@kryptosai/mcp-observatory 1.32.0 → 1.33.0

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

@@ -0,0 +1,255 @@
+# MCP Observatory Run Report
+
+Generated at 2026-07-15T22:34:57.590Z
+
+## Target and Environment Metadata
+
+- Target: `confluence-mcp-server`
+- Adapter: `local-process`
+- Command: `npx -y confluence-mcp-server`
+- Server: `confluence-mcp-server 1.3.3`
+- Platform: `darwin 25.5.0`
+- Node: `v22.22.1`
+
+## Executive Summary
+
+**Health Score: 69/100 (D)**
+
+| Dimension | Score | Weight |
+| --- | --- | --- |
+| Protocol Compliance | 100/100 | 30% |
+| Schema Quality | 60/100 | 20% |
+| Security | 20/100 | 20% |
+| Reliability | 67/100 | 20% |
+| Performance | 100/100 | 10% |
+
+| Gate | Total | Pass | Fail | Partial | Unsupported | Flaky | Skipped |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| fail | 9 | 2 | 2 | 3 | 2 | 0 | 0 |
+
+## At a Glance
+
+- Safety verdict: **Blocked** — One or more checks can break agent dependence and should be fixed before production use.
+- Top risks: attack-sim: Safe attack simulation found 1 finding(s): 0 high, 1 medium, 0 low.; runtime-profile: Detected 6 potential egress target(s) and 44 potential state mutation(s) with high confidence.; schema-quality: Found 3 quality finding(s) across 25 item(s): 0 warnings, 3 info.
+- Regression/schema drift: Run `mcp-observatory diff <previous-run.json> <current-run.json>` to classify regressions and schema drift.
+- Failing checks: security-lite, security
+- Partial or flaky checks: runtime-profile, schema-quality, attack-sim
+- Skipped checks: none
+- Unsupported checks: prompts, resources
+- Suggested next step: Start with the failing checks: security-lite, security.
+- CI next step: `Add CI: npx @kryptosai/mcp-observatory setup-ci --all --command "npx -y <server-package>"`
+
+## What Was Not Tested
+
+- ℹ️ credential_access: Credential scanning was performed (see security findings)
+- ℹ️ destructive_payloads: Destructive payloads were not attempted (safe-mode only)
+
+## Runtime Profile
+
+### Egress Manifest
+
+The following targets were identified as potentially reachable by this server (confidence: **high**):
+
+| Target | Protocol | Source | Confidence |
+| --- | --- | --- | --- |
+| baseUrl | unknown | tool_schema | high |
+| Confluence base URL, for example https://confluence.example.com. Required for first configuration; omitted values inherit the current connection. | unknown | description_analysis | medium |
+| Access token. Cloud treats this as an API token; Server auto mode treats it as Bearer. | unknown | description_analysis | medium |
+| confluence_search_pages | unknown | description_analysis | low |
+| confluence_execute_cql_search | unknown | description_analysis | low |
+| Base64 file content, optionally as a data URL | unknown | description_analysis | medium |
+
+### State Mutations
+
+The following state-modifying operations were identified from tool schemas:
+
+| Resource | Operation | Scope | Source |
+| --- | --- | --- | --- |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | tool_schema |
+| filesystem | write | working_directory | tool_schema |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+
+_Analyzed at 2026-07-15T22:34:58.279Z_
+
+## Regressions and Recoveries
+
+_Use the `diff` command against another run artifact to classify regressions and recoveries over time._
+
+## Full Capability Status Table
+
+| Focus | Check | Status | Duration (ms) | Message |
+| --- | --- | --- | --- | --- |
+| healthy | conformance | pass | 1.94 | All 7 conformance checks passed. |
+| healthy | tools | pass | 4.51 | Advertised capability responded with the minimal expected shape (25 items). |
+| review | attack-sim | partial | 0.83 | Safe attack simulation found 1 finding(s): 0 high, 1 medium, 0 low. |
+| review | runtime-profile | partial | 0.28 | Detected 6 potential egress target(s) and 44 potential state mutation(s) with high confidence. |
+| review | schema-quality | partial | 1.05 | Found 3 quality finding(s) across 25 item(s): 0 warnings, 3 info. |
+| confirm intent | prompts | unsupported | 0.00 | Prompts are not advertised by the target. |
+| confirm intent | resources | unsupported | 0.00 | Resources are not advertised by the target. |
+| act now | security | fail | 0.87 | Found 1 security finding(s): 1 high, 0 medium, 0 low. |
+| act now | security-lite | fail | 0.06 | Found 1 security finding(s): 1 high, 0 medium, 0 low. |
+
+## Evidence Snippets
+
+### conformance — pass
+
+Summary: All 7 conformance checks passed.
+
+- Endpoint: `conformance/check`
+  - Advertised: `true`
+  - Responded: `true`
+  - Minimal shape present: `true`
+  - Item count: `7`
+  - Identifiers: none
+  - Diagnostics: [pass] capabilities-present: Server returned capabilities object., [pass] server-info: Server provided initialization info., [pass] tools-capability-match: tools/list returned 25 tool(s). (+4 more)
+
+### tools — pass
+
+Summary: Advertised capability responded with the minimal expected shape (25 items).
+
+- Endpoint: `tools/list`
+  - Advertised: `true`
+  - Responded: `true`
+  - Minimal shape present: `true`
+  - Item count: `25`
+  - Identifiers: confluence_configure_connection, confluence_get_connection_status, confluence_get_current_user, confluence_search_pages, confluence_execute_cql_search (+20 more)
+  - Diagnostics: [confluence-mcp] No CONF_* connection env vars found; starting unconfigured., [confluence-mcp] Server running on stdio
+
+### attack-sim — partial
+
+Summary: Safe attack simulation found 1 finding(s): 0 high, 1 medium, 0 low.
+
+- Endpoint: `attack-sim/safe`
+  - Advertised: `true`
+  - Responded: `true`
+  - Minimal shape present: `true`
+  - Item count: `1`
+  - Identifiers: confluence_upload_attachment
+  - Diagnostics: [medium] Tool "confluence_upload_attachment" combines broad parameters (filePath, fileName) with destructive or non-read-only behavior.
+
+### runtime-profile — partial
+
+Summary: Detected 6 potential egress target(s) and 44 potential state mutation(s) with high confidence.
+
+- Endpoint: `runtime-profile/analyze`
+  - Advertised: `true`
+  - Responded: `true`
+  - Minimal shape present: `true`
+  - Item count: `50`
+  - Identifiers: none
+  - Diagnostics: Egress entries: 6, State mutations: 44, Confidence: high
+
+### schema-quality — partial
+
+Summary: Found 3 quality finding(s) across 25 item(s): 0 warnings, 3 info.
+
+- Endpoint: `schema-quality/scan`
+  - Advertised: `true`
+  - Responded: `true`
+  - Minimal shape present: `true`
+  - Item count: `3`
+  - Identifiers: confluence_configure_connection, confluence_search_pages, confluence_list_pending_page_updates
+  - Diagnostics: [info] tool "confluence_configure_connection": Has properties but no 'required' array declared, [info] tool "confluence_search_pages": Has properties but no 'required' array declared, [info] tool "confluence_list_pending_page_updates": Has properties but no 'required' array declared
+
+### prompts — unsupported
+
+Summary: Prompts are not advertised by the target.
+
+- Endpoint: `prompts/list`
+  - Advertised: `false`
+  - Responded: `false`
+  - Minimal shape present: `false`
+  - Item count: `0`
+  - Identifiers: none
+  - Diagnostics: none
+
+### resources — unsupported
+
+Summary: Resources are not advertised by the target.
+
+- Endpoint: `resources/list | resources/templates/list`
+  - Advertised: `false`
+  - Responded: `false`
+  - Minimal shape present: `false`
+  - Item count: `0`
+  - Identifiers: none
+  - Diagnostics: none
+
+### security — fail
+
+Summary: Found 1 security finding(s): 1 high, 0 medium, 0 low.
+
+- Endpoint: `security/scan`
+  - Advertised: `true`
+  - Responded: `true`
+  - Minimal shape present: `true`
+  - Item count: `1`
+  - Identifiers: confluence_execute_cql_search
+  - Diagnostics: [high] Tool "confluence_execute_cql_search" name suggests command execution capability.
+
+### security-lite — fail
+
+Summary: Found 1 security finding(s): 1 high, 0 medium, 0 low.
+
+- Endpoint: `security/scan-lite`
+  - Advertised: `true`
+  - Responded: `true`
+  - Minimal shape present: `true`
+  - Item count: `1`
+  - Identifiers: confluence_execute_cql_search
+  - Diagnostics: [high] Tool "confluence_execute_cql_search" name suggests command execution capability.
+
+## 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_2026-07-15T223457590Z_5e715cc0`
+- Gate: `fail`

package/docs/safety-index/artifacts/context7-server.json

@@ -2,9 +2,9 @@
   "artifactType": "run",
   "schemaVersion": "1.0.0",
   "gate": "pass",
-  "runId": "run_2026-07-06T194948132Z_cb0c4915",
-  "createdAt": "2026-07-06T19:49:48.132Z",
-  "toolVersion": "0.28.0",
+  "runId": "run_2026-07-15T223317716Z_6b43b34a",
+  "createdAt": "2026-07-15T22:33:17.716Z",
+  "toolVersion": "1.32.1",
   "target": {
     "targetId": "context7-server",
     "adapter": "local-process",
@@ -29,8 +29,8 @@
     "nodeVersion": "v22.22.1"
   },
   "summary": {
-    "total": 8,
-    "pass": 7,
+    "total": 9,
+    "pass": 8,
     "fail": 0,
     "partial": 1,
     "unsupported": 0,
@@ -43,7 +43,7 @@
       "id": "tools",
       "capability": "tools",
       "status": "pass",
-      "durationMs": 1.788749999999709,
+      "durationMs": 1.6031249999996362,
       "message": "Advertised capability responded with the minimal expected shape (2 items).",
       "evidence": [
         {
@@ -104,7 +104,7 @@
       "id": "prompts",
       "capability": "prompts",
       "status": "pass",
-      "durationMs": 0.2839160000003176,
+      "durationMs": 0.2611249999999927,
       "message": "Advertised capability responded with the minimal expected shape (0 items).",
       "evidence": [
         {
@@ -124,7 +124,7 @@
       "id": "resources",
       "capability": "resources",
       "status": "pass",
-      "durationMs": 0.4017499999999927,
+      "durationMs": 0.3718750000007276,
       "message": "Advertised capability responded with the minimal expected shape (0 items).",
       "evidence": [
         {
@@ -155,7 +155,7 @@
       "id": "security-lite",
       "capability": "security-lite",
       "status": "pass",
-      "durationMs": 0.02495900000030815,
+      "durationMs": 0.026667000000088592,
       "message": "No security issues detected (lightweight scan).",
       "evidence": [
         {
@@ -167,11 +167,52 @@
         }
       ]
     },
+    {
+      "id": "runtime-profile",
+      "capability": "runtime-profile",
+      "status": "pass",
+      "durationMs": 0.2845000000006621,
+      "message": "Detected 2 potential egress target(s) and 1 potential state mutation(s) with low confidence.",
+      "evidence": [
+        {
+          "endpoint": "runtime-profile/analyze",
+          "advertised": true,
+          "responded": true,
+          "minimalShapePresent": true,
+          "itemCount": 3,
+          "diagnostics": [
+            "Egress entries: 2",
+            "State mutations: 1",
+            "Confidence: medium"
+          ],
+          "findings": [
+            {
+              "target": "The question or task you need help with. This is used to rank library results by relevance to what the user is trying to accomplish. The query is sent to the Context7 API for processing. Do not include any sensitive or confidential information such as API keys, passwords, credentials, personal data, or proprietary code in your query.",
+              "protocol": "unknown",
+              "source": "description_analysis",
+              "confidence": "medium"
+            },
+            {
+              "target": "The question or task you need help with, scoped to a single concept. Be specific and include relevant details, but keep each query to one topic — if the user's question spans multiple distinct concepts, make a separate call per concept instead of combining them, unless the question is about how the concepts interact. Good: 'How to set up authentication with JWT in Express.js' or 'React useEffect cleanup function examples'. Bad (too vague): 'auth' or 'hooks'. Bad (too broad): 'routing and auth and caching in Next.js'. The query is sent to the Context7 API for processing. Do not include any sensitive or confidential information such as API keys, passwords, credentials, personal data, or proprietary code in your query.",
+              "protocol": "unknown",
+              "source": "description_analysis",
+              "confidence": "medium"
+            },
+            {
+              "resource": "filesystem",
+              "operation": "write",
+              "scope": "working_directory",
+              "source": "description_analysis"
+            }
+          ]
+        }
+      ]
+    },
     {
       "id": "conformance",
       "capability": "conformance",
       "status": "pass",
-      "durationMs": 1.094916000000012,
+      "durationMs": 1.04595800000061,
       "message": "All 7 conformance checks passed.",
       "evidence": [
         {
@@ -197,7 +238,7 @@
       "id": "schema-quality",
       "capability": "schema-quality",
       "status": "pass",
-      "durationMs": 0.5149579999997513,
+      "durationMs": 0.4874160000008487,
       "message": "All 2 item(s) have good schema quality.",
       "evidence": [
         {
@@ -214,7 +255,7 @@
       "id": "security",
       "capability": "security",
       "status": "pass",
-      "durationMs": 0.20175000000017462,
+      "durationMs": 0.25229200000012497,
       "message": "No security issues detected.",
       "evidence": [
         {
@@ -230,7 +271,7 @@
       "id": "attack-sim",
       "capability": "attack-sim",
       "status": "partial",
-      "durationMs": 1.0464579999998023,
+      "durationMs": 1.4219579999999041,
       "message": "Safe attack simulation found 2 finding(s): 0 high, 2 medium, 0 low.",
       "evidence": [
         {
@@ -328,16 +369,42 @@
         "weight": 0.1,
         "score": 100,
         "details": [
-          "Connect: 753ms",
+          "Connect: 1506ms",
           "p95 latency: 2ms (3 operations)"
         ]
       }
     ]
   },
   "performanceMetrics": {
-    "connectMs": 753.3337500000002,
-    "toolsListMs": 1.788749999999709,
-    "promptsListMs": 0.2839160000003176,
-    "resourcesListMs": 0.4017499999999927
+    "connectMs": 1506.127125,
+    "toolsListMs": 1.6031249999996362,
+    "promptsListMs": 0.2611249999999927,
+    "resourcesListMs": 0.3718750000007276
+  },
+  "runtimeProfile": {
+    "egress": [
+      {
+        "target": "The question or task you need help with. This is used to rank library results by relevance to what the user is trying to accomplish. The query is sent to the Context7 API for processing. Do not include any sensitive or confidential information such as API keys, passwords, credentials, personal data, or proprietary code in your query.",
+        "protocol": "unknown",
+        "source": "description_analysis",
+        "confidence": "medium"
+      },
+      {
+        "target": "The question or task you need help with, scoped to a single concept. Be specific and include relevant details, but keep each query to one topic — if the user's question spans multiple distinct concepts, make a separate call per concept instead of combining them, unless the question is about how the concepts interact. Good: 'How to set up authentication with JWT in Express.js' or 'React useEffect cleanup function examples'. Bad (too vague): 'auth' or 'hooks'. Bad (too broad): 'routing and auth and caching in Next.js'. The query is sent to the Context7 API for processing. Do not include any sensitive or confidential information such as API keys, passwords, credentials, personal data, or proprietary code in your query.",
+        "protocol": "unknown",
+        "source": "description_analysis",
+        "confidence": "medium"
+      }
+    ],
+    "stateMutations": [
+      {
+        "resource": "filesystem",
+        "operation": "write",
+        "scope": "working_directory",
+        "source": "description_analysis"
+      }
+    ],
+    "analyzedAt": "2026-07-15T22:33:19.225Z",
+    "confidence": "medium"
   }
 }

package/docs/safety-index/artifacts/context7-server.md

@@ -1,6 +1,6 @@
 # MCP Observatory Run Report
 
-Generated at 2026-07-06T19:49:48.132Z
+Generated at 2026-07-15T22:33:17.716Z
 
 ## Target and Environment Metadata
 
@@ -25,7 +25,7 @@ Generated at 2026-07-06T19:49:48.132Z
 
 | Gate | Total | Pass | Fail | Partial | Unsupported | Flaky | Skipped |
 | --- | --- | --- | --- | --- | --- | --- | --- |
-| pass | 8 | 7 | 0 | 1 | 0 | 0 | 0 |
+| pass | 9 | 8 | 0 | 1 | 0 | 0 | 0 |
 
 ## At a Glance
 
@@ -39,6 +39,34 @@ Generated at 2026-07-06T19:49:48.132Z
 - Suggested next step: Review the caveated checks next: attack-sim.
 - 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
+- ℹ️ credential_access: Credential scanning was performed (see security findings)
+- ℹ️ destructive_payloads: Destructive payloads were not attempted (safe-mode only)
+
+## Runtime Profile
+
+### Egress Manifest
+
+The following targets were identified as potentially reachable by this server (confidence: **medium**):
+
+| Target | Protocol | Source | Confidence |
+| --- | --- | --- | --- |
+| The question or task you need help with. This is used to rank library results by relevance to what the user is trying to accomplish. The query is sent to the Context7 API for processing. Do not include any sensitive or confidential information such as API keys, passwords, credentials, personal data, or proprietary code in your query. | unknown | description_analysis | medium |
+| The question or task you need help with, scoped to a single concept. Be specific and include relevant details, but keep each query to one topic — if the user's question spans multiple distinct concepts, make a separate call per concept instead of combining them, unless the question is about how the concepts interact. Good: 'How to set up authentication with JWT in Express.js' or 'React useEffect cleanup function examples'. Bad (too vague): 'auth' or 'hooks'. Bad (too broad): 'routing and auth and caching in Next.js'. The query is sent to the Context7 API for processing. Do not include any sensitive or confidential information such as API keys, passwords, credentials, personal data, or proprietary code in your query. | unknown | description_analysis | medium |
+
+### State Mutations
+
+The following state-modifying operations were identified from tool schemas:
+
+| Resource | Operation | Scope | Source |
+| --- | --- | --- | --- |
+| filesystem | write | working_directory | description_analysis |
+
+_Analyzed at 2026-07-15T22:33:19.225Z_
+
 ## Regressions and Recoveries
 
 _Use the `diff` command against another run artifact to classify regressions and recoveries over time._
@@ -47,14 +75,15 @@ _Use the `diff` command against another run artifact to classify regressions and
 
 | Focus | Check | Status | Duration (ms) | Message |
 | --- | --- | --- | --- | --- |
-| healthy | conformance | pass | 1.09 | All 7 conformance checks passed. |
-| healthy | prompts | pass | 0.28 | Advertised capability responded with the minimal expected shape (0 items). |
-| healthy | resources | pass | 0.40 | Advertised capability responded with the minimal expected shape (0 items). |
-| healthy | schema-quality | pass | 0.51 | All 2 item(s) have good schema quality. |
-| healthy | security | pass | 0.20 | No security issues detected. |
-| healthy | security-lite | pass | 0.02 | No security issues detected (lightweight scan). |
-| healthy | tools | pass | 1.79 | Advertised capability responded with the minimal expected shape (2 items). |
-| review | attack-sim | partial | 1.05 | Safe attack simulation found 2 finding(s): 0 high, 2 medium, 0 low. |
+| healthy | conformance | pass | 1.05 | All 7 conformance checks passed. |
+| healthy | prompts | pass | 0.26 | Advertised capability responded with the minimal expected shape (0 items). |
+| healthy | resources | pass | 0.37 | Advertised capability responded with the minimal expected shape (0 items). |
+| healthy | runtime-profile | pass | 0.28 | Detected 2 potential egress target(s) and 1 potential state mutation(s) with low confidence. |
+| healthy | schema-quality | pass | 0.49 | All 2 item(s) have good schema quality. |
+| healthy | security | pass | 0.25 | No security issues detected. |
+| healthy | security-lite | pass | 0.03 | No security issues detected (lightweight scan). |
+| healthy | tools | pass | 1.60 | Advertised capability responded with the minimal expected shape (2 items). |
+| review | attack-sim | partial | 1.42 | Safe attack simulation found 2 finding(s): 0 high, 2 medium, 0 low. |
 
 ## Evidence Snippets
 
@@ -101,6 +130,18 @@ Summary: Advertised capability responded with the minimal expected shape (0 item
   - Identifiers: none
   - Diagnostics: Context7 Documentation MCP Server v3.2.3 running on stdio
 
+### runtime-profile — pass
+
+Summary: Detected 2 potential egress target(s) and 1 potential state mutation(s) with low confidence.
+
+- Endpoint: `runtime-profile/analyze`
+  - Advertised: `true`
+  - Responded: `true`
+  - Minimal shape present: `true`
+  - Item count: `3`
+  - Identifiers: none
+  - Diagnostics: Egress entries: 2, State mutations: 1, Confidence: medium
+
 ### schema-quality — pass
 
 Summary: All 2 item(s) have good schema quality.
@@ -172,5 +213,5 @@ npm run cli -- report --run <path-to-run-artifact.json> --format markdown
 
 - Artifact type: `run`
 - Schema version: `1.0.0`
-- Run ID: `run_2026-07-06T194948132Z_cb0c4915`
+- Run ID: `run_2026-07-15T223317716Z_6b43b34a`
 - Gate: `pass`

package/docs/safety-index/artifacts/contract-analysis-server.json

@@ -0,0 +1,66 @@
+{
+  "artifactType": "run",
+  "schemaVersion": "1.0.0",
+  "gate": "fail",
+  "runId": "run_2026-07-15T223400017Z_c2485017",
+  "createdAt": "2026-07-15T22:34:00.017Z",
+  "toolVersion": "1.32.1",
+  "target": {
+    "targetId": "contract-analysis-server",
+    "adapter": "local-process",
+    "command": "npx",
+    "args": [
+      "-y",
+      "contract-analysis-mcp"
+    ],
+    "cwd": ".",
+    "metadata": {
+      "package": "contract-analysis-mcp",
+      "purpose": "mcp-safety-index",
+      "riskClass": "Contract data processing",
+      "failureClass": "Document analysis boundary",
+      "whyItMatters": "Contract analysis MCP servers parse, summarize, and extract clauses from legal documents — agents handling contracts need boundaries around confidential document 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 `contract-analysis-server`.\nCommand: npx -y contract-analysis-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  'contract-analysis-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_34_00_090Z-debug-0.log"
+}