@kryptosai/mcp-observatory 0.28.0 → 1.28.2

package/docs/safety-index/artifacts/executeautomation-playwright-server.md

@@ -1,6 +1,6 @@
 # MCP Observatory Run Report
 
-Generated at 2026-07-06T01:47:05.638Z
+Generated at 2026-07-06T19:49:57.956Z
 
 ## Target and Environment Metadata
 
@@ -8,8 +8,8 @@ Generated at 2026-07-06T01:47:05.638Z
 - Adapter: `local-process`
 - Command: `npx -y @executeautomation/playwright-mcp-server`
 - Server: `playwright-mcp 1.0.11`
-- Platform: `darwin 24.0.0`
-- Node: `v25.8.1`
+- Platform: `darwin 25.5.0`
+- Node: `v22.22.1`
 
 ## Executive Summary
 
@@ -25,18 +25,18 @@ Generated at 2026-07-06T01:47:05.638Z
 
 | Gate | Total | Pass | Fail | Partial | Unsupported | Flaky | Skipped |
 | --- | --- | --- | --- | --- | --- | --- | --- |
-| fail | 7 | 3 | 2 | 1 | 1 | 0 | 0 |
+| fail | 8 | 3 | 3 | 1 | 1 | 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: schema-quality: Found 1 quality finding(s) across 34 item(s): 1 warnings, 0 info.; security: Found 1 security finding(s): 1 high, 0 medium, 0 low.; security-lite: Found 1 security finding(s): 1 high, 0 medium, 0 low.
+- Top risks: schema-quality: Found 1 quality finding(s) across 34 item(s): 1 warnings, 0 info.; attack-sim: Safe attack simulation found 6 finding(s): 1 high, 5 medium, 0 low.; security: Found 1 security finding(s): 1 high, 0 medium, 0 low.
 - Regression/schema drift: Run `mcp-observatory diff <previous-run.json> <current-run.json>` to classify regressions and schema drift.
-- Failing checks: security-lite, security
+- Failing checks: security-lite, security, attack-sim
 - Partial or flaky checks: schema-quality
 - Skipped checks: none
 - Unsupported checks: prompts
-- Suggested next step: Start with the failing checks: security-lite, security.
+- 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>"`
 
 ## Regressions and Recoveries
@@ -47,12 +47,13 @@ _Use the `diff` command against another run artifact to classify regressions and
 
 | Focus | Check | Status | Duration (ms) | Message |
 | --- | --- | --- | --- | --- |
-| healthy | conformance | pass | 2.72 | All 7 conformance checks passed. |
-| healthy | resources | pass | 0.73 | Advertised capability responded with the minimal expected shape, but one optional resource endpoint appears unsupported. |
-| healthy | tools | pass | 1.47 | Advertised capability responded with the minimal expected shape (33 items). |
-| review | schema-quality | partial | 0.75 | Found 1 quality finding(s) across 34 item(s): 1 warnings, 0 info. |
+| healthy | conformance | pass | 2.29 | All 7 conformance checks passed. |
+| healthy | resources | pass | 0.61 | Advertised capability responded with the minimal expected shape, but one optional resource endpoint appears unsupported. |
+| healthy | tools | pass | 1.18 | Advertised capability responded with the minimal expected shape (33 items). |
+| review | schema-quality | partial | 0.62 | Found 1 quality finding(s) across 34 item(s): 1 warnings, 0 info. |
 | confirm intent | prompts | unsupported | 0.00 | Prompts are not advertised by the target. |
-| act now | security | fail | 0.42 | Found 1 security finding(s): 1 high, 0 medium, 0 low. |
+| act now | attack-sim | fail | 1.44 | Safe attack simulation found 6 finding(s): 1 high, 5 medium, 0 low. |
+| act now | security | fail | 0.29 | 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
@@ -124,6 +125,18 @@ Summary: Prompts are not advertised by the target.
   - Identifiers: none
   - Diagnostics: none
 
+### attack-sim — fail
+
+Summary: Safe attack simulation found 6 finding(s): 1 high, 5 medium, 0 low.
+
+- Endpoint: `attack-sim/safe`
+  - Advertised: `true`
+  - Responded: `true`
+  - Minimal shape present: `true`
+  - Item count: `6`
+  - Identifiers: playwright_upload_file, playwright_evaluate, playwright_post, playwright_put, playwright_patch (+1 more)
+  - Diagnostics: [medium] Tool "playwright_upload_file" combines broad parameters (filePath) with destructive or non-read-only behavior., [high] Tool "playwright_evaluate" combines broad parameters (script) with destructive or non-read-only behavior., [medium] Tool "playwright_post" combines broad parameters (url, headers) with destructive or non-read-only behavior. (+3 more)
+
 ### security — fail
 
 Summary: Found 1 security finding(s): 1 high, 0 medium, 0 low.
@@ -159,5 +172,5 @@ npm run cli -- report --run <path-to-run-artifact.json> --format markdown
 
 - Artifact type: `run`
 - Schema version: `1.0.0`
-- Run ID: `run_2026-07-06T014705638Z_2fa3564a`
+- Run ID: `run_2026-07-06T194957955Z_4eaf8a90`
 - Gate: `fail`

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

@@ -2,9 +2,9 @@
   "artifactType": "run",
   "schemaVersion": "1.0.0",
   "gate": "pass",
-  "runId": "run_2026-07-06T014653596Z_2f383767",
-  "createdAt": "2026-07-06T01:46:53.596Z",
-  "toolVersion": "0.26.1",
+  "runId": "run_2026-07-06T194947442Z_4e90392b",
+  "createdAt": "2026-07-06T19:49:47.442Z",
+  "toolVersion": "0.28.0",
   "target": {
     "targetId": "filesystem-server",
     "adapter": "local-process",
@@ -26,14 +26,14 @@
     "serverVersion": "0.2.0"
   },
   "environment": {
-    "platform": "darwin 24.0.0",
-    "nodeVersion": "v25.8.1"
+    "platform": "darwin 25.5.0",
+    "nodeVersion": "v22.22.1"
   },
   "summary": {
-    "total": 7,
+    "total": 8,
     "pass": 2,
     "fail": 0,
-    "partial": 3,
+    "partial": 4,
     "unsupported": 2,
     "flaky": 0,
     "skipped": 0,
@@ -44,7 +44,7 @@
       "id": "tools",
       "capability": "tools",
       "status": "pass",
-      "durationMs": 6.062416000000212,
+      "durationMs": 5.032166999999845,
       "message": "Advertised capability responded with the minimal expected shape (14 items).",
       "evidence": [
         {
@@ -71,7 +71,9 @@
           ],
           "diagnostics": [
             "Secure MCP Filesystem Server running on stdio",
-            "Client does not support MCP Roots, using allowed directories set from server args: [ '/Users/sanghoon/mcp-observatory/examples/filesystem-fixture' ]"
+            "Client does not support MCP Roots, using allowed directories set from server args: [",
+            "'/Users/williamweishuhn/Documents/New project/mcp-observatory/examples/filesystem-fixture'",
+            "]"
           ],
           "schemas": {
             "read_file": {
@@ -325,7 +327,7 @@
       "id": "prompts",
       "capability": "prompts",
       "status": "unsupported",
-      "durationMs": 0.002250000000003638,
+      "durationMs": 0.0017920000000231084,
       "message": "Prompts are not advertised by the target.",
       "evidence": [
         {
@@ -341,7 +343,7 @@
       "id": "resources",
       "capability": "resources",
       "status": "unsupported",
-      "durationMs": 0.0014999999998508429,
+      "durationMs": 0.0014160000000629225,
       "message": "Resources are not advertised by the target.",
       "evidence": [
         {
@@ -357,7 +359,7 @@
       "id": "security-lite",
       "capability": "security-lite",
       "status": "partial",
-      "durationMs": 0.1989160000002812,
+      "durationMs": 0.13637500000004366,
       "message": "Found 3 security finding(s): 0 high, 3 medium, 0 low.",
       "evidence": [
         {
@@ -403,7 +405,7 @@
       "id": "conformance",
       "capability": "conformance",
       "status": "pass",
-      "durationMs": 6.366665999999896,
+      "durationMs": 5.456833000000188,
       "message": "All 7 conformance checks passed.",
       "evidence": [
         {
@@ -429,7 +431,7 @@
       "id": "schema-quality",
       "capability": "schema-quality",
       "status": "partial",
-      "durationMs": 2.5983750000000327,
+      "durationMs": 2.5004579999999805,
       "message": "Found 18 quality finding(s) across 14 item(s): 0 warnings, 18 info.",
       "evidence": [
         {
@@ -589,7 +591,7 @@
       "id": "security",
       "capability": "security",
       "status": "partial",
-      "durationMs": 2.7058750000001055,
+      "durationMs": 2.2048749999999018,
       "message": "Found 3 security finding(s): 0 high, 3 medium, 0 low.",
       "evidence": [
         {
@@ -630,6 +632,97 @@
           ]
         }
       ]
+    },
+    {
+      "id": "attack-sim",
+      "capability": "attack-sim",
+      "status": "partial",
+      "durationMs": 2.602374999999938,
+      "message": "Safe attack simulation found 3 finding(s): 0 high, 3 medium, 0 low.",
+      "evidence": [
+        {
+          "endpoint": "attack-sim/safe",
+          "advertised": true,
+          "responded": true,
+          "minimalShapePresent": true,
+          "itemCount": 3,
+          "identifiers": [
+            "write_file",
+            "edit_file",
+            "create_directory"
+          ],
+          "diagnostics": [
+            "[medium] Tool \"write_file\" combines broad parameters (path) with destructive or non-read-only behavior.",
+            "[medium] Tool \"edit_file\" combines broad parameters (path) with destructive or non-read-only behavior.",
+            "[medium] Tool \"create_directory\" combines broad parameters (path) with destructive or non-read-only behavior."
+          ],
+          "findings": [
+            {
+              "ruleId": "attack-sim/permission-boundary/broad-destructive-tool",
+              "attackClass": "permission-boundary",
+              "severity": "medium",
+              "itemType": "tool",
+              "itemName": "write_file",
+              "message": "Tool \"write_file\" combines broad parameters (path) with destructive or non-read-only behavior.",
+              "evidence": {
+                "broadParams": [
+                  "path"
+                ],
+                "annotations": {
+                  "readOnlyHint": false,
+                  "destructiveHint": true,
+                  "idempotentHint": true
+                },
+                "description": "Create a new file or completely overwrite an existing file with new content. Use with caution as it will overwrite existing files without warning. Handles text content with proper encoding. Only works within allowed directories."
+              },
+              "recommendation": "Constrain this tool with typed inputs, allowlists, explicit read-only/destructive annotations, and a harmless CI fixture.",
+              "recommendedAction": "gate"
+            },
+            {
+              "ruleId": "attack-sim/permission-boundary/broad-destructive-tool",
+              "attackClass": "permission-boundary",
+              "severity": "medium",
+              "itemType": "tool",
+              "itemName": "edit_file",
+              "message": "Tool \"edit_file\" combines broad parameters (path) with destructive or non-read-only behavior.",
+              "evidence": {
+                "broadParams": [
+                  "path"
+                ],
+                "annotations": {
+                  "readOnlyHint": false,
+                  "destructiveHint": true,
+                  "idempotentHint": false
+                },
+                "description": "Make line-based edits to a text file. Each edit replaces exact line sequences with new content. Returns a git-style diff showing the changes made. Only works within allowed directories."
+              },
+              "recommendation": "Constrain this tool with typed inputs, allowlists, explicit read-only/destructive annotations, and a harmless CI fixture.",
+              "recommendedAction": "gate"
+            },
+            {
+              "ruleId": "attack-sim/permission-boundary/broad-destructive-tool",
+              "attackClass": "permission-boundary",
+              "severity": "medium",
+              "itemType": "tool",
+              "itemName": "create_directory",
+              "message": "Tool \"create_directory\" combines broad parameters (path) with destructive or non-read-only behavior.",
+              "evidence": {
+                "broadParams": [
+                  "path"
+                ],
+                "annotations": {
+                  "readOnlyHint": false,
+                  "destructiveHint": false,
+                  "idempotentHint": true
+                },
+                "description": "Create a new directory or ensure a directory exists. Can create multiple nested directories in one operation. If the directory already exists, this operation will succeed silently. Perfect for setting up directory structures for projects or ensuring required paths exist. Only works within allowed directories."
+              },
+              "recommendation": "Constrain this tool with typed inputs, allowlists, explicit read-only/destructive annotations, and a harmless CI fixture.",
+              "recommendedAction": "gate"
+            }
+          ]
+        }
+      ]
     }
   ],
   "healthScore": {
@@ -658,7 +751,8 @@
         "score": 60,
         "details": [
           "security-lite: partial (60/100)",
-          "security: partial (60/100)"
+          "security: partial (60/100)",
+          "attack-sim: partial (60/100)"
         ]
       },
       {
@@ -676,16 +770,16 @@
         "weight": 0.1,
         "score": 100,
         "details": [
-          "Connect: 682ms",
-          "p95 latency: 6ms (3 operations)"
+          "Connect: 662ms",
+          "p95 latency: 5ms (3 operations)"
         ]
       }
     ]
   },
   "performanceMetrics": {
-    "connectMs": 681.851917,
-    "toolsListMs": 6.062416000000212,
-    "promptsListMs": 0.002250000000003638,
-    "resourcesListMs": 0.0014999999998508429
+    "connectMs": 661.862083,
+    "toolsListMs": 5.032166999999845,
+    "promptsListMs": 0.0017920000000231084,
+    "resourcesListMs": 0.0014160000000629225
   }
 }

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

@@ -1,6 +1,6 @@
 # MCP Observatory Run Report
 
-Generated at 2026-07-06T01:46:53.596Z
+Generated at 2026-07-06T19:49:47.442Z
 
 ## Target and Environment Metadata
 
@@ -8,8 +8,8 @@ Generated at 2026-07-06T01:46:53.596Z
 - Adapter: `local-process`
 - Command: `npx -y @modelcontextprotocol/server-filesystem examples/filesystem-fixture`
 - Server: `secure-filesystem-server 0.2.0`
-- Platform: `darwin 24.0.0`
-- Node: `v25.8.1`
+- Platform: `darwin 25.5.0`
+- Node: `v22.22.1`
 
 ## Executive Summary
 
@@ -25,18 +25,18 @@ Generated at 2026-07-06T01:46:53.596Z
 
 | Gate | Total | Pass | Fail | Partial | Unsupported | Flaky | Skipped |
 | --- | --- | --- | --- | --- | --- | --- | --- |
-| pass | 7 | 2 | 0 | 3 | 2 | 0 | 0 |
+| pass | 8 | 2 | 0 | 4 | 2 | 0 | 0 |
 
 ## At a Glance
 
 - Safety verdict: **Needs review** — The server is usable, but caveated checks should be reviewed before agents depend on it.
-- Top risks: schema-quality: Found 18 quality finding(s) across 14 item(s): 0 warnings, 18 info.; security: Found 3 security finding(s): 0 high, 3 medium, 0 low.; security-lite: Found 3 security finding(s): 0 high, 3 medium, 0 low.
+- Top risks: attack-sim: Safe attack simulation found 3 finding(s): 0 high, 3 medium, 0 low.; schema-quality: Found 18 quality finding(s) across 14 item(s): 0 warnings, 18 info.; security: Found 3 security finding(s): 0 high, 3 medium, 0 low.
 - 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: security-lite, schema-quality, security
+- Partial or flaky checks: security-lite, schema-quality, security, attack-sim
 - Skipped checks: none
 - Unsupported checks: prompts, resources
-- Suggested next step: Review the caveated checks next: security-lite, schema-quality, security.
+- Suggested next step: Review the caveated checks next: security-lite, schema-quality, security, attack-sim.
 - CI next step: `Add CI: npx @kryptosai/mcp-observatory setup-ci --all --command "npx -y <server-package>"`
 
 ## Regressions and Recoveries
@@ -47,11 +47,12 @@ _Use the `diff` command against another run artifact to classify regressions and
 
 | Focus | Check | Status | Duration (ms) | Message |
 | --- | --- | --- | --- | --- |
-| healthy | conformance | pass | 6.37 | All 7 conformance checks passed. |
-| healthy | tools | pass | 6.06 | Advertised capability responded with the minimal expected shape (14 items). |
-| review | schema-quality | partial | 2.60 | Found 18 quality finding(s) across 14 item(s): 0 warnings, 18 info. |
-| review | security | partial | 2.71 | Found 3 security finding(s): 0 high, 3 medium, 0 low. |
-| review | security-lite | partial | 0.20 | Found 3 security finding(s): 0 high, 3 medium, 0 low. |
+| healthy | conformance | pass | 5.46 | All 7 conformance checks passed. |
+| healthy | tools | pass | 5.03 | Advertised capability responded with the minimal expected shape (14 items). |
+| review | attack-sim | partial | 2.60 | Safe attack simulation found 3 finding(s): 0 high, 3 medium, 0 low. |
+| review | schema-quality | partial | 2.50 | Found 18 quality finding(s) across 14 item(s): 0 warnings, 18 info. |
+| review | security | partial | 2.20 | Found 3 security finding(s): 0 high, 3 medium, 0 low. |
+| review | security-lite | partial | 0.14 | Found 3 security finding(s): 0 high, 3 medium, 0 low. |
 | 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. |
 
@@ -79,7 +80,19 @@ Summary: Advertised capability responded with the minimal expected shape (14 ite
   - Minimal shape present: `true`
   - Item count: `14`
   - Identifiers: read_file, read_text_file, read_media_file, read_multiple_files, write_file (+9 more)
-  - Diagnostics: Secure MCP Filesystem Server running on stdio, Client does not support MCP Roots, using allowed directories set from server args: [ '/Users/sanghoon/mcp-observatory/examples/filesystem-fixture' ]
+  - Diagnostics: Secure MCP Filesystem Server running on stdio, Client does not support MCP Roots, using allowed directories set from server args: [, '/Users/williamweishuhn/Documents/New project/mcp-observatory/examples/filesystem-fixture' (+1 more)
+
+### attack-sim — partial
+
+Summary: Safe attack simulation found 3 finding(s): 0 high, 3 medium, 0 low.
+
+- Endpoint: `attack-sim/safe`
+  - Advertised: `true`
+  - Responded: `true`
+  - Minimal shape present: `true`
+  - Item count: `3`
+  - Identifiers: write_file, edit_file, create_directory
+  - Diagnostics: [medium] Tool "write_file" combines broad parameters (path) with destructive or non-read-only behavior., [medium] Tool "edit_file" combines broad parameters (path) with destructive or non-read-only behavior., [medium] Tool "create_directory" combines broad parameters (path) with destructive or non-read-only behavior.
 
 ### schema-quality — partial
 
@@ -152,5 +165,5 @@ npm run cli -- report --run <path-to-run-artifact.json> --format markdown
 
 - Artifact type: `run`
 - Schema version: `1.0.0`
-- Run ID: `run_2026-07-06T014653596Z_2f383767`
+- Run ID: `run_2026-07-06T194947442Z_4e90392b`
 - Gate: `pass`