-07-15T22:33:27.249Z
 
 ## Target and Environment Metadata
 
@@ -66,7 +66,7 @@ The following state-modifying operations were identified from tool schemas:
 | filesystem | write | working_directory | description_analysis |
 | filesystem | write | working_directory | description_analysis |
 
-_Analyzed at 2026-07-12T23:44:08.288Z_
+_Analyzed at 2026-07-15T22:33:28.074Z_
 
 ## Regressions and Recoveries
 
@@ -76,15 +76,15 @@ _Use the `diff` command against another run artifact to classify regressions and
 
 | Focus | Check | Status | Duration (ms) | Message |
 | --- | --- | --- | --- | --- |
-| healthy | conformance | pass | 1074.56 | All 7 conformance checks passed. |
-| healthy | resources | pass | 0.65 | Advertised capability responded with the minimal expected shape, but one optional resource endpoint appears unsupported. |
-| healthy | security | pass | 0.14 | No security issues detected. |
+| healthy | conformance | pass | 1002.07 | All 7 conformance checks passed. |
+| healthy | resources | pass | 0.64 | Advertised capability responded with the minimal expected shape, but one optional resource endpoint appears unsupported. |
+| healthy | security | pass | 0.16 | No security issues detected. |
 | healthy | security-lite | pass | 0.04 | No security issues detected (lightweight scan). |
-| healthy | tools | pass | 0.43 | Advertised capability responded with the minimal expected shape (8 items). |
+| healthy | tools | pass | 0.44 | Advertised capability responded with the minimal expected shape (8 items). |
 | review | runtime-profile | partial | 0.07 | Detected 3 potential egress target(s) and 2 potential state mutation(s) with high confidence. |
-| review | schema-quality | partial | 0.50 | Found 2 quality finding(s) across 9 item(s): 1 warnings, 1 info. |
+| review | schema-quality | partial | 1.21 | Found 2 quality finding(s) across 9 item(s): 1 warnings, 1 info. |
 | confirm intent | prompts | unsupported | 0.00 | Prompts are not advertised by the target. |
-| act now | attack-sim | fail | 0.44 | Safe attack simulation found 1 finding(s): 1 high, 0 medium, 0 low. |
+| act now | attack-sim | fail | 1.78 | Safe attack simulation found 1 finding(s): 1 high, 0 medium, 0 low. |
 
 ## Evidence Snippets
 
@@ -214,5 +214,5 @@ npm run cli -- report --run <path-to-run-artifact.json> --format markdown
 
 - Artifact type: `run`
 - Schema version: `1.0.0`
-- Run ID: `run_2026-07-12T234407396Z_24f05cfd`
+- Run ID: `run_2026-07-15T223327249Z_cf6d1b10`
 - Gate: `fail`