@kryptosai/mcp-observatory 1.32.1 → 1.34.0

package/docs/safety-index/artifacts/bhuvan-mcp.md

@@ -0,0 +1,106 @@
+# MCP Observatory Run Report
+
+Generated at 2026-07-15T22:36:00.597Z
+
+## Target and Environment Metadata
+
+- Target: `bhuvan-mcp`
+- Adapter: `local-process`
+- Command: `npx -y bhuvan-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 `bhuvan-mcp`.
+Command: npx -y bhuvan-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  'bhuvan-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_00_675Z-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_2026-07-15T223600597Z_47db61ca`
+- Gate: `fail`

package/docs/safety-index/artifacts/brave-search-mcp-server-v2.json

@@ -0,0 +1,66 @@
+{
+  "artifactType": "run",
+  "schemaVersion": "1.0.0",
+  "gate": "fail",
+  "runId": "run_2026-07-15T223430686Z_4b033b64",
+  "createdAt": "2026-07-15T22:34:30.686Z",
+  "toolVersion": "1.32.1",
+  "target": {
+    "targetId": "brave-search-mcp-server-v2",
+    "adapter": "local-process",
+    "command": "npx",
+    "args": [
+      "-y",
+      "@brave/brave-search-mcp-server"
+    ],
+    "cwd": ".",
+    "metadata": {
+      "package": "@brave/brave-search-mcp-server",
+      "purpose": "mcp-safety-index",
+      "riskClass": "Untrusted content retrieval",
+      "failureClass": "Web search/result boundary",
+      "whyItMatters": "Brave Search MCP v2 returns web results, images, videos, and AI summaries — untrusted content ingestion into agent context with broader result types than v1."
+    }
+  },
+  "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 `brave-search-mcp-server-v2`.\nCommand: npx -y @brave/brave-search-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- Error: --brave-api-key is required. You can get one at https://brave.com/search/api/.\n- Invalid configuration"
+}

package/docs/safety-index/artifacts/brave-search-mcp-server-v2.md

@@ -0,0 +1,103 @@
+# MCP Observatory Run Report
+
+Generated at 2026-07-15T22:34:30.686Z
+
+## Target and Environment Metadata
+
+- Target: `brave-search-mcp-server-v2`
+- Adapter: `local-process`
+- Command: `npx -y @brave/brave-search-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 `brave-search-mcp-server-v2`.
+Command: npx -y @brave/brave-search-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:
+- Error: --brave-api-key is required. You can get one at https://brave.com/search/api/.
+- Invalid configuration
+```
+
+## 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_2026-07-15T223430686Z_4b033b64`
+- Gate: `fail`

package/docs/safety-index/artifacts/brave-search-server.json

@@ -2,9 +2,9 @@
   "artifactType": "run",
   "schemaVersion": "1.0.0",
   "gate": "pass",
-  "runId": "run_2026-07-12T234431584Z_0c1cf559",
-  "createdAt": "2026-07-12T23:44:31.584Z",
-  "toolVersion": "1.31.0",
+  "runId": "run_2026-07-15T223349149Z_75061521",
+  "createdAt": "2026-07-15T22:33:49.149Z",
+  "toolVersion": "1.32.1",
   "target": {
     "targetId": "brave-search-server",
     "adapter": "local-process",
@@ -43,7 +43,7 @@
       "id": "tools",
       "capability": "tools",
       "status": "pass",
-      "durationMs": 0.4080420000027516,
+      "durationMs": 0.45558400000300026,
       "message": "Advertised capability responded with the minimal expected shape (2 items).",
       "evidence": [
         {
@@ -107,7 +107,7 @@
       "id": "prompts",
       "capability": "prompts",
       "status": "unsupported",
-      "durationMs": 0.0007909999985713512,
+      "durationMs": 0.0008329999982379377,
       "message": "Prompts are not advertised by the target.",
       "evidence": [
         {
@@ -123,7 +123,7 @@
       "id": "resources",
       "capability": "resources",
       "status": "unsupported",
-      "durationMs": 0.0005840000012540258,
+      "durationMs": 0.0005410000012489036,
       "message": "Resources are not advertised by the target.",
       "evidence": [
         {
@@ -139,7 +139,7 @@
       "id": "security-lite",
       "capability": "security-lite",
       "status": "pass",
-      "durationMs": 0.02145800000289455,
+      "durationMs": 0.019874999998137355,
       "message": "No security issues detected (lightweight scan).",
       "evidence": [
         {
@@ -155,7 +155,7 @@
       "id": "runtime-profile",
       "capability": "runtime-profile",
       "status": "pass",
-      "durationMs": 0.05570799999986775,
+      "durationMs": 0.04724999999598367,
       "message": "Detected 2 potential egress target(s) and 0 potential state mutation(s) with low confidence.",
       "evidence": [
         {
@@ -190,7 +190,7 @@
       "id": "conformance",
       "capability": "conformance",
       "status": "pass",
-      "durationMs": 0.5054579999996349,
+      "durationMs": 0.5120830000014394,
       "message": "All 7 conformance checks passed.",
       "evidence": [
         {
@@ -216,7 +216,7 @@
       "id": "schema-quality",
       "capability": "schema-quality",
       "status": "pass",
-      "durationMs": 0.21558299999742303,
+      "durationMs": 0.22141700000065612,
       "message": "All 2 item(s) have good schema quality.",
       "evidence": [
         {
@@ -233,7 +233,7 @@
       "id": "security",
       "capability": "security",
       "status": "pass",
-      "durationMs": 0.13141600000381004,
+      "durationMs": 0.1336250000022119,
       "message": "No security issues detected.",
       "evidence": [
         {
@@ -249,7 +249,7 @@
       "id": "attack-sim",
       "capability": "attack-sim",
       "status": "pass",
-      "durationMs": 0.3077080000002752,
+      "durationMs": 0.30258299999695737,
       "message": "Safe attack simulation found no high-risk MCP attack-readiness findings.",
       "evidence": [
         {
@@ -308,17 +308,17 @@
         "weight": 0.1,
         "score": 100,
         "details": [
-          "Connect: 763ms",
+          "Connect: 762ms",
           "p95 latency: 0ms (3 operations)"
         ]
       }
     ]
   },
   "performanceMetrics": {
-    "connectMs": 763.0463339999988,
-    "toolsListMs": 0.4080420000027516,
-    "promptsListMs": 0.0007909999985713512,
-    "resourcesListMs": 0.0005840000012540258
+    "connectMs": 761.5001669999983,
+    "toolsListMs": 0.45558400000300026,
+    "promptsListMs": 0.0008329999982379377,
+    "resourcesListMs": 0.0005410000012489036
   },
   "runtimeProfile": {
     "egress": [
@@ -335,7 +335,7 @@
         "confidence": "low"
       }
     ],
-    "analyzedAt": "2026-07-12T23:44:32.348Z",
+    "analyzedAt": "2026-07-15T22:33:49.912Z",
     "confidence": "medium"
   }
 }

package/docs/safety-index/artifacts/brave-search-server.md

@@ -1,6 +1,6 @@
 # MCP Observatory Run Report
 
-Generated at 2026-07-12T23:44:31.584Z
+Generated at 2026-07-15T22:33:49.149Z
 
 ## Target and Environment Metadata
 
@@ -56,7 +56,7 @@ The following targets were identified as potentially reachable by this server (c
 | brave_web_search | unknown | description_analysis | low |
 | brave_local_search | unknown | description_analysis | low |
 
-_Analyzed at 2026-07-12T23:44:32.348Z_
+_Analyzed at 2026-07-15T22:33:49.912Z_
 
 ## Regressions and Recoveries
 
@@ -66,13 +66,13 @@ _Use the `diff` command against another run artifact to classify regressions and
 
 | Focus | Check | Status | Duration (ms) | Message |
 | --- | --- | --- | --- | --- |
-| healthy | attack-sim | pass | 0.31 | Safe attack simulation found no high-risk MCP attack-readiness findings. |
+| healthy | attack-sim | pass | 0.30 | Safe attack simulation found no high-risk MCP attack-readiness findings. |
 | healthy | conformance | pass | 0.51 | All 7 conformance checks passed. |
-| healthy | runtime-profile | pass | 0.06 | Detected 2 potential egress target(s) and 0 potential state mutation(s) with low confidence. |
+| healthy | runtime-profile | pass | 0.05 | Detected 2 potential egress target(s) and 0 potential state mutation(s) with low confidence. |
 | healthy | schema-quality | pass | 0.22 | All 2 item(s) have good schema quality. |
 | healthy | security | pass | 0.13 | No security issues detected. |
 | healthy | security-lite | pass | 0.02 | No security issues detected (lightweight scan). |
-| healthy | tools | pass | 0.41 | Advertised capability responded with the minimal expected shape (2 items). |
+| healthy | tools | pass | 0.46 | Advertised capability responded with the minimal expected shape (2 items). |
 | 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. |
 
@@ -197,5 +197,5 @@ npm run cli -- report --run <path-to-run-artifact.json> --format markdown
 
 - Artifact type: `run`
 - Schema version: `1.0.0`
-- Run ID: `run_2026-07-12T234431584Z_0c1cf559`
+- Run ID: `run_2026-07-15T223349149Z_75061521`
 - Gate: `pass`

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

@@ -2,9 +2,9 @@
   "artifactType": "run",
   "schemaVersion": "1.0.0",
   "gate": "pass",
-  "runId": "run_2026-07-12T234409514Z_67c87a4e",
-  "createdAt": "2026-07-12T23:44:09.514Z",
-  "toolVersion": "1.31.0",
+  "runId": "run_2026-07-17T003632701Z_d2b3603f",
+  "createdAt": "2026-07-17T00:36:32.701Z",
+  "toolVersion": "1.33.0",
   "target": {
     "targetId": "browsermcp-server",
     "adapter": "local-process",
@@ -43,7 +43,7 @@
       "id": "tools",
       "capability": "tools",
       "status": "pass",
-      "durationMs": 0.9639999999999418,
+      "durationMs": 0.9412910000010015,
       "message": "Advertised capability responded with the minimal expected shape (12 items).",
       "evidence": [
         {
@@ -242,7 +242,7 @@
       "id": "prompts",
       "capability": "prompts",
       "status": "unsupported",
-      "durationMs": 0.0009160000008705538,
+      "durationMs": 0.0009169999993901001,
       "message": "Prompts are not advertised by the target.",
       "evidence": [
         {
@@ -258,7 +258,7 @@
       "id": "resources",
       "capability": "resources",
       "status": "pass",
-      "durationMs": 0.4857090000004973,
+      "durationMs": 0.4441659999993135,
       "message": "Advertised capability responded with the minimal expected shape, but one optional resource endpoint appears unsupported.",
       "evidence": [
         {
@@ -285,7 +285,7 @@
       "id": "security-lite",
       "capability": "security-lite",
       "status": "pass",
-      "durationMs": 0.027999999998428393,
+      "durationMs": 0.026583999999274965,
       "message": "No security issues detected (lightweight scan).",
       "evidence": [
         {
@@ -301,7 +301,7 @@
       "id": "runtime-profile",
       "capability": "runtime-profile",
       "status": "partial",
-      "durationMs": 0.08887500000128057,
+      "durationMs": 0.08045800000036252,
       "message": "Detected 3 potential egress target(s) and 0 potential state mutation(s) with high confidence.",
       "evidence": [
         {
@@ -342,7 +342,7 @@
       "id": "conformance",
       "capability": "conformance",
       "status": "pass",
-      "durationMs": 1.643000000000029,
+      "durationMs": 1.7910000000010768,
       "message": "All 7 conformance checks passed.",
       "evidence": [
         {
@@ -368,7 +368,7 @@
       "id": "schema-quality",
       "capability": "schema-quality",
       "status": "pass",
-      "durationMs": 0.4385839999995369,
+      "durationMs": 0.363999999999578,
       "message": "All 12 item(s) have good schema quality.",
       "evidence": [
         {
@@ -385,7 +385,7 @@
       "id": "security",
       "capability": "security",
       "status": "pass",
-      "durationMs": 0.15845899999840185,
+      "durationMs": 0.16358300000138115,
       "message": "No security issues detected.",
       "evidence": [
         {
@@ -401,7 +401,7 @@
       "id": "attack-sim",
       "capability": "attack-sim",
       "status": "pass",
-      "durationMs": 0.5191660000018601,
+      "durationMs": 0.40025000000059663,
       "message": "Safe attack simulation found no high-risk MCP attack-readiness findings.",
       "evidence": [
         {
@@ -460,17 +460,17 @@
         "weight": 0.1,
         "score": 100,
         "details": [
-          "Connect: 869ms",
+          "Connect: 712ms",
           "p95 latency: 1ms (3 operations)"
         ]
       }
     ]
   },
   "performanceMetrics": {
-    "connectMs": 868.9238330000007,
-    "toolsListMs": 0.9639999999999418,
-    "promptsListMs": 0.0009160000008705538,
-    "resourcesListMs": 0.4857090000004973
+    "connectMs": 712.0667080000003,
+    "toolsListMs": 0.9412910000010015,
+    "promptsListMs": 0.0009169999993901001,
+    "resourcesListMs": 0.4441659999993135
   },
   "runtimeProfile": {
     "egress": [
@@ -493,7 +493,7 @@
         "confidence": "low"
       }
     ],
-    "analyzedAt": "2026-07-12T23:44:10.385Z",
+    "analyzedAt": "2026-07-17T00:36:33.415Z",
     "confidence": "high"
   }
 }

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

@@ -1,6 +1,6 @@
 # MCP Observatory Run Report
 
-Generated at 2026-07-12T23:44:09.514Z
+Generated at 2026-07-17T00:36:32.701Z
 
 ## Target and Environment Metadata
 
@@ -58,7 +58,7 @@ The following targets were identified as potentially reachable by this server (c
 | The URL to navigate to | unknown | description_analysis | medium |
 | browser_navigate | unknown | description_analysis | low |
 
-_Analyzed at 2026-07-12T23:44:10.385Z_
+_Analyzed at 2026-07-17T00:36:33.415Z_
 
 ## Regressions and Recoveries
 
@@ -68,14 +68,14 @@ _Use the `diff` command against another run artifact to classify regressions and
 
 | Focus | Check | Status | Duration (ms) | Message |
 | --- | --- | --- | --- | --- |
-| healthy | attack-sim | pass | 0.52 | Safe attack simulation found no high-risk MCP attack-readiness findings. |
-| healthy | conformance | pass | 1.64 | All 7 conformance checks passed. |
-| healthy | resources | pass | 0.49 | Advertised capability responded with the minimal expected shape, but one optional resource endpoint appears unsupported. |
-| healthy | schema-quality | pass | 0.44 | All 12 item(s) have good schema quality. |
+| healthy | attack-sim | pass | 0.40 | Safe attack simulation found no high-risk MCP attack-readiness findings. |
+| healthy | conformance | pass | 1.79 | All 7 conformance checks passed. |
+| healthy | resources | pass | 0.44 | Advertised capability responded with the minimal expected shape, but one optional resource endpoint appears unsupported. |
+| healthy | schema-quality | pass | 0.36 | All 12 item(s) have good schema quality. |
 | healthy | security | pass | 0.16 | No security issues detected. |
 | healthy | security-lite | pass | 0.03 | No security issues detected (lightweight scan). |
-| healthy | tools | pass | 0.96 | Advertised capability responded with the minimal expected shape (12 items). |
-| review | runtime-profile | partial | 0.09 | Detected 3 potential egress target(s) and 0 potential state mutation(s) with high confidence. |
+| healthy | tools | pass | 0.94 | Advertised capability responded with the minimal expected shape (12 items). |
+| review | runtime-profile | partial | 0.08 | Detected 3 potential egress target(s) and 0 potential state mutation(s) with high confidence. |
 | confirm intent | prompts | unsupported | 0.00 | Prompts are not advertised by the target. |
 
 ## Evidence Snippets
@@ -206,5 +206,5 @@ npm run cli -- report --run <path-to-run-artifact.json> --format markdown
 
 - Artifact type: `run`
 - Schema version: `1.0.0`
-- Run ID: `run_2026-07-12T234409514Z_67c87a4e`
+- Run ID: `run_2026-07-17T003632701Z_d2b3603f`
 - Gate: `pass`

package/docs/safety-index/artifacts/cal-com-mcp.json

@@ -0,0 +1,66 @@
+{
+  "artifactType": "run",
+  "schemaVersion": "1.0.0",
+  "gate": "fail",
+  "runId": "run_2026-07-15T223543015Z_2e6cd958",
+  "createdAt": "2026-07-15T22:35:43.015Z",
+  "toolVersion": "1.32.1",
+  "target": {
+    "targetId": "cal-com-mcp",
+    "adapter": "local-process",
+    "command": "npx",
+    "args": [
+      "-y",
+      "cal-com-mcp"
+    ],
+    "cwd": ".",
+    "metadata": {
+      "package": "cal-com-mcp",
+      "purpose": "mcp-safety-index",
+      "riskClass": "Scheduling and calendar API access",
+      "failureClass": "Booking/availability/calendar boundary",
+      "whyItMatters": "Cal.com (46K+ GitHub stars, Indian-origin OSS) powers scheduling for millions. MCP servers creating bookings, managing availability, and accessing calendars handle time-sensitive commitment 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 `cal-com-mcp`.\nCommand: npx -y cal-com-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  'cal-com-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_43_096Z-debug-0.log"
+}