@kryptosai/mcp-observatory 1.32.0 → 1.33.0

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

@@ -0,0 +1,106 @@
+# MCP Observatory Run Report
+
+Generated at 2026-07-15T22:33:44.649Z
+
+## Target and Environment Metadata
+
+- Target: `sentry-server`
+- Adapter: `local-process`
+- Command: `npx -y @sentry/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 `sentry-server`.
+Command: npx -y @sentry/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:
+- @sentry/mcp-server --access-token=TOKEN --host=sentry.internal:9000 --insecure-http
+- @sentry/mcp-server --access-token=TOKEN --host=sentry.example.com --disable-skills=seer
+- @sentry/mcp-server --access-token=TOKEN --agent-provider=azure-openai --openai-base-url=https://example.openai.azure.com/openai/v1/
+- @sentry/mcp-server --access-token=TOKEN --agent-provider=anthropic
+- @sentry/mcp-server --access-token=TOKEN --agent-provider=openrouter
+```
+
+## 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_2026-07-15T223344649Z_b28e28f1`
+- Gate: `fail`

package/docs/safety-index/artifacts/sequential-thinking-server.json

@@ -2,9 +2,9 @@
   "artifactType": "run",
   "schemaVersion": "1.0.0",
   "gate": "pass",
-  "runId": "run_2026-07-06T194946140Z_d608f553",
-  "createdAt": "2026-07-06T19:49:46.140Z",
-  "toolVersion": "0.28.0",
+  "runId": "run_2026-07-15T223314258Z_b0743985",
+  "createdAt": "2026-07-15T22:33:14.258Z",
+  "toolVersion": "1.32.1",
   "target": {
     "targetId": "sequential-thinking-server",
     "adapter": "local-process",
@@ -29,8 +29,8 @@
     "nodeVersion": "v22.22.1"
   },
   "summary": {
-    "total": 8,
-    "pass": 6,
+    "total": 9,
+    "pass": 7,
     "fail": 0,
     "partial": 0,
     "unsupported": 2,
@@ -43,7 +43,7 @@
       "id": "tools",
       "capability": "tools",
       "status": "pass",
-      "durationMs": 3.737249999999676,
+      "durationMs": 3.7027079999998023,
       "message": "Advertised capability responded with the minimal expected shape (1 item).",
       "evidence": [
         {
@@ -122,7 +122,7 @@
       "id": "prompts",
       "capability": "prompts",
       "status": "unsupported",
-      "durationMs": 0.00408400000014808,
+      "durationMs": 0.0025829999999587017,
       "message": "Prompts are not advertised by the target.",
       "evidence": [
         {
@@ -138,7 +138,7 @@
       "id": "resources",
       "capability": "resources",
       "status": "unsupported",
-      "durationMs": 0.0015830000002097222,
+      "durationMs": 0.0014160000000629225,
       "message": "Resources are not advertised by the target.",
       "evidence": [
         {
@@ -154,7 +154,7 @@
       "id": "security-lite",
       "capability": "security-lite",
       "status": "pass",
-      "durationMs": 0.0753340000001117,
+      "durationMs": 0.028458000000227912,
       "message": "No security issues detected (lightweight scan).",
       "evidence": [
         {
@@ -166,11 +166,40 @@
         }
       ]
     },
+    {
+      "id": "runtime-profile",
+      "capability": "runtime-profile",
+      "status": "pass",
+      "durationMs": 0.07162500000004002,
+      "message": "Detected 0 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": 1,
+          "diagnostics": [
+            "Egress entries: 0",
+            "State mutations: 1",
+            "Confidence: medium"
+          ],
+          "findings": [
+            {
+              "resource": "filesystem",
+              "operation": "write",
+              "scope": "working_directory",
+              "source": "description_analysis"
+            }
+          ]
+        }
+      ]
+    },
     {
       "id": "conformance",
       "capability": "conformance",
       "status": "pass",
-      "durationMs": 1.5115419999997357,
+      "durationMs": 1.5712499999999636,
       "message": "All 7 conformance checks passed.",
       "evidence": [
         {
@@ -196,7 +225,7 @@
       "id": "schema-quality",
       "capability": "schema-quality",
       "status": "pass",
-      "durationMs": 0.8508339999998498,
+      "durationMs": 0.81179099999963,
       "message": "All 1 item(s) have good schema quality.",
       "evidence": [
         {
@@ -213,7 +242,7 @@
       "id": "security",
       "capability": "security",
       "status": "pass",
-      "durationMs": 0.908542000000125,
+      "durationMs": 0.9031660000000556,
       "message": "No security issues detected.",
       "evidence": [
         {
@@ -229,7 +258,7 @@
       "id": "attack-sim",
       "capability": "attack-sim",
       "status": "pass",
-      "durationMs": 0.819166000000223,
+      "durationMs": 0.8238340000002609,
       "message": "Safe attack simulation found no high-risk MCP attack-readiness findings.",
       "evidence": [
         {
@@ -288,16 +317,28 @@
         "weight": 0.1,
         "score": 100,
         "details": [
-          "Connect: 614ms",
+          "Connect: 840ms",
           "p95 latency: 4ms (3 operations)"
         ]
       }
     ]
   },
   "performanceMetrics": {
-    "connectMs": 614.4627080000002,
-    "toolsListMs": 3.737249999999676,
-    "promptsListMs": 0.00408400000014808,
-    "resourcesListMs": 0.0015830000002097222
+    "connectMs": 839.9979169999999,
+    "toolsListMs": 3.7027079999998023,
+    "promptsListMs": 0.0025829999999587017,
+    "resourcesListMs": 0.0014160000000629225
+  },
+  "runtimeProfile": {
+    "stateMutations": [
+      {
+        "resource": "filesystem",
+        "operation": "write",
+        "scope": "working_directory",
+        "source": "description_analysis"
+      }
+    ],
+    "analyzedAt": "2026-07-15T22:33:15.104Z",
+    "confidence": "medium"
   }
 }

package/docs/safety-index/artifacts/sequential-thinking-server.md

@@ -1,6 +1,6 @@
 # MCP Observatory Run Report
 
-Generated at 2026-07-06T19:49:46.140Z
+Generated at 2026-07-15T22:33:14.258Z
 
 ## Target and Environment Metadata
 
@@ -25,7 +25,7 @@ Generated at 2026-07-06T19:49:46.140Z
 
 | Gate | Total | Pass | Fail | Partial | Unsupported | Flaky | Skipped |
 | --- | --- | --- | --- | --- | --- | --- | --- |
-| pass | 8 | 6 | 0 | 0 | 2 | 0 | 0 |
+| pass | 9 | 7 | 0 | 0 | 2 | 0 | 0 |
 
 ## At a Glance
 
@@ -39,6 +39,25 @@ Generated at 2026-07-06T19:49:46.140Z
 - Suggested next step: Confirm that unsupported capabilities are intentional for this target: prompts, resources.
 - 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
+
+### State Mutations
+
+The following state-modifying operations were identified from tool schemas:
+
+| Resource | Operation | Scope | Source |
+| --- | --- | --- | --- |
+| filesystem | write | working_directory | description_analysis |
+
+_Analyzed at 2026-07-15T22:33:15.104Z_
+
 ## Regressions and Recoveries
 
 _Use the `diff` command against another run artifact to classify regressions and recoveries over time._
@@ -48,11 +67,12 @@ _Use the `diff` command against another run artifact to classify regressions and
 | Focus | Check | Status | Duration (ms) | Message |
 | --- | --- | --- | --- | --- |
 | healthy | attack-sim | pass | 0.82 | Safe attack simulation found no high-risk MCP attack-readiness findings. |
-| healthy | conformance | pass | 1.51 | All 7 conformance checks passed. |
-| healthy | schema-quality | pass | 0.85 | All 1 item(s) have good schema quality. |
-| healthy | security | pass | 0.91 | No security issues detected. |
-| healthy | security-lite | pass | 0.08 | No security issues detected (lightweight scan). |
-| healthy | tools | pass | 3.74 | Advertised capability responded with the minimal expected shape (1 item). |
+| healthy | conformance | pass | 1.57 | All 7 conformance checks passed. |
+| healthy | runtime-profile | pass | 0.07 | Detected 0 potential egress target(s) and 1 potential state mutation(s) with low confidence. |
+| healthy | schema-quality | pass | 0.81 | All 1 item(s) have good schema quality. |
+| healthy | security | pass | 0.90 | No security issues detected. |
+| healthy | security-lite | pass | 0.03 | No security issues detected (lightweight scan). |
+| healthy | tools | pass | 3.70 | Advertised capability responded with the minimal expected shape (1 item). |
 | 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. |
 
@@ -82,6 +102,18 @@ Summary: All 7 conformance checks passed.
   - Identifiers: none
   - Diagnostics: [pass] capabilities-present: Server returned capabilities object., [pass] server-info: Server provided initialization info., [pass] tools-capability-match: tools/list returned 1 tool(s). (+4 more)
 
+### runtime-profile — pass
+
+Summary: Detected 0 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: `1`
+  - Identifiers: none
+  - Diagnostics: Egress entries: 0, State mutations: 1, Confidence: medium
+
 ### schema-quality — pass
 
 Summary: All 1 item(s) have good schema quality.
@@ -165,5 +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_2026-07-06T194946140Z_d608f553`
+- Run ID: `run_2026-07-15T223314258Z_b0743985`
 - Gate: `pass`

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

@@ -0,0 +1,66 @@
+{
+  "artifactType": "run",
+  "schemaVersion": "1.0.0",
+  "gate": "fail",
+  "runId": "run_2026-07-15T223445738Z_0e225507",
+  "createdAt": "2026-07-15T22:34:45.738Z",
+  "toolVersion": "1.32.1",
+  "target": {
+    "targetId": "shopify-mcp-server",
+    "adapter": "local-process",
+    "command": "npx",
+    "args": [
+      "-y",
+      "shopify-mcp"
+    ],
+    "cwd": ".",
+    "metadata": {
+      "package": "shopify-mcp",
+      "purpose": "mcp-safety-index",
+      "riskClass": "Store data access",
+      "failureClass": "Product/order boundary",
+      "whyItMatters": "Shopify MCP servers expose store products, orders, customers, and inventory via the GraphQL API — agents could modify product listings, process orders, or manage storefront data with financial consequences."
+    }
+  },
+  "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 `shopify-mcp-server`.\nCommand: npx -y shopify-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- Error: Authentication credentials are required.\n- Option 1 — Static access token (legacy apps):\n- --accessToken=shpat_xxxxx\n- Option 2 — Client credentials (Dev Dashboard apps, Jan 2026+):\n- --clientId=your_client_id --clientSecret=your_client_secret"
+}

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

@@ -0,0 +1,106 @@
+# MCP Observatory Run Report
+
+Generated at 2026-07-15T22:34:45.738Z
+
+## Target and Environment Metadata
+
+- Target: `shopify-mcp-server`
+- Adapter: `local-process`
+- Command: `npx -y shopify-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 `shopify-mcp-server`.
+Command: npx -y shopify-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:
+- Error: Authentication credentials are required.
+- Option 1 — Static access token (legacy apps):
+- --accessToken=shpat_xxxxx
+- Option 2 — Client credentials (Dev Dashboard apps, Jan 2026+):
+- --clientId=your_client_id --clientSecret=your_client_secret
+```
+
+## 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_2026-07-15T223445738Z_0e225507`
+- Gate: `fail`

package/docs/safety-index/artifacts/shopify-mcp.json

@@ -0,0 +1,66 @@
+{
+  "artifactType": "run",
+  "schemaVersion": "1.0.0",
+  "gate": "fail",
+  "runId": "run_2026-07-15T223451620Z_10ed929a",
+  "createdAt": "2026-07-15T22:34:51.620Z",
+  "toolVersion": "1.32.1",
+  "target": {
+    "targetId": "shopify-mcp",
+    "adapter": "local-process",
+    "command": "npx",
+    "args": [
+      "-y",
+      "shopify-mcp"
+    ],
+    "cwd": ".",
+    "metadata": {
+      "package": "shopify-mcp",
+      "purpose": "mcp-safety-index",
+      "riskClass": "E-commerce platform access",
+      "failureClass": "Store/product/order boundary",
+      "whyItMatters": "Shopify MCP servers can manage products, orders, customers, and store settings — agents could modify live e-commerce operations."
+    }
+  },
+  "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 `shopify-mcp`.\nCommand: npx -y shopify-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- Error: Authentication credentials are required.\n- Option 1 — Static access token (legacy apps):\n- --accessToken=shpat_xxxxx\n- Option 2 — Client credentials (Dev Dashboard apps, Jan 2026+):\n- --clientId=your_client_id --clientSecret=your_client_secret"
+}