@kryptosai/mcp-observatory 1.32.0 → 1.33.0

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

@@ -0,0 +1,243 @@
+# MCP Observatory Run Report
+
+Generated at 2026-07-15T22:33:42.802Z
+
+## Target and Environment Metadata
+
+- Target: `firecrawl-server`
+- Adapter: `local-process`
+- Command: `npx -y firecrawl-mcp`
+- Server: `firecrawl-fastmcp 3.22.3`
+- Platform: `darwin 25.5.0`
+- Node: `v22.22.1`
+
+## Executive Summary
+
+**Health Score: 53/100 (F)**
+
+| Dimension | Score | Weight |
+| --- | --- | --- |
+| Protocol Compliance | 60/100 | 30% |
+| Schema Quality | 60/100 | 20% |
+| Security | 0/100 | 20% |
+| Reliability | 67/100 | 20% |
+| Performance | 100/100 | 10% |
+
+| Gate | Total | Pass | Fail | Partial | Unsupported | Flaky | Skipped |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| fail | 9 | 1 | 3 | 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: conformance: 6/7 conformance checks passed, 1 failed.; runtime-profile: Detected 21 potential egress target(s) and 16 potential state mutation(s) with high confidence.; schema-quality: Found 147 quality finding(s) across 26 item(s): 0 warnings, 147 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, attack-sim
+- Partial or flaky checks: runtime-profile, conformance, schema-quality
+- Skipped checks: none
+- Unsupported checks: prompts, resources
+- Suggested next step: Start with the failing checks: security-lite, security, 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
+- 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 |
+| --- | --- | --- | --- |
+| url | unknown | tool_schema | high |
+| firecrawl_scrape | unknown | description_analysis | low |
+| url | unknown | tool_schema | high |
+| firecrawl_map | unknown | description_analysis | low |
+| firecrawl_search | unknown | description_analysis | low |
+| firecrawl_search_feedback | unknown | description_analysis | low |
+| endpoint | unknown | tool_schema | high |
+| url | unknown | tool_schema | high |
+| firecrawl_feedback | unknown | description_analysis | low |
+| url | unknown | tool_schema | high |
+| webhook | unknown | tool_schema | high |
+| firecrawl_crawl | unknown | description_analysis | low |
+| firecrawl_extract | unknown | description_analysis | low |
+| firecrawl_agent | unknown | description_analysis | low |
+| url | unknown | tool_schema | high |
+| firecrawl_interact | unknown | description_analysis | low |
+| firecrawl_parse | unknown | description_analysis | low |
+| firecrawl_monitor_create | unknown | description_analysis | low |
+| firecrawl_monitor_update | unknown | description_analysis | low |
+| firecrawl_monitor_check | unknown | description_analysis | low |
+| firecrawl_research_search_github | unknown | description_analysis | low |
+
+### 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 | 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 |
+| 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 | execute | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+| filesystem | write | working_directory | description_analysis |
+
+_Analyzed at 2026-07-15T22:33:43.769Z_
+
+## 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 | tools | pass | 8.35 | Advertised capability responded with the minimal expected shape (26 items). |
+| review | conformance | partial | 2.92 | 6/7 conformance checks passed, 1 failed. |
+| review | runtime-profile | partial | 0.41 | Detected 21 potential egress target(s) and 16 potential state mutation(s) with high confidence. |
+| review | schema-quality | partial | 1.02 | Found 147 quality finding(s) across 26 item(s): 0 warnings, 147 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 | attack-sim | fail | 1.70 | Safe attack simulation found 9 finding(s): 1 high, 8 medium, 0 low. |
+| act now | security | fail | 1.07 | Found 1 security finding(s): 1 high, 0 medium, 0 low. |
+| act now | security-lite | fail | 0.42 | Found 1 security finding(s): 1 high, 0 medium, 0 low. |
+
+## Evidence Snippets
+
+### tools — pass
+
+Summary: Advertised capability responded with the minimal expected shape (26 items).
+
+- Endpoint: `tools/list`
+  - Advertised: `true`
+  - Responded: `true`
+  - Minimal shape present: `true`
+  - Item count: `26`
+  - Identifiers: firecrawl_scrape, firecrawl_map, firecrawl_search, firecrawl_search_feedback, firecrawl_feedback (+21 more)
+  - Diagnostics: No FIRECRAWL_API_KEY or FIRECRAWL_API_URL set — running in keyless mode. firecrawl_scrape and firecrawl_search are free (rate-limited per IP) against the Firecrawl cloud; other tools require an API key (get one free at https://firecrawl.dev).
+
+### conformance — partial
+
+Summary: 6/7 conformance checks passed, 1 failed.
+
+- Endpoint: `conformance/check`
+  - Advertised: `true`
+  - Responded: `true`
+  - Minimal shape present: `false`
+  - Item count: `7`
+  - Identifiers: tool-response-content
+  - Diagnostics: [pass] capabilities-present: Server returned capabilities object., [pass] server-info: Server provided initialization info., [pass] tools-capability-match: tools/list returned 26 tool(s). (+4 more)
+
+### runtime-profile — partial
+
+Summary: Detected 21 potential egress target(s) and 16 potential state mutation(s) with high confidence.
+
+- Endpoint: `runtime-profile/analyze`
+  - Advertised: `true`
+  - Responded: `true`
+  - Minimal shape present: `true`
+  - Item count: `37`
+  - Identifiers: none
+  - Diagnostics: Egress entries: 21, State mutations: 16, Confidence: high
+
+### schema-quality — partial
+
+Summary: Found 147 quality finding(s) across 26 item(s): 0 warnings, 147 info.
+
+- Endpoint: `schema-quality/scan`
+  - Advertised: `true`
+  - Responded: `true`
+  - Minimal shape present: `true`
+  - Item count: `147`
+  - Identifiers: firecrawl_scrape, firecrawl_map, firecrawl_search, firecrawl_search_feedback, firecrawl_feedback (+19 more)
+  - Diagnostics: [info] tool "firecrawl_scrape": Property 'url' missing description, [info] tool "firecrawl_scrape": Property 'formats' missing description, [info] tool "firecrawl_scrape": Property 'jsonOptions' missing description (+144 more)
+
+### 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
+
+### attack-sim — fail
+
+Summary: Safe attack simulation found 9 finding(s): 1 high, 8 medium, 0 low.
+
+- Endpoint: `attack-sim/safe`
+  - Advertised: `true`
+  - Responded: `true`
+  - Minimal shape present: `true`
+  - Item count: `9`
+  - Identifiers: firecrawl_scrape, firecrawl_search, firecrawl_feedback, firecrawl_crawl, firecrawl_interact (+4 more)
+  - Diagnostics: [medium] Tool "firecrawl_scrape" combines broad parameters (url) with destructive or non-read-only behavior., [medium] Tool "firecrawl_search" combines broad parameters (query) with destructive or non-read-only behavior., [medium] Tool "firecrawl_feedback" combines broad parameters (endpoint, url) with destructive or non-read-only behavior. (+6 more)
+
+### 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: firecrawl_interact
+  - Diagnostics: [high] Tool "firecrawl_interact" has parameter "code" which may allow arbitrary command execution.
+
+### 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: firecrawl_interact
+  - Diagnostics: [high] Tool "firecrawl_interact" has parameter "code" which may allow arbitrary command execution.
+
+## 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_2026-07-15T223342802Z_482400a3`
+- Gate: `fail`

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

@@ -0,0 +1,66 @@
+{
+  "artifactType": "run",
+  "schemaVersion": "1.0.0",
+  "gate": "fail",
+  "runId": "run_2026-07-15T223402661Z_7e29b8a7",
+  "createdAt": "2026-07-15T22:34:02.661Z",
+  "toolVersion": "1.32.1",
+  "target": {
+    "targetId": "flight-server",
+    "adapter": "local-process",
+    "command": "npx",
+    "args": [
+      "-y",
+      "flight-mcp-server"
+    ],
+    "cwd": ".",
+    "metadata": {
+      "package": "flight-mcp-server",
+      "purpose": "mcp-safety-index",
+      "riskClass": "Travel booking API access",
+      "failureClass": "Flight search boundary",
+      "whyItMatters": "Flight MCP servers search, compare, and book flights through airline APIs — agents with booking access need payment and itinerary confirmation boundaries."
+    }
+  },
+  "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 `flight-server`.\nCommand: npx -y flight-mcp-server\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- at runServer (file:///Users/williamweishuhn/.npm/_npx/0492f3c9bc39e9d7/node_modules/flight-mcp-server/dist/index.js:12:24)\n- at file:///Users/williamweishuhn/.npm/_npx/0492f3c9bc39e9d7/node_modules/flight-mcp-server/dist/index.js:26:1\n- at ModuleJob.run (node:internal/modules/esm/module_job:343:25)\n- at async onImport.tracePromise.__proto__ (node:internal/modules/esm/loader:665:26)\n- at async asyncRunEntryPointWithESMLoader (node:internal/modules/run_main:117:5)"
+}

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

@@ -0,0 +1,106 @@
+# MCP Observatory Run Report
+
+Generated at 2026-07-15T22:34:02.661Z
+
+## Target and Environment Metadata
+
+- Target: `flight-server`
+- Adapter: `local-process`
+- Command: `npx -y flight-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>"`
+
+## 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 `flight-server`.
+Command: npx -y flight-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:
+- at runServer (file:///Users/williamweishuhn/.npm/_npx/0492f3c9bc39e9d7/node_modules/flight-mcp-server/dist/index.js:12:24)
+- at file:///Users/williamweishuhn/.npm/_npx/0492f3c9bc39e9d7/node_modules/flight-mcp-server/dist/index.js:26:1
+- at ModuleJob.run (node:internal/modules/esm/module_job:343:25)
+- at async onImport.tracePromise.__proto__ (node:internal/modules/esm/loader:665:26)
+- at async asyncRunEntryPointWithESMLoader (node:internal/modules/run_main:117:5)
+```
+
+## 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_2026-07-15T223402661Z_7e29b8a7`
+- Gate: `fail`

package/docs/safety-index/artifacts/foodpanda-pakistan-mcp.json

@@ -0,0 +1,66 @@
+{
+  "artifactType": "run",
+  "schemaVersion": "1.0.0",
+  "gate": "fail",
+  "runId": "run_2026-07-15T223601442Z_a60172b9",
+  "createdAt": "2026-07-15T22:36:01.442Z",
+  "toolVersion": "1.32.1",
+  "target": {
+    "targetId": "foodpanda-pakistan-mcp",
+    "adapter": "local-process",
+    "command": "npx",
+    "args": [
+      "-y",
+      "foodpanda-pakistan-mcp"
+    ],
+    "cwd": ".",
+    "metadata": {
+      "package": "foodpanda-pakistan-mcp",
+      "purpose": "mcp-safety-index",
+      "riskClass": "Pakistani food delivery platform API access",
+      "failureClass": "Order/restaurant/delivery boundary",
+      "whyItMatters": "Foodpanda is Pakistan's largest food delivery platform covering all major cities. MCP servers exposing order management, restaurant data, and delivery tracking handle real-time logistics and payment data for millions of users."
+    }
+  },
+  "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 `foodpanda-pakistan-mcp`.\nCommand: npx -y foodpanda-pakistan-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  'foodpanda-pakistan-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_36_01_517Z-debug-0.log"
+}

package/docs/safety-index/artifacts/foodpanda-pakistan-mcp.md

@@ -0,0 +1,106 @@
+# MCP Observatory Run Report
+
+Generated at 2026-07-15T22:36:01.442Z
+
+## Target and Environment Metadata
+
+- Target: `foodpanda-pakistan-mcp`
+- Adapter: `local-process`
+- Command: `npx -y foodpanda-pakistan-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 `foodpanda-pakistan-mcp`.
+Command: npx -y foodpanda-pakistan-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  'foodpanda-pakistan-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_36_01_517Z-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_2026-07-15T223601442Z_a60172b9`
+- Gate: `fail`

package/docs/safety-index/artifacts/gcp-mcp-server.json

@@ -0,0 +1,66 @@
+{
+  "artifactType": "run",
+  "schemaVersion": "1.0.0",
+  "gate": "fail",
+  "runId": "run_2026-07-15T223451316Z_f7d490a7",
+  "createdAt": "2026-07-15T22:34:51.316Z",
+  "toolVersion": "1.32.1",
+  "target": {
+    "targetId": "gcp-mcp-server",
+    "adapter": "local-process",
+    "command": "npx",
+    "args": [
+      "-y",
+      "mcp-server-gcp"
+    ],
+    "cwd": ".",
+    "metadata": {
+      "package": "mcp-server-gcp",
+      "purpose": "mcp-safety-index",
+      "riskClass": "Cloud infrastructure control",
+      "failureClass": "GCP service boundary",
+      "whyItMatters": "GCP MCP servers can interact with Compute Engine, Cloud Storage, BigQuery, and other GCP services — broad cloud control surface."
+    }
+  },
+  "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 `gcp-mcp-server`.\nCommand: npx -y mcp-server-gcp\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 could not determine executable to run\n- npm error A complete log of this run can be found in: /Users/williamweishuhn/.npm/_logs/2026-07-15T22_34_51_384Z-debug-0.log"
+}