Mcp Observatory

> 🇨🇳 中文文档: [README.zh-CN.md](README.zh-CN.md) | 欢迎中国开发者贡献!

MCP Observatory

  ███╗   ███╗ ██████╗██████╗
  ████╗ ████║██╔════╝██╔══██╗
  ██╔████╔██║██║     ██████╔╝
  ██║╚██╔╝██║██║     ██╔═══╝
  ██║ ╚═╝ ██║╚██████╗██║
  ╚═╝     ╚═╝ ╚═════╝╚═╝
     O B S E R V A T O R Y

[](https://github.com/KryptosAI/mcp-observatory/actions/workflows/ci.yml) [](https://github.com/KryptosAI/mcp-observatory/actions/workflows/codeql.yml) [](https://github.com/KryptosAI/mcp-observatory/actions/workflows/coverage.yml) [](https://www.npmjs.com/package/@kryptosai/mcp-observatory) [](https://github.com/KryptosAI/mcp-observatory/stargazers) [](./LICENSE)

More badges

[](https://securityscorecards.dev/viewer/?uri=github.com/KryptosAI/mcp-observatory) [](./.github/dependabot.yml) [](./.github/workflows/release.yml) [](https://www.npmjs.com/package/@kryptosai/mcp-observatory) [](./package.json) [](https://smithery.ai/server/@kryptosai/mcp-observatory) [](https://glama.ai/mcp/servers/KryptosAI/mcp-observatory) [](./CONTRIBUTORS.md) [](https://gitee.com/williamweishuhn/mcp-observatory) [](https://gitee.com/williamweishuhn/mcp-observatory) [](https://registry.modelcontextprotocol.io) [](https://mcpmarket.com) [](https://mcp-hub.cn) [](https://opentools.ai) [](https://gitee.com/williamweishuhn/mcp-observatory)

MCP Observatory maps the risk graph of agent toolchains before agents depend on them. It helps teams validate MCP servers before deployment into sensitive, regulated, or mission-critical agentic AI environments.

Agents should not depend on tools nobody tests. MCP Observatory turns a local MCP check into portable receipts, risk graphs, release-gate evidence, SARIF for GitHub Code Scanning, GitHub Actions gates, schema drift detection, trust status output, score badges, and agent-accessible diagnostics.

npx @kryptosai/mcp-observatory audit npx -y my-mcp-server --profile nsa-mcp --format markdown --output mcp-audit.md

Sample trust output:

{
  "target_id": "my-mcp-server",
  "profile": "nsa-mcp",
  "score": 87,
  "status": "needs_review",
  "finding_count": 2
}

The nsa-mcp profile is not an official certification. It maps MCP Observatory findings to practical control areas for sensitive environments: trust boundaries, tool permissions, tool description integrity, authentication, secrets exposure, schema validation, input validation, auditability, runtime safety, and supply chain.

Trust Signals

| Signal | What it means | |---|---| | CI + coverage | Typecheck, lint, tests, build, packed install, artifact validation, smoke test, and measured coverage run in GitHub Actions. | | CodeQL + OpenSSF Scorecard | Static analysis and supply-chain posture are visible in GitHub-native security surfaces. | | Dependabot | npm and GitHub Actions dependency updates are monitored weekly. | | npm provenance workflow | Release automation is prepared for npm provenance through GitHub OIDC. | | Security policy | Vulnerability reports go through private disclosure; see [SECURITY.md](./SECURITY.md). |

Try It

Run the public evidence loop: generate a receipt, map it into a risk graph, add CI/SARIF, then request a private fleet review when the server matters to production.

npx @kryptosai/mcp-observatory audit npx -y my-mcp-server --profile nsa-mcp --format markdown --output report.md
npx @kryptosai/mcp-observatory audit npx -y my-mcp-server --profile nsa-mcp --format sarif --output results.sarif
npx @kryptosai/mcp-observatory score npx -y my-mcp-server --profile nsa-mcp --format json

Or start with the homepage demo: safely simulate MCP attack-readiness for one server, emit an action receipt, and produce SARIF evidence that maintainers can inspect in GitHub Code Scanning.

npx @kryptosai/mcp-observatory attack-sim npx -y my-mcp-server --sarif attack-results.sarif

Emit the portable trust record:

npx @kryptosai/mcp-observatory audit npx -y my-mcp-server --profile nsa-mcp --format json --output report.json --receipt receipt.json
npx @kryptosai/mcp-observatory receipt npx -y my-mcp-server --profile nsa-mcp --format markdown --output receipt.md
npx @kryptosai/mcp-observatory risk-graph --input receipt.json --json mcp-risk-graph.json --output mcp-risk-graph.md --html mcp-risk-graph.html

Then make the evidence repeatable in CI:

npx @kryptosai/mcp-observatory setup-ci --all --command "npx -y my-mcp-server" --sarif

See the [government and enterprise pilot brief](./docs/government-enterprise-pilot.md), [public guidance crosswalk](./docs/public-guidance-crosswalk.md), [procurement one-pager](./docs/procurement-one-pager.md), [security due diligence packet](./docs/security-due-diligence.md), [NSA-MCP audit CI guide](./docs/nsa-mcp-audit-ci.md), [example NSA-MCP audit report](./docs/examples/nsa-mcp-audit-report.md), [MCP Receipts](./docs/mcp-receipts.md), [MCP Attack Simulator](./docs/mcp-attack-simulator.md), [Tool-call receipts](./docs/tool-call-receipts.md), [MCP Risk Graph](./docs/receipt-graph.md), [private fleet risk graph pilot](./docs/private-mcp-fleet-risk-graph.md), [launch page](./docs/launch.md), [GitHub Code Scanning demo](./docs/code-scanning-demo.md), [GitHub Code Scanning for MCP servers](./docs/github-code-scanning-for-mcp.md), [sample safety reports](./docs/mcp-server-safety-index.md), and [reference evaluations](./docs/reference-evaluations.md).

Want a receipt for a server your agent depends on? Comment on Drop an MCP server, get a receipt #146 or use the structured receipt request form. Public requests can become Safety Index entries, delta receipts, SARIF evidence, and maintainer CI conversations.

Evidence You Can Inspect

| Evidence | Where | |---|---| | Example GitHub Actions adoption | [setup-ci --all](./docs/setup-ci-doctor.md) and the generated workflow docs | | NSA-MCP audit example | [Markdown report](./docs/examples/nsa-mcp-audit-report.md), [SARIF](./docs/examples/nsa-mcp-results.sarif), and [score JSON](./docs/examples/nsa-mcp-score.json) | | Procurement and pilot packet | [Public guidance crosswalk](./docs/public-guidance-crosswalk.md), [procurement one-pager](./docs/procurement-one-pager.md), and [security due diligence](./docs/security-due-diligence.md) | | Attack simulation output | [MCP Attack Simulator](./docs/mcp-attack-simulator.md) | | MCP receipts | [Portable trust receipts](./docs/mcp-receipts.md) | | Tool-call receipts | [Receipt standard](./docs/tool-call-receipts.md) for reproducible MCP evidence | | Risk graph | [Server-to-evidence map](./docs/receipt-graph.md) for agent toolchain trust decisions | | SARIF / Code Scanning output | [GitHub Code Scanning demo](./docs/code-scanning-demo.md) | | Real MCP server evaluations | [MCP Server Safety Index](./docs/mcp-server-safety-index.md) | | Reference reports | [Reference evaluations](./docs/reference-evaluations.md) | | Maintainer and contributor proof | [MCP Observatory Contributors](./docs/contributor-recognition.md) | | Open core boundary | [What is open vs. commercial](./docs/commercial-boundary.md) | | Security disclosure path | [SECURITY.md](./SECURITY.md) |

Two more fast paths:

Cloned this repo? Start here: [CLONED_THIS.md](./CLONED_THIS.md). Want to contribute? Add one server to the [MCP Target Registry](./docs/target-registry.md), use the [Agent Task Pack](./docs/agent-tasks.md), and get public credit through [MCP Observatory Contributors](./docs/contributor-recognition.md).

AI coding agents, agentic workflows, and rough PRs are welcome. Use the [10x Agentic Growth Sprint](./docs/10x-agentic-growth-sprint.md), [Agentic Contributor Outreach](./docs/agentic-contributor-outreach.md), or open a Contributor quest, Agentic contribution idea, or [Drop an MCP server, get a receipt](./docs/drop-server-get-receipt.md) issue to suggest a target, prompt, docs fix, receipt, or setup-ci --sarif integration.

Add MCP CI and Code Scanning in one command:

npx @kryptosai/mcp-observatory setup-ci --all --command "npx -y my-mcp-server" --sarif --schedule weekly

Repair or upgrade an existing adoption kit:

npx @kryptosai/mcp-observatory setup-ci --doctor --fix

Installing MCP Observatory in an MCP server project also prints the exact CI setup command. Projects can opt into automatic workflow creation during install with [mcpObservatory.autoSetupCi](./docs/automatic-ci-integration.md).

Normal scan and test runs include safe attack-readiness simulation by default. Use --no-attack-sim only when you want the older compatibility-only path.

Upload normalized MCP findings to GitHub Code Scanning when you want a security-native release gate:

npx @kryptosai/mcp-observatory setup-ci --all --command "npx -y my-mcp-server" --sarif

Add Observatory as an agent-accessible MCP server:

claude mcp add mcp-observatory -- npx -y @kryptosai/mcp-observatory serve

Building an autonomous agent, OpenClaw-style productivity machine, MCP gateway, or bot runtime? Start with the [agent runtime quickstart](./docs/agent-runtime-quickstart.md), copy the [OpenClaw MCP reliability agent template](./docs/openclaw-agent-template/SOUL.md), or point your agent at [llms.txt](./llms.txt) and [AGENTS.md](./AGENTS.md).

Or test a server immediately:

npx @kryptosai/mcp-observatory test npx -y @modelcontextprotocol/server-everything

Use it as a CLI, a GitHub Action, or an MCP server that lets your AI agent scan, test, record, replay, and verify other MCP servers autonomously.

[](https://glama.ai/mcp/servers/KryptosAI/mcp-observatory)

The Glama card is an external MCP directory scorecard. Treat it as directory-level social proof; click through for the underlying category details before using it as a production approval signal.

Why MCP Observatory

MCP servers are becoming production dependencies. If agents rely on them, teams need a way to catch broken tools, unsafe schemas, schema drift, slow responses, and security footguns before those failures reach users.

Observatory gives maintainers and teams:

• One-command CI setup with setup-ci --all
• Profile-mapped audits with audit --profile nsa-mcp
• MCP receipts that package target, evidence, verdict, action, and reproduction commands
• MCP risk graphs that group servers by capability boundary, receipt state, CI posture, and recommended action
• Action receipts that say allow, gate, rerun, quarantine, or escalate
• GitHub PR comments for compatibility, drift, and security findings
• GitHub Code Scanning SARIF for normalized MCP findings
• Health score badges for public trust signals
• Record/replay/verify workflows for regression testing
• MCP server mode so agents can inspect other MCP servers directly
• Production support path for hosted history, private repo reporting, certification, support, and fleet visibility

See the [launch page](./docs/launch.md), [GitHub Code Scanning for MCP servers](./docs/github-code-scanning-for-mcp.md), [Code Scanning demo](./docs/code-scanning-demo.md), [target gallery](./docs/target-gallery.md), [target registry](./docs/target-registry.md), [target contribution guide](./docs/target-contribution-guide.md), [MCP Observatory Contributors](./docs/contributor-recognition.md), [Agent Task Pack](./docs/agent-tasks.md), [MCP Receipts](./docs/mcp-receipts.md), [Tool-call receipts](./docs/tool-call-receipts.md), [MCP Risk Graph](./docs/receipt-graph.md), [setup-ci --doctor](./docs/setup-ci-doctor.md), [MCP server security field guide](./docs/mcp-security-field-guide.md), [Safety Methodology](./docs/methodology.md), [MCP Server Safety Index](./docs/mcp-server-safety-index.md), [June 2026 safety field report](./docs/mcp-safety-field-report-2026-06.md), [reference evaluations](./docs/reference-evaluations.md), [MCP lock files](./docs/mcp-lock-files.md), [public proof](./docs/proof.md), [campaign attribution](./docs/campaign-attribution.md), [local metrics dashboard](./docs/metrics-dashboard.md), [open core boundary](./docs/commercial-boundary.md), [MCP Attack Simulation Evidence Pack](./docs/attack-simulation-pilot.md), [Private MCP Fleet Risk Graph](./docs/private-mcp-fleet-risk-graph.md), and [commercial support](./COMMERCIAL.md).

For Security And Platform Teams

MCP servers are becoming part of the AI software supply chain. Agents need reliable, testable, auditable tools before those tools become dependencies in mission-critical workflows.

MCP Observatory gives security and platform teams MCP server CI, schema drift detection, security findings, SARIF/HTML/Markdown reports, GitHub Code Scanning upload, and a path toward certification or fleet visibility. Local OSS use stays free; production, private repo, and fleet usage can move through a paid MCP Readiness Review.

Production Support

Local OSS use stays free under MIT. Teams running MCP in production can use the [Private MCP Fleet Risk Graph](./docs/private-mcp-fleet-risk-graph.md) and [MCP Attack Simulation Evidence Pack](./docs/attack-simulation-pilot.md) for safe-mode attack simulation, SARIF/Code Scanning setup, CI rollout, private evidence reporting, and owner-ready remediation notes. Private fleet risk graph pilots start at $50,000; attack simulation packages start at $15,000; narrow readiness reviews start at $2,500.

The open source repo is the public evidence engine. Private telemetry intelligence, company/account prioritization, commercial ranking weights, hosted fleet workflows, and buyer-specific evidence packs stay outside the OSS package; see the [open core boundary](./docs/commercial-boundary.md).

Run npx @kryptosai/mcp-observatory cloud, open a pilot request from the issue chooser, or see [COMMERCIAL.md](./COMMERCIAL.md). Also see [privacy and telemetry](./PRIVACY.md), [campaign attribution](./docs/campaign-attribution.md), and [terms for production use](./TERMS.md).

How It Compares

| Feature | mcp-observatory | Snyk agent-scan | Cisco mcp-scanner | agent-shield | |---|---|---|---|---| | MCP-native | ✓ | ✓ | ✓ | ✓ | | Attack simulation | ✓ | ✗ | ✗ | ✗ | | Schema drift detection | ✓ | ✗ | ✗ | ✗ | | Record/replay/verify | ✓ | ✗ | ✗ | ✗ | | Health scoring (0-100) | ✓ | ✗ | ✗ | ✗ | | SARIF output | ✓ | ✓ | ✓ | ✓ | | CI/CD native (setup-ci) | ✓ | ✓ | ✓ | ✓ | | Safety index (17+ servers) | ✓ | ✗ | ✗ | ✗ | | Runtime enforcement via mcp-seatbelt | ✓ | ✗ | ✗ | ✗ |

Quick Start

Scan every MCP server in your Claude config:

npx @kryptosai/mcp-observatory

Go deeper — also invoke safe tools to verify they actually run:

npx @kryptosai/mcp-observatory scan deep

Test a specific server:

npx @kryptosai/mcp-observatory test npx -y @modelcontextprotocol/server-everything

Add it to Claude Code as an MCP server:

claude mcp add mcp-observatory -- npx -y @kryptosai/mcp-observatory serve

Or add it manually to your config:

{
  "mcpServers": {
    "mcp-observatory": {
      "command": "npx",
      "args": ["-y", "@kryptosai/mcp-observatory", "serve"]
    }
  }
}

Commands

| Command | What it does | |---------|-------------| | scan | Auto-discover servers, check them, and run safe attack-readiness simulation by default | | scan deep | Scan, run safe attack simulation, and also invoke safe tools to verify they execute | | test / test --target | Test one server and emit an action receipt by command or target config | | record | Record a server session to a cassette file for offline replay | | replay | Replay a cassette offline — no live server needed | | verify | Verify a live server still matches a recorded cassette | | diff | Compare two run artifacts for regressions and schema drift | | watch | Watch a server for changes, alert on regressions | | `s

…

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: KryptosAI
• Source: KryptosAI/mcp-observatory
• License: MIT
• Homepage: https://github.com/KryptosAI/mcp-observatory#readme

Install and usage instructions live in the source repository linked above.