@kryptosai/mcp-observatory 0.27.0 → 1.28.1

package/docs/safety-index/artifacts/ref-tools-server.md

@@ -1,6 +1,6 @@
 # MCP Observatory Run Report
 
-Generated at 2026-06-24T02:07:28.542Z
+Generated at 2026-07-06T19:49:51.606Z
 
 ## Target and Environment Metadata
 
@@ -25,7 +25,7 @@ Generated at 2026-06-24T02:07:28.542Z
 
 | Gate | Total | Pass | Fail | Partial | Unsupported | Flaky | Skipped |
 | --- | --- | --- | --- | --- | --- | --- | --- |
-| pass | 7 | 6 | 0 | 0 | 1 | 0 | 0 |
+| pass | 8 | 7 | 0 | 0 | 1 | 0 | 0 |
 
 ## At a Glance
 
@@ -47,16 +47,29 @@ _Use the `diff` command against another run artifact to classify regressions and
 
 | Focus | Check | Status | Duration (ms) | Message |
 | --- | --- | --- | --- | --- |
-| healthy | conformance | pass | 0.59 | All 7 conformance checks passed. |
-| healthy | prompts | pass | 0.22 | Advertised capability responded with the minimal expected shape (2 items). |
-| healthy | schema-quality | pass | 0.44 | All 4 item(s) have good schema quality. |
-| healthy | security | pass | 0.45 | No security issues detected. |
+| healthy | attack-sim | pass | 0.25 | Safe attack simulation found no high-risk MCP attack-readiness findings. |
+| healthy | conformance | pass | 0.51 | All 7 conformance checks passed. |
+| healthy | prompts | pass | 0.19 | Advertised capability responded with the minimal expected shape (2 items). |
+| healthy | schema-quality | pass | 0.50 | All 4 item(s) have good schema quality. |
+| healthy | security | pass | 0.19 | No security issues detected. |
 | healthy | security-lite | pass | 0.02 | No security issues detected (lightweight scan). |
-| healthy | tools | pass | 0.96 | Advertised capability responded with the minimal expected shape (2 items). |
+| healthy | tools | pass | 0.89 | Advertised capability responded with the minimal expected shape (2 items). |
 | confirm intent | resources | unsupported | 0.00 | Resources are not advertised by the target. |
 
 ## Evidence Snippets
 
+### attack-sim — pass
+
+Summary: Safe attack simulation found no high-risk MCP attack-readiness findings.
+
+- Endpoint: `attack-sim/safe`
+  - Advertised: `true`
+  - Responded: `true`
+  - Minimal shape present: `true`
+  - Item count: `0`
+  - Identifiers: none
+  - Diagnostics: none
+
 ### conformance — pass
 
 Summary: All 7 conformance checks passed.
@@ -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_2026-06-24T020728542Z_cc57c712`
+- Run ID: `run_2026-07-06T194951606Z_e657d5a4`
 - Gate: `pass`

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

@@ -2,9 +2,9 @@
   "artifactType": "run",
   "schemaVersion": "1.0.0",
   "gate": "pass",
-  "runId": "run_2026-06-24T020722515Z_10f2e6a0",
-  "createdAt": "2026-06-24T02:07:22.515Z",
-  "toolVersion": "0.24.0",
+  "runId": "run_2026-07-06T194946140Z_d608f553",
+  "createdAt": "2026-07-06T19:49:46.140Z",
+  "toolVersion": "0.28.0",
   "target": {
     "targetId": "sequential-thinking-server",
     "adapter": "local-process",
@@ -29,8 +29,8 @@
     "nodeVersion": "v22.22.1"
   },
   "summary": {
-    "total": 7,
-    "pass": 5,
+    "total": 8,
+    "pass": 6,
     "fail": 0,
     "partial": 0,
     "unsupported": 2,
@@ -43,7 +43,7 @@
       "id": "tools",
       "capability": "tools",
       "status": "pass",
-      "durationMs": 4.4761249999996835,
+      "durationMs": 3.737249999999676,
       "message": "Advertised capability responded with the minimal expected shape (1 item).",
       "evidence": [
         {
@@ -67,8 +67,8 @@
                   "description": "Your current thinking step"
                 },
                 "nextThoughtNeeded": {
-                  "type": "boolean",
-                  "description": "Whether another thought step is needed"
+                  "description": "Whether another thought step is needed",
+                  "type": "boolean"
                 },
                 "thoughtNumber": {
                   "type": "integer",
@@ -109,7 +109,6 @@
               },
               "required": [
                 "thought",
-                "nextThoughtNeeded",
                 "thoughtNumber",
                 "totalThoughts"
               ],
@@ -123,7 +122,7 @@
       "id": "prompts",
       "capability": "prompts",
       "status": "unsupported",
-      "durationMs": 0.005541999999877589,
+      "durationMs": 0.00408400000014808,
       "message": "Prompts are not advertised by the target.",
       "evidence": [
         {
@@ -139,7 +138,7 @@
       "id": "resources",
       "capability": "resources",
       "status": "unsupported",
-      "durationMs": 0.0015410000000883883,
+      "durationMs": 0.0015830000002097222,
       "message": "Resources are not advertised by the target.",
       "evidence": [
         {
@@ -155,7 +154,7 @@
       "id": "security-lite",
       "capability": "security-lite",
       "status": "pass",
-      "durationMs": 0.1121250000001055,
+      "durationMs": 0.0753340000001117,
       "message": "No security issues detected (lightweight scan).",
       "evidence": [
         {
@@ -171,7 +170,7 @@
       "id": "conformance",
       "capability": "conformance",
       "status": "pass",
-      "durationMs": 2.253124999999727,
+      "durationMs": 1.5115419999997357,
       "message": "All 7 conformance checks passed.",
       "evidence": [
         {
@@ -197,7 +196,7 @@
       "id": "schema-quality",
       "capability": "schema-quality",
       "status": "pass",
-      "durationMs": 0.8925840000001699,
+      "durationMs": 0.8508339999998498,
       "message": "All 1 item(s) have good schema quality.",
       "evidence": [
         {
@@ -214,7 +213,7 @@
       "id": "security",
       "capability": "security",
       "status": "pass",
-      "durationMs": 1.133458000000246,
+      "durationMs": 0.908542000000125,
       "message": "No security issues detected.",
       "evidence": [
         {
@@ -225,6 +224,23 @@
           "itemCount": 0
         }
       ]
+    },
+    {
+      "id": "attack-sim",
+      "capability": "attack-sim",
+      "status": "pass",
+      "durationMs": 0.819166000000223,
+      "message": "Safe attack simulation found no high-risk MCP attack-readiness findings.",
+      "evidence": [
+        {
+          "endpoint": "attack-sim/safe",
+          "advertised": true,
+          "responded": true,
+          "minimalShapePresent": true,
+          "itemCount": 0,
+          "identifiers": []
+        }
+      ]
     }
   ],
   "healthScore": {
@@ -253,7 +269,8 @@
         "score": 100,
         "details": [
           "security-lite: pass (100/100)",
-          "security: pass (100/100)"
+          "security: pass (100/100)",
+          "attack-sim: pass (100/100)"
         ]
       },
       {
@@ -271,16 +288,16 @@
         "weight": 0.1,
         "score": 100,
         "details": [
-          "Connect: 722ms",
+          "Connect: 614ms",
           "p95 latency: 4ms (3 operations)"
         ]
       }
     ]
   },
   "performanceMetrics": {
-    "connectMs": 722.4729170000003,
-    "toolsListMs": 4.4761249999996835,
-    "promptsListMs": 0.005541999999877589,
-    "resourcesListMs": 0.0015410000000883883
+    "connectMs": 614.4627080000002,
+    "toolsListMs": 3.737249999999676,
+    "promptsListMs": 0.00408400000014808,
+    "resourcesListMs": 0.0015830000002097222
   }
 }

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

@@ -1,6 +1,6 @@
 # MCP Observatory Run Report
 
-Generated at 2026-06-24T02:07:22.515Z
+Generated at 2026-07-06T19:49:46.140Z
 
 ## Target and Environment Metadata
 
@@ -25,7 +25,7 @@ Generated at 2026-06-24T02:07:22.515Z
 
 | Gate | Total | Pass | Fail | Partial | Unsupported | Flaky | Skipped |
 | --- | --- | --- | --- | --- | --- | --- | --- |
-| pass | 7 | 5 | 0 | 0 | 2 | 0 | 0 |
+| pass | 8 | 6 | 0 | 0 | 2 | 0 | 0 |
 
 ## At a Glance
 
@@ -47,16 +47,29 @@ _Use the `diff` command against another run artifact to classify regressions and
 
 | Focus | Check | Status | Duration (ms) | Message |
 | --- | --- | --- | --- | --- |
-| healthy | conformance | pass | 2.25 | All 7 conformance checks passed. |
-| healthy | schema-quality | pass | 0.89 | All 1 item(s) have good schema quality. |
-| healthy | security | pass | 1.13 | No security issues detected. |
-| healthy | security-lite | pass | 0.11 | No security issues detected (lightweight scan). |
-| healthy | tools | pass | 4.48 | Advertised capability responded with the minimal expected shape (1 item). |
-| confirm intent | prompts | unsupported | 0.01 | Prompts are not advertised by the target. |
+| 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). |
+| 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. |
 
 ## Evidence Snippets
 
+### attack-sim — pass
+
+Summary: Safe attack simulation found no high-risk MCP attack-readiness findings.
+
+- Endpoint: `attack-sim/safe`
+  - Advertised: `true`
+  - Responded: `true`
+  - Minimal shape present: `true`
+  - Item count: `0`
+  - Identifiers: none
+  - Diagnostics: none
+
 ### conformance — pass
 
 Summary: All 7 conformance checks passed.
@@ -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_2026-06-24T020722515Z_10f2e6a0`
+- Run ID: `run_2026-07-06T194946140Z_d608f553`
 - Gate: `pass`

package/docs/safety-index/targets.json

@@ -6,7 +6,10 @@
     "packageName": "@modelcontextprotocol/server-everything",
     "category": "Reference",
     "command": "npx",
-    "args": ["-y", "@modelcontextprotocol/server-everything"],
+    "args": [
+      "-y",
+      "@modelcontextprotocol/server-everything"
+    ],
     "timeoutMs": 60000,
     "riskClass": "Reference compatibility",
     "failureClass": "Broad protocol surface",
@@ -21,7 +24,10 @@
     "packageName": "@modelcontextprotocol/server-sequential-thinking",
     "category": "Reference",
     "command": "npx",
-    "args": ["-y", "@modelcontextprotocol/server-sequential-thinking"],
+    "args": [
+      "-y",
+      "@modelcontextprotocol/server-sequential-thinking"
+    ],
     "timeoutMs": 60000,
     "riskClass": "Reference compatibility",
     "failureClass": "Tool schema clarity",
@@ -35,7 +41,10 @@
     "packageName": "@modelcontextprotocol/server-memory",
     "category": "Reference / Memory",
     "command": "npx",
-    "args": ["-y", "@modelcontextprotocol/server-memory"],
+    "args": [
+      "-y",
+      "@modelcontextprotocol/server-memory"
+    ],
     "timeoutMs": 60000,
     "riskClass": "Agent memory mutation",
     "failureClass": "Persistent state tools",
@@ -49,7 +58,11 @@
     "packageName": "@modelcontextprotocol/server-filesystem",
     "category": "Filesystem",
     "command": "npx",
-    "args": ["-y", "@modelcontextprotocol/server-filesystem", "examples/filesystem-fixture"],
+    "args": [
+      "-y",
+      "@modelcontextprotocol/server-filesystem",
+      "examples/filesystem-fixture"
+    ],
     "timeoutMs": 30000,
     "riskClass": "Filesystem boundary",
     "failureClass": "Sandboxed filesystem access",
@@ -63,7 +76,10 @@
     "packageName": "@upstash/context7-mcp",
     "category": "Documentation / Search",
     "command": "npx",
-    "args": ["-y", "@upstash/context7-mcp"],
+    "args": [
+      "-y",
+      "@upstash/context7-mcp"
+    ],
     "timeoutMs": 60000,
     "riskClass": "Untrusted content retrieval",
     "failureClass": "Prompt-injection-sensitive retrieval",
@@ -77,7 +93,10 @@
     "packageName": "promptopia-mcp",
     "category": "Prompts",
     "command": "npx",
-    "args": ["-y", "promptopia-mcp"],
+    "args": [
+      "-y",
+      "promptopia-mcp"
+    ],
     "env": {
       "PROMPTS_DIR": "examples/promptopia-prompts"
     },
@@ -94,13 +113,33 @@
     "packageName": "ref-tools-mcp",
     "category": "Developer Tools",
     "command": "npx",
-    "args": ["-y", "ref-tools-mcp"],
+    "args": [
+      "-y",
+      "ref-tools-mcp"
+    ],
     "timeoutMs": 60000,
     "riskClass": "Developer reference tooling",
     "failureClass": "Prompt/tool inventory",
     "whyItMatters": "Developer tools become agent dependencies when wired into coding workflows.",
     "reproductionNotes": "Zero-config public package."
   },
+  {
+    "id": "cyanheads-git-mcp-server",
+    "name": "Git MCP Server",
+    "repo": "https://www.npmjs.com/package/@cyanheads/git-mcp-server",
+    "packageName": "@cyanheads/git-mcp-server",
+    "category": "Developer Tools",
+    "command": "npx",
+    "args": [
+      "-y",
+      "@cyanheads/git-mcp-server"
+    ],
+    "timeoutMs": 60000,
+    "riskClass": "Repository mutation",
+    "failureClass": "Git tool boundary",
+    "whyItMatters": "Coding agents often need Git context and can cause real repository changes if tool boundaries are unclear.",
+    "reproductionNotes": "Zero-config public package. Keep tool invocation read-only unless a harmless fixture repository is added."
+  },
   {
     "id": "opentofu-server",
     "name": "OpenTofu MCP server",
@@ -108,7 +147,10 @@
     "packageName": "@opentofu/opentofu-mcp-server",
     "category": "Infrastructure",
     "command": "npx",
-    "args": ["-y", "@opentofu/opentofu-mcp-server"],
+    "args": [
+      "-y",
+      "@opentofu/opentofu-mcp-server"
+    ],
     "timeoutMs": 60000,
     "riskClass": "Infrastructure-as-code",
     "failureClass": "Infrastructure tool surface",
@@ -122,9 +164,14 @@
     "packageName": "puppeteer-mcp-server",
     "category": "Browser Automation",
     "command": "npx",
-    "args": ["-y", "puppeteer-mcp-server"],
+    "args": [
+      "-y",
+      "puppeteer-mcp-server"
+    ],
     "timeoutMs": 60000,
-    "securitySuppressions": ["puppeteer_evaluate:shell-injection"],
+    "securitySuppressions": [
+      "puppeteer_evaluate:shell-injection"
+    ],
     "riskClass": "Browser control",
     "failureClass": "Browser/code execution boundary",
     "whyItMatters": "Browser automation gives agents navigation, page state, and sometimes code-evaluation powers.",
@@ -137,7 +184,10 @@
     "packageName": "@browsermcp/mcp",
     "category": "Browser Automation",
     "command": "npx",
-    "args": ["-y", "@browsermcp/mcp"],
+    "args": [
+      "-y",
+      "@browsermcp/mcp"
+    ],
     "timeoutMs": 60000,
     "riskClass": "Browser control",
     "failureClass": "Browser-control boundary",
@@ -152,7 +202,10 @@
     "packageName": "@playwright/mcp",
     "category": "Browser Automation",
     "command": "npx",
-    "args": ["-y", "@playwright/mcp"],
+    "args": [
+      "-y",
+      "@playwright/mcp"
+    ],
     "timeoutMs": 60000,
     "riskClass": "Browser control",
     "failureClass": "Browser/code execution boundary",
@@ -166,7 +219,10 @@
     "packageName": "@antv/mcp-server-chart",
     "category": "Visualization",
     "command": "npx",
-    "args": ["-y", "@antv/mcp-server-chart"],
+    "args": [
+      "-y",
+      "@antv/mcp-server-chart"
+    ],
     "timeoutMs": 60000,
     "riskClass": "Generated artifacts",
     "failureClass": "Artifact-producing tools",
@@ -181,12 +237,32 @@
     "packageName": "@executeautomation/playwright-mcp-server",
     "category": "Browser Automation",
     "command": "npx",
-    "args": ["-y", "@executeautomation/playwright-mcp-server"],
+    "args": [
+      "-y",
+      "@executeautomation/playwright-mcp-server"
+    ],
     "timeoutMs": 60000,
     "riskClass": "Browser control",
     "failureClass": "Startup/listing reproducibility",
     "whyItMatters": "A public browser automation package that fails basic listing checks shows why reproducible readiness evidence matters.",
     "reproductionNotes": "Evaluated as a public package; current result should be treated as a maintainer conversation starter.",
     "publicProof": "https://github.com/executeautomation/mcp-playwright/pull/225"
+  },
+  {
+    "id": "kubernetes-server",
+    "name": "Flux159 Kubernetes MCP server",
+    "repo": "https://github.com/Flux159/mcp-server-kubernetes",
+    "packageName": "mcp-server-kubernetes",
+    "category": "Infrastructure / Kubernetes",
+    "command": "npx",
+    "args": [
+      "-y",
+      "mcp-server-kubernetes"
+    ],
+    "timeoutMs": 60000,
+    "riskClass": "Kubernetes control plane",
+    "failureClass": "Command and cluster mutation boundary",
+    "whyItMatters": "Kubernetes MCP servers can expose cluster mutation, pod exec, manifest apply/delete, and broad kubectl command surfaces to agents.",
+    "reproductionNotes": "Zero-config public package. Evaluated without cluster credentials; findings are metadata and schema boundary prompts, not exploit claims."
   }
 ]

package/docs/security-due-diligence.md

@@ -0,0 +1,87 @@
+# Security Due Diligence Packet
+
+Use this page as the first-pass answer set for security, procurement, or pilot-review conversations.
+
+## Product Boundary
+
+MCP Observatory is a local-first CLI, GitHub Action workflow, and MCP server for testing MCP servers before agents depend on them.
+
+It does not claim to prove that an MCP server is safe for every mission. It produces repeatable evidence for startup behavior, tool surface, schema quality, known security footguns, attack-readiness simulations, SARIF, and trust status.
+
+## Data Handling
+
+Default local audit behavior:
+
+- no hosted service required
+- no network upload required
+- no secret value collection required
+- no file content collection required
+- no environment dump collection required
+- report artifacts can remain inside the customer repo or CI artifact store
+
+Secret-like values should be redacted. Findings should report names, patterns, rule IDs, and evidence excerpts only where needed for review.
+
+## Deployment Model
+
+Supported modes:
+
+- local CLI run by developer or reviewer
+- GitHub Actions workflow on pull requests and schedules
+- SARIF upload to GitHub Code Scanning
+- MCP server mode for agent-accessible diagnostics
+- optional hosted reporting or private pilot workflows
+
+## Controls Produced
+
+Artifacts produced by an audit:
+
+- Markdown report
+- JSON report
+- SARIF results
+- compact score JSON
+- check statuses
+- normalized findings with fingerprints and recommendations
+- profile control mappings
+
+## Failure Policy
+
+Audit does not fail by default. CI can opt into policy gates:
+
+```bash
+npx @kryptosai/mcp-observatory audit npx -y my-mcp-server --profile nsa-mcp --format markdown --output mcp-audit.md --fail-on-critical
+npx @kryptosai/mcp-observatory audit npx -y my-mcp-server --profile nsa-mcp --format markdown --output mcp-audit.md --fail-on-high
+```
+
+This lets teams onboard in observation mode, then tighten enforcement after review.
+
+## Supply Chain Posture
+
+Current project trust signals include:
+
+- GitHub Actions CI
+- CodeQL
+- OpenSSF Scorecard badge
+- Dependabot
+- npm package metadata
+- MIT license
+- documented security disclosure path
+- packed-install dry-run validation in release workflows
+
+## Review Questions
+
+| Question | Short answer |
+|---|---|
+| Does local audit require cloud upload? | No. |
+| Does the `nsa-mcp` profile imply NSA approval? | No. It is a public-guidance mapping only. |
+| Can findings appear in GitHub Code Scanning? | Yes, via SARIF. |
+| Can teams fail builds only on critical or high findings? | Yes, with explicit flags. |
+| Can reports stay private? | Yes. |
+| Can a reviewer reproduce results? | Yes, using the target command and profile in the report. |
+| Does it execute destructive attack payloads? | No. Attack simulation is safe-mode metadata/schema/canary evidence. |
+
+## Known Limitations
+
+- Passing checks do not prove semantic safety.
+- False positives require reviewer feedback and, where appropriate, documented suppressions.
+- Some MCP servers require credentials or fixtures to test meaningful behavior safely.
+- The first `nsa-mcp` profile is intentionally practical coverage, not a complete government control catalog.

package/docs/setup-ci-doctor.md

@@ -6,6 +6,8 @@
 npx @kryptosai/mcp-observatory setup-ci --doctor
 ```
 
+MCP server packages can also opt into install-time workflow creation by setting `mcpObservatory.autoSetupCi` in `package.json`. See [Automatic CI Integration](./automatic-ci-integration.md).
+
 It checks:
 
 - the GitHub Action workflow exists
@@ -18,10 +20,20 @@ It checks:
 Use it after generating a kit:
 
 ```bash
-npx @kryptosai/mcp-observatory setup-ci --all --command "npx -y <server-package>"
+npx @kryptosai/mcp-observatory setup-ci --all --command "npx -y <server-package>" --sarif --schedule weekly
 npx @kryptosai/mcp-observatory setup-ci --doctor
 ```
 
+When a passing `test`, `run`, or single-target `scan` offers CI conversion, the generated kit includes SARIF/Code Scanning upload and weekly scheduled checks by default. Use `--no-ci-sarif` on that source command if a repo wants the lowest-permission workflow first.
+
+Repair or upgrade an existing kit in one step:
+
+```bash
+npx @kryptosai/mcp-observatory setup-ci --doctor --fix
+```
+
+`--fix` preserves an existing target or command when it can infer one, then rewrites the adoption kit with deep checks, security checks, SARIF upload, maintainer copy, badge snippets, and weekly scheduled runs.
+
 Use it during maintainer PRs to make review easier:
 
 ```bash

package/docs/target-gallery.md

@@ -0,0 +1,49 @@
+# Target Gallery
+
+The Target Gallery turns the Safety Index into a maintainer-friendly map of the MCP ecosystem. It is not a leaderboard. It groups examples by the kind of agent dependency risk they represent.
+
+For reproducible evidence, see the [MCP Server Safety Index](./mcp-server-safety-index.md). For contributor credit attached to accepted targets, see [MCP Observatory Contributors](./contributor-recognition.md) and [Contributor Proof Cards](./contributor-proof-cards/).
+
+## Reference And Baseline Servers
+
+| Target | Why Agents Care | Next Step |
+| --- | --- | --- |
+| Official everything server | Broad MCP protocol surface across tools, prompts, and resources | Keep as a baseline compatibility target |
+| Official sequential thinking server | Small tool surface with readable schemas | Use as a simple CI starter target |
+| Official memory server | Agent-facing persistent state | Watch schema and write boundaries |
+
+## Filesystem, Browser, And Execution Boundaries
+
+| Target | Why Agents Care | Next Step |
+| --- | --- | --- |
+| Official filesystem server | File access boundaries need harmless test roots | Review path scope before production |
+| BrowserMCP | Browser-control tools can affect live sessions | Add read-only CI before agent rollout |
+| Microsoft Playwright MCP | Browser automation can cross into code execution policy | Treat findings as policy review prompts |
+| Puppeteer MCP server | Browser automation needs clear execution boundaries | Keep intentional browser checks explicit |
+| ExecuteAutomation Playwright MCP | Startup/listing reproducibility affects agent trust | Start with maintainer conversation |
+
+## Retrieval, Documentation, And Prompt Surfaces
+
+| Target | Why Agents Care | Next Step |
+| --- | --- | --- |
+| Context7 | Retrieval tools can move untrusted text into agent context | Add drift and schema checks |
+| Promptopia | Prompt/resource contracts shape agent behavior | Keep generated evidence current |
+| Ref tools | Developer-tool inventory should stay stable | Add CI and badge proof |
+
+## Infrastructure And Artifact-Producing Tools
+
+| Target | Why Agents Care | Next Step |
+| --- | --- | --- |
+| OpenTofu MCP server | Infrastructure tools can influence production changes | Run checks before unattended agents use it |
+| AntV chart MCP server | Artifact-producing tools need clear schemas and outputs | Keep CI evidence public |
+
+## Add A Target
+
+Use the [target contribution guide](./target-contribution-guide.md). The best target has a public package, no secrets, no paid dependency, and a harmless startup command.
+
+```bash
+npm run safety-index
+npm test -- tests/safety-index.test.ts
+```
+
+Accepted target PRs can receive a Target Scout or Target Verifier role, an All Contributors entry, and a proof card under `docs/contributor-proof-cards/` that links to the merged PR and generated public evidence.

package/docs/target-registry.md

@@ -23,6 +23,7 @@ Every accepted target creates several useful surfaces:
 - JSON and Markdown evidence artifacts
 - a maintainer conversation starter
 - a badge or CI adoption path
+- contributor recognition and a proof-card link
 - a small contribution that another agent can copy
 
 That means one tiny PR can produce docs, evidence, search surface, backlinks, and future issues.
@@ -89,10 +90,13 @@ Add one object to `docs/safety-index/targets.json`:
 3. Add one target entry.
 4. Run the Safety Index locally.
 5. Open a small PR with the target and generated evidence.
-6. Optionally ask the maintainer if they want an Observatory badge or CI check.
+6. Add or request a contributor proof card.
+7. Optionally ask the maintainer if they want an Observatory badge or CI check.
 
 Use the detailed walkthrough in [Target Contribution Guide](./target-contribution-guide.md).
 
+Accepted target contributions can receive a role on [MCP Observatory Contributors](./contributor-recognition.md), an All Contributors entry, and a Markdown proof card under [`docs/contributor-proof-cards/`](./contributor-proof-cards/).
+
 ## Contribution Queue
 
 Ready-made target tasks live under the [`target-registry` label](https://github.com/KryptosAI/mcp-observatory/issues?q=is%3Aissue%20is%3Aopen%20label%3Atarget-registry). Pick one issue, make one small PR, and include generated evidence.