@kryptosai/mcp-observatory 0.27.0 → 0.28.0

package/docs/github-code-scanning-for-mcp.md

@@ -75,7 +75,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v6
-      - uses: KryptosAI/mcp-observatory/action@v0.26.1
+      - uses: KryptosAI/mcp-observatory/action@v0.27.0
         with:
           command: npx -y my-mcp-server
           deep: true

package/docs/launch.md

@@ -0,0 +1,64 @@
+# MCP Observatory Launch Page
+
+```
+  ███╗   ███╗ ██████╗██████╗
+  ████╗ ████║██╔════╝██╔══██╗
+  ██╔████╔██║██║     ██████╔╝
+  ██║╚██╔╝██║██║     ██╔═══╝
+  ██║ ╚═╝ ██║╚██████╗██║
+  ╚═╝     ╚═╝ ╚═════╝╚═╝
+     O B S E R V A T O R Y
+```
+
+MCP Observatory is the GitHub-native CI and security gate for MCP servers before agents depend on them.
+
+It turns a local MCP check into evidence maintainers already understand: GitHub Actions, SARIF, Code Scanning findings, score badges, reproducible run artifacts, and maintainer-ready PR copy.
+
+## The Fast Path
+
+1. Test one MCP server locally.
+
+```bash
+npx @kryptosai/mcp-observatory test npx -y my-mcp-server --campaign launch-proof
+```
+
+2. Convert the passing check into CI.
+
+```bash
+npx @kryptosai/mcp-observatory setup-ci --all --command "npx -y my-mcp-server" --sarif --campaign launch-proof
+```
+
+3. Verify the adoption kit.
+
+```bash
+npx @kryptosai/mcp-observatory setup-ci --doctor
+```
+
+## Why Maintainers Use It
+
+- Catch MCP startup, tool listing, prompt, resource, schema, and drift failures before agents rely on a server.
+- Convert a one-off local check into a repeatable GitHub Action without hand-writing workflow YAML.
+- Emit normalized SARIF so MCP findings can appear in GitHub Code Scanning.
+- Share reproducible JSON and Markdown evidence without exposing private telemetry.
+- Let coding agents run Observatory as an MCP server and inspect other MCP tools autonomously.
+
+## Public Proof
+
+- [GitHub Code Scanning for MCP servers](./github-code-scanning-for-mcp.md)
+- [Code Scanning demo](./code-scanning-demo.md)
+- [MCP Server Safety Index](./mcp-server-safety-index.md)
+- [Target gallery](./target-gallery.md)
+- [Public proof log](./proof.md)
+- [Agent task pack](./agent-tasks.md)
+
+## For Teams Running MCP In Production
+
+If MCP servers are becoming production dependencies, use the same evidence model privately:
+
+- CI rollout for selected MCP servers
+- SARIF and GitHub Code Scanning setup
+- private readiness review
+- prioritized fixes and owner-ready next steps
+- Safety Index-style report for internal agent dependencies
+
+See the [MCP Readiness Review](./paid-pilot-offer.md). The default package starts at `$2,500`.

package/docs/mcp-attack-simulator.md

@@ -0,0 +1,57 @@
+# MCP Attack Simulator
+
+MCP Attack Simulator runs safe, inert simulation checks over MCP server metadata, schemas, captured evidence, and optional baselines. It produces reproducible Safety Index evidence without executing destructive payloads.
+
+## Quick Start
+
+```bash
+npx @kryptosai/mcp-observatory attack-sim --target ./target.json --output attack-report.md --json attack-artifact.json
+```
+
+Or run directly against a server command:
+
+```bash
+npx @kryptosai/mcp-observatory attack-sim npx -y my-mcp-server
+```
+
+For GitHub Code Scanning:
+
+```bash
+npx @kryptosai/mcp-observatory attack-sim \
+  --target ./target.json \
+  --json attack-artifact.json \
+  --sarif attack-results.sarif \
+  --fail-on-high
+```
+
+## What It Tests
+
+- **Tool poisoning:** suspicious hidden or behavioral instructions in tool, prompt, resource, and schema metadata.
+- **Exfiltration canaries:** fake Observatory canaries and credential-like values in captured evidence.
+- **Permission boundaries:** broad path, command, network, or payload parameters combined with destructive or non-read-only behavior.
+- **Contract drift:** when `--baseline <run-artifact>` is supplied, new destructive tools, broadened schemas, and removed required fields.
+
+## Safe Simulation Only
+
+The simulator does not run exploit payloads, contact attacker infrastructure, write or delete files, or exfiltrate data. It uses metadata, schema, drift, and already-captured response evidence.
+
+If safe tool invocation is needed, run normal Observatory checks with existing deep invocation behavior and review the captured artifact. The simulator inspects captured evidence; it does not invent new dangerous calls.
+
+## Outputs
+
+- JSON: a normal MCP Observatory run artifact with an `attack-sim` check.
+- Markdown: an attack simulation report with verdict, findings, reproduction command, and maintainer fixes.
+- SARIF: Code Scanning findings for high and medium risk results.
+
+## Baseline Drift
+
+Use a prior run artifact as the baseline:
+
+```bash
+npx @kryptosai/mcp-observatory attack-sim \
+  --target ./target.json \
+  --baseline .mcp-observatory/runs/previous.json \
+  --output attack-report.md
+```
+
+This flags agent-contract changes that can turn a previously acceptable MCP dependency into a review item.

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

@@ -1,19 +1,21 @@
-# MCP Server Safety Index v1
+# MCP Server Safety Index
 
 The MCP Server Safety Index is an evidence standard for MCP readiness. It is not a leaderboard and does not rank maintainers.
 
-Each row links to a reproducible command, a JSON run artifact, and a Markdown report generated by MCP Observatory. The goal is to show which failure classes matter before teams let agents depend on MCP servers.
+Each row links to a reproducible command, a JSON run artifact, and a Markdown report generated by MCP Observatory. Entries can also include safe attack-simulation evidence as public artifacts are generated. The goal is to show which failure classes matter before teams let agents depend on MCP servers. In short: MCP servers need [tool-call receipts](./tool-call-receipts.md), not badges.
 
-For the rules behind this page, see the [Safety Methodology](./methodology.md).
+Future public grades can include [MCP Attack Simulator](./mcp-attack-simulator.md) evidence. Attack Simulator findings add safe, reproducible checks for tool poisoning, exfiltration canaries, permission-boundary risk, and contract drift without executing destructive payloads.
+
+For the rules behind this page, see the [Safety Methodology](./methodology.md). For a smaller server-to-evidence map, see the [MCP Receipt Graph](./receipt-graph.md).
 
 ## Snapshot
 
-- Evaluated servers: 13
+- Evaluated servers: 15
 - Ready for CI: 10
-- Needs review before production: 1
+- Needs review before production: 3
 - Unsafe default posture: 2
 - Not reproducible: 0
-- Latest run: 2026-06-24T02:07:44.894Z
+- Latest run: 2026-07-06T05:32:58.918Z
 
 ## Evaluations
 
@@ -26,12 +28,14 @@ For the rules behind this page, see the [Safety Methodology](./methodology.md).
 | 5 | [Context7](https://github.com/upstash/context7) | Documentation / Search | **Ready for CI** | Prompt-injection-sensitive retrieval | `npx -y @upstash/context7-mcp` | [JSON](./safety-index/artifacts/context7-server.json) / [report](./safety-index/artifacts/context7-server.md) | Zero-config public package. |
 | 6 | [Promptopia](https://www.npmjs.com/package/promptopia-mcp) | Prompts | **Ready for CI** | Prompt/resource contract | `npx -y promptopia-mcp` | [JSON](./safety-index/artifacts/promptopia-server.json) / [report](./safety-index/artifacts/promptopia-server.md) | Uses the checked-in prompt fixture through package defaults. |
 | 7 | [Ref tools](https://www.npmjs.com/package/ref-tools-mcp) | Developer Tools | **Ready for CI** | Prompt/tool inventory | `npx -y ref-tools-mcp` | [JSON](./safety-index/artifacts/ref-tools-server.json) / [report](./safety-index/artifacts/ref-tools-server.md) | Zero-config public package. |
-| 8 | [OpenTofu MCP server](https://github.com/opentofu/opentofu-mcp-server) | Infrastructure | **Ready for CI** | Infrastructure tool surface | `npx -y @opentofu/opentofu-mcp-server` | [JSON](./safety-index/artifacts/opentofu-server.json) / [report](./safety-index/artifacts/opentofu-server.md) | Zero-config public package. |
-| 9 | [Puppeteer MCP server](https://www.npmjs.com/package/puppeteer-mcp-server) | Browser Automation | **Ready for CI** | Browser/code execution boundary | `npx -y puppeteer-mcp-server` | [JSON](./safety-index/artifacts/puppeteer-server.json) / [report](./safety-index/artifacts/puppeteer-server.md) | Intentional browser evaluation is suppressed so remaining findings stay readable. |
-| 10 | [BrowserMCP](https://github.com/BrowserMCP/mcp) | Browser Automation | **Ready for CI** | Browser-control boundary | `npx -y @browsermcp/mcp` | [JSON](./safety-index/artifacts/browsermcp-server.json) / [report](./safety-index/artifacts/browsermcp-server.md) | Zero-config public package. [public proof](https://github.com/BrowserMCP/mcp/pull/189) |
-| 11 | [Microsoft Playwright MCP](https://github.com/microsoft/playwright-mcp) | Browser Automation | **Unsafe default posture** | Browser/code execution boundary | `npx -y @playwright/mcp` | [JSON](./safety-index/artifacts/playwright-mcp-server.json) / [report](./safety-index/artifacts/playwright-mcp-server.md) | Zero-config public package; security findings represent policy-review prompts, not a vulnerability claim. |
-| 12 | [AntV chart MCP server](https://github.com/antvis/mcp-server-chart) | Visualization | **Ready for CI** | Artifact-producing tools | `npx -y @antv/mcp-server-chart` | [JSON](./safety-index/artifacts/antv-chart-server.json) / [report](./safety-index/artifacts/antv-chart-server.md) | Zero-config public package. [public proof](https://github.com/antvis/mcp-server-chart/pull/312) |
-| 13 | [ExecuteAutomation Playwright MCP](https://github.com/executeautomation/mcp-playwright) | Browser Automation | **Unsafe default posture** | Startup/listing reproducibility | `npx -y @executeautomation/playwright-mcp-server` | [JSON](./safety-index/artifacts/executeautomation-playwright-server.json) / [report](./safety-index/artifacts/executeautomation-playwright-server.md) | Evaluated as a public package; current result should be treated as a maintainer conversation starter. [public proof](https://github.com/executeautomation/mcp-playwright/pull/225) |
+| 8 | [Git MCP Server](https://www.npmjs.com/package/@cyanheads/git-mcp-server) | Developer Tools | **Needs review before production** | Git tool boundary | `npx -y @cyanheads/git-mcp-server` | [JSON](./safety-index/artifacts/cyanheads-git-mcp-server.json) / [report](./safety-index/artifacts/cyanheads-git-mcp-server.md) | Zero-config public package. Keep tool invocation read-only unless a harmless fixture repository is added. |
+| 9 | [OpenTofu MCP server](https://github.com/opentofu/opentofu-mcp-server) | Infrastructure | **Ready for CI** | Infrastructure tool surface | `npx -y @opentofu/opentofu-mcp-server` | [JSON](./safety-index/artifacts/opentofu-server.json) / [report](./safety-index/artifacts/opentofu-server.md) | Zero-config public package. |
+| 10 | [Puppeteer MCP server](https://www.npmjs.com/package/puppeteer-mcp-server) | Browser Automation | **Ready for CI** | Browser/code execution boundary | `npx -y puppeteer-mcp-server` | [JSON](./safety-index/artifacts/puppeteer-server.json) / [report](./safety-index/artifacts/puppeteer-server.md) | Intentional browser evaluation is suppressed so remaining findings stay readable. |
+| 11 | [BrowserMCP](https://github.com/BrowserMCP/mcp) | Browser Automation | **Ready for CI** | Browser-control boundary | `npx -y @browsermcp/mcp` | [JSON](./safety-index/artifacts/browsermcp-server.json) / [report](./safety-index/artifacts/browsermcp-server.md) | Zero-config public package. [public proof](https://github.com/BrowserMCP/mcp/pull/189) |
+| 12 | [Microsoft Playwright MCP](https://github.com/microsoft/playwright-mcp) | Browser Automation | **Unsafe default posture** | Browser/code execution boundary | `npx -y @playwright/mcp` | [JSON](./safety-index/artifacts/playwright-mcp-server.json) / [report](./safety-index/artifacts/playwright-mcp-server.md) | Zero-config public package; security findings represent policy-review prompts, not a vulnerability claim. |
+| 13 | [AntV chart MCP server](https://github.com/antvis/mcp-server-chart) | Visualization | **Ready for CI** | Artifact-producing tools | `npx -y @antv/mcp-server-chart` | [JSON](./safety-index/artifacts/antv-chart-server.json) / [report](./safety-index/artifacts/antv-chart-server.md) | Zero-config public package. [public proof](https://github.com/antvis/mcp-server-chart/pull/312) |
+| 14 | [ExecuteAutomation Playwright MCP](https://github.com/executeautomation/mcp-playwright) | Browser Automation | **Unsafe default posture** | Startup/listing reproducibility | `npx -y @executeautomation/playwright-mcp-server` | [JSON](./safety-index/artifacts/executeautomation-playwright-server.json) / [report](./safety-index/artifacts/executeautomation-playwright-server.md) | Evaluated as a public package; current result should be treated as a maintainer conversation starter. [public proof](https://github.com/executeautomation/mcp-playwright/pull/225) |
+| 15 | [Flux159 Kubernetes MCP server](https://github.com/Flux159/mcp-server-kubernetes) | Infrastructure / Kubernetes | **Needs review before production** | Command and cluster mutation boundary | `npx -y mcp-server-kubernetes` | [JSON](./safety-index/artifacts/kubernetes-server.json) / [report](./safety-index/artifacts/kubernetes-server.md) / [attack-sim](./safety-index/artifacts/kubernetes-server.attack.md) / [SARIF](./safety-index/artifacts/kubernetes-server.attack.sarif) | Zero-config public package. Evaluated without cluster credentials; findings are metadata and schema boundary prompts, not exploit claims. |
 
 ## Patterns Observed
 
@@ -39,6 +43,8 @@ For the rules behind this page, see the [Safety Methodology](./methodology.md).
 - Artifact-producing tools: 1 server(s)
 - Broad protocol surface: 1 server(s)
 - Browser-control boundary: 1 server(s)
+- Command and cluster mutation boundary: 1 server(s)
+- Git tool boundary: 1 server(s)
 - Infrastructure tool surface: 1 server(s)
 - Persistent state tools: 1 server(s)
 - Prompt-injection-sensitive retrieval: 1 server(s)

package/docs/proof.md

@@ -5,8 +5,8 @@ MCP Observatory is early, but it is already a working MCP testing/security stack
 ## Current Public Surface
 
 - npm package: `@kryptosai/mcp-observatory`
-- GitHub Action: `KryptosAI/mcp-observatory/action@v0.26.1`
-- Latest release: `v0.26.1`
+- GitHub Action: `KryptosAI/mcp-observatory/action@v0.27.0`
+- Latest release: `v0.27.0`
 - CLI command count: scan, test, record, replay, verify, diff, watch, suggest, serve, lock, history, setup-ci, init-ci, ci-report, enterprise-report, score, badge, cloud
 - Test suite: 348 passing tests across 45 test files as of July 1, 2026
 - GitHub traffic snapshot: 745 clones and 232 unique cloners in the visible June 2026 traffic window
@@ -76,6 +76,9 @@ Open and accepted third-party integrations are tracked here:
 
 GitHub code search shows public references outside the main repo. These are discovery/listing signals, not customer claims:
 
+- PulseMCP has a maintainer-recognized `io.github.KryptosAI/mcp-observatory` listing with `server.json` visibility.
+- Smithery, Glama, LobeHub, Yarn/Vibehackers, and other MCP catalogs surface MCP Observatory install or scorecard pages.
+- MseeP has an unclaimed listing for MCP Observatory. Treat it as a directory opportunity until ownership, scan evidence, and badge wording are reviewed.
 - `punkpeye/awesome-mcp-devtools` lists MCP Observatory in an MCP developer-tools index.
 - `linny006/mcp-servers-live` mirrors a public MCP Observatory listing page.
 - `gabrielmoreira/awesome-ai-rabbit-holes` catalogs the GitHub project.

package/docs/receipt-graph.md

@@ -0,0 +1,54 @@
+# MCP Receipt Graph
+
+Agent trust should be a receipt graph, not a follower graph.
+
+A social graph says who is popular. A receipt graph says what was verified, what could not happen during the run, which artifact can be rerun, and what changed since the last trusted state.
+
+Use this page as the first public map from MCP servers to reproducible evidence. It is intentionally small: a receipt graph should start with high-quality, rerunnable receipts before it tries to become a giant directory.
+
+## Receipt Graph Fields
+
+| Field | Meaning |
+| --- | --- |
+| Server | Public MCP server, package, or repo. |
+| Receipt | JSON/Markdown evidence generated by MCP Observatory. |
+| Attack evidence | Safe `attack-sim` command, report, or SARIF. |
+| CI/SARIF path | Whether the next step is a maintainer CI gate, Code Scanning, or both. |
+| Capability envelope | What the run was allowed to access. |
+| Last verified | Timestamp of the latest public Safety Index refresh. |
+
+## Seed Graph
+
+| Server | Receipt | Attack evidence | CI/SARIF path | Capability envelope | Last verified |
+| --- | --- | --- | --- | --- | --- |
+| [Official everything server](https://github.com/modelcontextprotocol/servers) | [JSON](./safety-index/artifacts/everything-server.json) / [report](./safety-index/artifacts/everything-server.md) | `attack-sim npx -y @modelcontextprotocol/server-everything` | Public reference baseline; CI-ready. | Public package, no secrets, no production data. | 2026-07-06 |
+| [Official sequential thinking server](https://github.com/modelcontextprotocol/servers) | [JSON](./safety-index/artifacts/sequential-thinking-server.json) / [report](./safety-index/artifacts/sequential-thinking-server.md) | `attack-sim npx -y @modelcontextprotocol/server-sequential-thinking` | Public reference baseline; CI-ready. | Public package, no secrets, no production data. | 2026-07-06 |
+| [Official memory server](https://github.com/modelcontextprotocol/servers) | [JSON](./safety-index/artifacts/memory-server.json) / [report](./safety-index/artifacts/memory-server.md) | `attack-sim npx -y @modelcontextprotocol/server-memory` | Public reference baseline; CI-ready. | Public package, no secrets, no production data. | 2026-07-06 |
+| [Context7](https://github.com/upstash/context7) | [JSON](./safety-index/artifacts/context7-server.json) / [report](./safety-index/artifacts/context7-server.md) | `attack-sim npx -y @upstash/context7-mcp` | Maintainer CI conversation candidate. | Public package, no secrets, no production data. | 2026-07-06 |
+| [BrowserMCP](https://github.com/BrowserMCP/mcp) | [JSON](./safety-index/artifacts/browsermcp-server.json) / [report](./safety-index/artifacts/browsermcp-server.md) | `attack-sim npx -y @browsermcp/mcp` | Browser boundary candidate for CI/SARIF. | Public package, no secrets, no production credentials. | 2026-07-06 |
+| [Microsoft Playwright MCP](https://github.com/microsoft/playwright-mcp) | [JSON](./safety-index/artifacts/playwright-mcp-server.json) / [report](./safety-index/artifacts/playwright-mcp-server.md) | `attack-sim npx -y @playwright/mcp` | High-capability browser boundary; Code Scanning useful. | Public package, no secrets, no production credentials. | 2026-07-06 |
+| [Puppeteer MCP server](https://www.npmjs.com/package/puppeteer-mcp-server) | [JSON](./safety-index/artifacts/puppeteer-server.json) / [report](./safety-index/artifacts/puppeteer-server.md) | `attack-sim npx -y puppeteer-mcp-server` | Browser boundary candidate for review before production. | Public package, no secrets, no production credentials. | 2026-07-06 |
+| [OpenTofu MCP server](https://github.com/opentofu/opentofu-mcp-server) | [JSON](./safety-index/artifacts/opentofu-server.json) / [report](./safety-index/artifacts/opentofu-server.md) | `attack-sim npx -y @opentofu/opentofu-mcp-server` | Infrastructure tool surface; CI/SARIF recommended. | Public package, no secrets, no production infrastructure. | 2026-07-06 |
+| [Flux159 Kubernetes MCP server](https://github.com/Flux159/mcp-server-kubernetes) | [JSON](./safety-index/artifacts/kubernetes-server.json) / [report](./safety-index/artifacts/kubernetes-server.md) | [attack-sim](./safety-index/artifacts/kubernetes-server.attack.md) / [SARIF](./safety-index/artifacts/kubernetes-server.attack.sarif) | Kubernetes command and cluster mutation boundary; CI/SARIF recommended before agent dependency. | Public package, no secrets, no kubeconfig, no cluster tool invocation. | 2026-07-06 |
+
+## How To Add A Node
+
+1. Open a [Drop an MCP server, get a receipt request](https://github.com/KryptosAI/mcp-observatory/issues/new?template=tool-call-receipt-request.yml).
+2. Provide a public MCP server and safe startup command.
+3. Run:
+
+```bash
+npx @kryptosai/mcp-observatory test <safe startup command> --json run-artifact.json --markdown run-report.md
+npx @kryptosai/mcp-observatory attack-sim <safe startup command> --json attack-artifact.json --output attack-report.md --sarif attack-results.sarif
+npx @kryptosai/mcp-observatory setup-ci --all --command "<safe startup command>" --sarif
+```
+
+4. Attach sanitized artifacts or open a focused PR.
+
+## Agent-Native Ask
+
+```text
+Name one MCP server your agent depends on. I will help turn it into a reproducible receipt: safe startup command, run artifact, attack-sim evidence, SARIF, and a CI gate maintainers can review.
+```
+
+For the public intake loop, see [Drop an MCP server, get a receipt](./drop-server-get-receipt.md) or comment on [the live GitHub thread](https://github.com/KryptosAI/mcp-observatory/issues/146).

package/docs/safety-index/artifacts/antv-chart-server.json

@@ -2,9 +2,9 @@
   "artifactType": "run",
   "schemaVersion": "1.0.0",
   "gate": "pass",
-  "runId": "run_2026-06-24T020741323Z_41a77db3",
-  "createdAt": "2026-06-24T02:07:41.323Z",
-  "toolVersion": "0.24.0",
+  "runId": "run_2026-07-06T014704792Z_4aa8d9c4",
+  "createdAt": "2026-07-06T01:47:04.792Z",
+  "toolVersion": "0.26.1",
   "target": {
     "targetId": "antv-chart-server",
     "adapter": "local-process",
@@ -25,8 +25,8 @@
     "serverVersion": "0.8.x"
   },
   "environment": {
-    "platform": "darwin 25.5.0",
-    "nodeVersion": "v22.22.1"
+    "platform": "darwin 24.0.0",
+    "nodeVersion": "v25.8.1"
   },
   "summary": {
     "total": 7,
@@ -43,7 +43,7 @@
       "id": "tools",
       "capability": "tools",
       "status": "pass",
-      "durationMs": 2.671415999997407,
+      "durationMs": 1.9061670000010054,
       "message": "Advertised capability responded with the minimal expected shape (27 items).",
       "evidence": [
         {
@@ -82,9 +82,9 @@
             "generate_spreadsheet"
           ],
           "diagnostics": [
-            "[MCP-Server-Chart] 2026-06-24T02:07:44.865Z ℹ️  setting up tool handlers...",
-            "[MCP-Server-Chart] 2026-06-24T02:07:44.867Z ℹ️  tool handlers set up",
-            "[MCP-Server-Chart] 2026-06-24T02:07:44.868Z ✅ Stdio MCP Server started"
+            "[MCP-Server-Chart] 2026-07-06T01:47:05.616Z ℹ️  setting up tool handlers...",
+            "[MCP-Server-Chart] 2026-07-06T01:47:05.617Z ℹ️  tool handlers set up",
+            "[MCP-Server-Chart] 2026-07-06T01:47:05.618Z ✅ Stdio MCP Server started"
           ],
           "schemas": {
             "generate_area_chart": {
@@ -2602,7 +2602,7 @@
       "id": "prompts",
       "capability": "prompts",
       "status": "unsupported",
-      "durationMs": 0.0014999999984866008,
+      "durationMs": 0.0009579999987181509,
       "message": "Prompts are not advertised by the target.",
       "evidence": [
         {
@@ -2618,7 +2618,7 @@
       "id": "resources",
       "capability": "resources",
       "status": "unsupported",
-      "durationMs": 0.002874999998311978,
+      "durationMs": 0.002207999999882304,
       "message": "Resources are not advertised by the target.",
       "evidence": [
         {
@@ -2634,7 +2634,7 @@
       "id": "security-lite",
       "capability": "security-lite",
       "status": "pass",
-      "durationMs": 0.12066699999923003,
+      "durationMs": 0.08966599999985192,
       "message": "No security issues detected (lightweight scan).",
       "evidence": [
         {
@@ -2650,7 +2650,7 @@
       "id": "conformance",
       "capability": "conformance",
       "status": "pass",
-      "durationMs": 2.8167500000017753,
+      "durationMs": 1.4091669999997976,
       "message": "All 7 conformance checks passed.",
       "evidence": [
         {
@@ -2676,7 +2676,7 @@
       "id": "schema-quality",
       "capability": "schema-quality",
       "status": "pass",
-      "durationMs": 1.4510000000009313,
+      "durationMs": 1.022541000000274,
       "message": "All 27 item(s) have good schema quality.",
       "evidence": [
         {
@@ -2693,7 +2693,7 @@
       "id": "security",
       "capability": "security",
       "status": "pass",
-      "durationMs": 1.5284999999967113,
+      "durationMs": 0.9119160000009288,
       "message": "No security issues detected.",
       "evidence": [
         {
@@ -2750,16 +2750,16 @@
         "weight": 0.1,
         "score": 100,
         "details": [
-          "Connect: 3548ms",
-          "p95 latency: 3ms (3 operations)"
+          "Connect: 830ms",
+          "p95 latency: 2ms (3 operations)"
         ]
       }
     ]
   },
   "performanceMetrics": {
-    "connectMs": 3548.425417000002,
-    "toolsListMs": 2.671415999997407,
-    "promptsListMs": 0.0014999999984866008,
-    "resourcesListMs": 0.002874999998311978
+    "connectMs": 830.341375,
+    "toolsListMs": 1.9061670000010054,
+    "promptsListMs": 0.0009579999987181509,
+    "resourcesListMs": 0.002207999999882304
   }
 }

package/docs/safety-index/artifacts/antv-chart-server.md

@@ -1,6 +1,6 @@
 # MCP Observatory Run Report
 
-Generated at 2026-06-24T02:07:41.323Z
+Generated at 2026-07-06T01:47:04.792Z
 
 ## Target and Environment Metadata
 
@@ -8,8 +8,8 @@ Generated at 2026-06-24T02:07:41.323Z
 - Adapter: `local-process`
 - Command: `npx -y @antv/mcp-server-chart`
 - Server: `mcp-server-chart 0.8.x`
-- Platform: `darwin 25.5.0`
-- Node: `v22.22.1`
+- Platform: `darwin 24.0.0`
+- Node: `v25.8.1`
 
 ## Executive Summary
 
@@ -47,11 +47,11 @@ _Use the `diff` command against another run artifact to classify regressions and
 
 | Focus | Check | Status | Duration (ms) | Message |
 | --- | --- | --- | --- | --- |
-| healthy | conformance | pass | 2.82 | All 7 conformance checks passed. |
-| healthy | schema-quality | pass | 1.45 | All 27 item(s) have good schema quality. |
-| healthy | security | pass | 1.53 | No security issues detected. |
-| healthy | security-lite | pass | 0.12 | No security issues detected (lightweight scan). |
-| healthy | tools | pass | 2.67 | Advertised capability responded with the minimal expected shape (27 items). |
+| healthy | conformance | pass | 1.41 | All 7 conformance checks passed. |
+| healthy | schema-quality | pass | 1.02 | All 27 item(s) have good schema quality. |
+| healthy | security | pass | 0.91 | No security issues detected. |
+| healthy | security-lite | pass | 0.09 | No security issues detected (lightweight scan). |
+| healthy | tools | pass | 1.91 | Advertised capability responded with the minimal expected shape (27 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. |
 
@@ -115,7 +115,7 @@ Summary: Advertised capability responded with the minimal expected shape (27 ite
   - Minimal shape present: `true`
   - Item count: `27`
   - Identifiers: generate_area_chart, generate_bar_chart, generate_boxplot_chart, generate_column_chart, generate_district_map (+22 more)
-  - Diagnostics: [MCP-Server-Chart] 2026-06-24T02:07:44.865Z ℹ️  setting up tool handlers..., [MCP-Server-Chart] 2026-06-24T02:07:44.867Z ℹ️  tool handlers set up, [MCP-Server-Chart] 2026-06-24T02:07:44.868Z ✅ Stdio MCP Server started
+  - Diagnostics: [MCP-Server-Chart] 2026-07-06T01:47:05.616Z ℹ️  setting up tool handlers..., [MCP-Server-Chart] 2026-07-06T01:47:05.617Z ℹ️  tool handlers set up, [MCP-Server-Chart] 2026-07-06T01:47:05.618Z ✅ Stdio MCP Server started
 
 ### prompts — unsupported
 
@@ -152,5 +152,5 @@ npm run cli -- report --run <path-to-run-artifact.json> --format markdown
 
 - Artifact type: `run`
 - Schema version: `1.0.0`
-- Run ID: `run_2026-06-24T020741323Z_41a77db3`
+- Run ID: `run_2026-07-06T014704792Z_4aa8d9c4`
 - Gate: `pass`

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

@@ -2,9 +2,9 @@
   "artifactType": "run",
   "schemaVersion": "1.0.0",
   "gate": "pass",
-  "runId": "run_2026-06-24T020731112Z_2e7853f8",
-  "createdAt": "2026-06-24T02:07:31.112Z",
-  "toolVersion": "0.24.0",
+  "runId": "run_2026-07-06T014702689Z_66630a02",
+  "createdAt": "2026-07-06T01:47:02.689Z",
+  "toolVersion": "0.26.1",
   "target": {
     "targetId": "browsermcp-server",
     "adapter": "local-process",
@@ -25,8 +25,8 @@
     "serverVersion": "0.1.3"
   },
   "environment": {
-    "platform": "darwin 25.5.0",
-    "nodeVersion": "v22.22.1"
+    "platform": "darwin 24.0.0",
+    "nodeVersion": "v25.8.1"
   },
   "summary": {
     "total": 7,
@@ -43,7 +43,7 @@
       "id": "tools",
       "capability": "tools",
       "status": "pass",
-      "durationMs": 1.2612079999998969,
+      "durationMs": 0.9707080000007409,
       "message": "Advertised capability responded with the minimal expected shape (12 items).",
       "evidence": [
         {
@@ -242,7 +242,7 @@
       "id": "prompts",
       "capability": "prompts",
       "status": "unsupported",
-      "durationMs": 0.0015829999993002275,
+      "durationMs": 0.0007919999989098869,
       "message": "Prompts are not advertised by the target.",
       "evidence": [
         {
@@ -258,7 +258,7 @@
       "id": "resources",
       "capability": "resources",
       "status": "pass",
-      "durationMs": 0.675042000000758,
+      "durationMs": 0.6247500000008586,
       "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": 0.03508300000066811,
+      "durationMs": 0.02770799999962037,
       "message": "No security issues detected (lightweight scan).",
       "evidence": [
         {
@@ -301,7 +301,7 @@
       "id": "conformance",
       "capability": "conformance",
       "status": "pass",
-      "durationMs": 2.116834000000381,
+      "durationMs": 1.5951249999998254,
       "message": "All 7 conformance checks passed.",
       "evidence": [
         {
@@ -327,7 +327,7 @@
       "id": "schema-quality",
       "capability": "schema-quality",
       "status": "pass",
-      "durationMs": 0.5424579999998969,
+      "durationMs": 0.48875000000043656,
       "message": "All 12 item(s) have good schema quality.",
       "evidence": [
         {
@@ -344,7 +344,7 @@
       "id": "security",
       "capability": "security",
       "status": "pass",
-      "durationMs": 0.24799999999959255,
+      "durationMs": 0.25716600000123435,
       "message": "No security issues detected.",
       "evidence": [
         {
@@ -401,16 +401,16 @@
         "weight": 0.1,
         "score": 100,
         "details": [
-          "Connect: 903ms",
+          "Connect: 705ms",
           "p95 latency: 1ms (3 operations)"
         ]
       }
     ]
   },
   "performanceMetrics": {
-    "connectMs": 902.8017089999994,
-    "toolsListMs": 1.2612079999998969,
-    "promptsListMs": 0.0015829999993002275,
-    "resourcesListMs": 0.675042000000758
+    "connectMs": 705.3232910000006,
+    "toolsListMs": 0.9707080000007409,
+    "promptsListMs": 0.0007919999989098869,
+    "resourcesListMs": 0.6247500000008586
   }
 }

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

@@ -1,6 +1,6 @@
 # MCP Observatory Run Report
 
-Generated at 2026-06-24T02:07:31.112Z
+Generated at 2026-07-06T01:47:02.689Z
 
 ## Target and Environment Metadata
 
@@ -8,8 +8,8 @@ Generated at 2026-06-24T02:07:31.112Z
 - Adapter: `local-process`
 - Command: `npx -y @browsermcp/mcp`
 - Server: `Browser MCP 0.1.3`
-- Platform: `darwin 25.5.0`
-- Node: `v22.22.1`
+- Platform: `darwin 24.0.0`
+- Node: `v25.8.1`
 
 ## Executive Summary
 
@@ -47,12 +47,12 @@ _Use the `diff` command against another run artifact to classify regressions and
 
 | Focus | Check | Status | Duration (ms) | Message |
 | --- | --- | --- | --- | --- |
-| healthy | conformance | pass | 2.12 | All 7 conformance checks passed. |
-| healthy | resources | pass | 0.68 | Advertised capability responded with the minimal expected shape, but one optional resource endpoint appears unsupported. |
-| healthy | schema-quality | pass | 0.54 | All 12 item(s) have good schema quality. |
-| healthy | security | pass | 0.25 | No security issues detected. |
-| healthy | security-lite | pass | 0.04 | No security issues detected (lightweight scan). |
-| healthy | tools | pass | 1.26 | Advertised capability responded with the minimal expected shape (12 items). |
+| healthy | conformance | pass | 1.60 | All 7 conformance checks passed. |
+| healthy | resources | pass | 0.62 | Advertised capability responded with the minimal expected shape, but one optional resource endpoint appears unsupported. |
+| healthy | schema-quality | pass | 0.49 | All 12 item(s) have good schema quality. |
+| healthy | security | pass | 0.26 | No security issues detected. |
+| healthy | security-lite | pass | 0.03 | No security issues detected (lightweight scan). |
+| healthy | tools | pass | 0.97 | Advertised capability responded with the minimal expected shape (12 items). |
 | confirm intent | prompts | unsupported | 0.00 | Prompts are not advertised by the target. |
 
 ## Evidence Snippets
@@ -159,5 +159,5 @@ npm run cli -- report --run <path-to-run-artifact.json> --format markdown
 
 - Artifact type: `run`
 - Schema version: `1.0.0`
-- Run ID: `run_2026-06-24T020731112Z_2e7853f8`
+- Run ID: `run_2026-07-06T014702689Z_66630a02`
 - Gate: `pass`