MCP Observatory

🇨🇳 中文文档: README.zh-CN.md | 欢迎中国开发者贡献!

Secure the MCP servers you're building. MCP Observatory is the CI-native security tool for teams shipping custom MCP servers. Test during development, catch schema drift, simulate attacks, and generate compliance evidence — before agents depend on your servers.

Runtime enforcement: Use mcp-seatbelt to block dangerous MCP tool calls at runtime based on observatory scan results.

Get Started

npx @kryptosai/mcp-observatory demo

Scans your configured MCP servers (or a built-in demo server if you have none) and shows your safety grade in seconds. No config, no arguments — instant value.

Have servers? Scan them all:

npx @kryptosai/mcp-observatory

Test a specific server:

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

Add CI + Code Scanning in one command:

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

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, GitHub Code Scanning for MCP servers, Code Scanning demo, target gallery, target registry, target contribution guide, MCP Observatory Contributors, Agent Task Pack, MCP Receipts, Tool-call receipts, MCP Risk Graph, setup-ci --doctor, MCP server security field guide, Safety Methodology, MCP Server Safety Index, June 2026 safety field report, reference evaluations, MCP lock files, public proof, campaign attribution, local metrics dashboard, open core boundary, MCP Attack Simulation Evidence Pack, Private MCP Fleet Risk Graph, and commercial support.

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.

Whether you're shipping one MCP server or running a fleet, MCP Observatory gives you CI-native security scoring, attack simulation, schema drift detection, SARIF/HTML/Markdown reports, and GitHub Code Scanning — from your first npx command to production deployment. Local development stays free; teams running private repos, fleets, or compliance pipelines can upgrade 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 and MCP Attack Simulation Evidence Pack 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.

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

How It Compares

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

Run with no arguments for an interactive menu:

What It Does

Check capabilities — connects to a server and verifies tools, prompts, and resources respond correctly.

Invoke tools — goes beyond listing. Actually calls safe tools (no required params / readOnlyHint) and reports which ones work and which ones crash.

npx @kryptosai/mcp-observatory scan deep

Detect schema drift — diffs two runs and surfaces added/removed fields, type changes, and breaking parameter changes.

npx @kryptosai/mcp-observatory diff run-a.json run-b.json

Recommend servers — scans your project for languages, frameworks, databases, and cloud providers, then cross-references the MCP registry to suggest servers you're missing.

npx @kryptosai/mcp-observatory suggest

Or ask your agent "what MCP servers should I add?" when running in MCP server mode.

Security scanning — analyzes tool schemas for dangerous patterns: shell injection surfaces, broad filesystem access, missing auth, and credential leakage in responses.

npx @kryptosai/mcp-observatory test --security npx -y my-mcp-server

Record / replay / verify — capture a live session, replay it offline in CI, and verify nothing changed. Like VCR for MCP.

# Record a session
npx @kryptosai/mcp-observatory record npx -y @modelcontextprotocol/server-everything

# Replay offline (no server needed)
npx @kryptosai/mcp-observatory replay .mcp-observatory/cassettes/latest.cassette.json

# Verify the live server still matches
npx @kryptosai/mcp-observatory verify cassette.json npx -y @modelcontextprotocol/server-everything

Watch for regressions — re-runs checks on an interval and alerts when something changes.

npx @kryptosai/mcp-observatory watch target.json

Scan locations

When you run scan, it looks for MCP configs in:

• ~/.claude.json (Claude Code)
• ~/Library/Application Support/Claude/claude_desktop_config.json (Claude Desktop, macOS)
• %APPDATA%/Claude/claude_desktop_config.json (Claude Desktop, Windows)
• .claude.json and .mcp.json (current directory)

Architecture

                    ┌─────────────────────────┐
                    │   MCP Observatory CLI    │
                    │  npx @kryptosai/mcp-     │
                    │     observatory scan     │
                    └───────────┬─────────────┘
                                │
                    ┌───────────▼─────────────┐
                    │   Config Discovery       │
                    │  (Claude, Cursor, etc.)  │
                    └───────────┬─────────────┘
                                │
              ┌─────────────────┼─────────────────┐
              ▼                 ▼                  ▼
    ┌─────────────────┐ ┌──────────────┐ ┌──────────────────┐
    │   Security Scan  │ │  Attack Sim  │ │  Schema Drift    │
    │  (shell, creds)  │ │ (tool poison)│ │  (version diff)  │
    └────────┬────────┘ └──────┬───────┘ └────────┬─────────┘
             │                 │                   │
             └─────────────────┼───────────────────┘
                               ▼
                    ┌─────────────────────┐
                    │   Health Score       │
                    │  (0-100 + verdict)   │
                    └──────────┬──────────┘
                               │
              ┌────────────────┼────────────────┐
              ▼                ▼                 ▼
    ┌──────────────┐  ┌──────────────┐  ┌──────────────┐
    │  SARIF       │  │  Markdown    │  │  CI Gateway  │
    │  (Code Scan) │  │  Report      │  │  (setup-ci)  │
    └──────────────┘  └──────────────┘  └──────────────┘

CI / GitHub Action

Add Observatory to your MCP server's CI pipeline:

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

Check the adoption kit:

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

Successful test, run, and single-target scan checks also offer to convert the passing result into a CI adoption kit. That automatic conversion enables SARIF/Code Scanning and weekly scheduled checks by default; pass --no-ci-sarif when you only want a conservative workflow without Code Scanning upload.

Or create the workflow manually:

# .github/workflows/observatory.yml
name: MCP Server Check
on: [pull_request]

permissions:
  contents: read

jobs:
  observatory:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: KryptosAI/mcp-observatory/[email protected]
        with:
          command: npx -y my-mcp-server
          deep: true
          security: true
          comment-on-pr: false
          set-status: false

Action inputs:

The action can comment on PRs and set commit statuses when the workflow grants write permissions. setup-ci generates read-only third-party-friendly workflows by default and lets maintainers opt into comments/statuses later. init-ci remains available as a backward-compatible alias. See action/README.md for all options.

Production teams can add hosted CI history, private-repo reporting, recurring security reports, certification review, support, and fleet visibility. Run npx @kryptosai/mcp-observatory cloud, see COMMERCIAL.md, or open a pilot request from the issue chooser.

Certified by MCP Observatory

MCP server maintainers can add a public compatibility/security signal to their README:

[![MCP Observatory](https://img.shields.io/badge/MCP%20Observatory-enabled-2563eb)](https://github.com/KryptosAI/mcp-observatory)

Or generate a score badge from a live check:

npx @kryptosai/mcp-observatory badge npx -y my-mcp-server --output docs/mcp-health.svg

See the certification distribution loop for the GitHub Action template, maintainer PR body, and badge rollout playbook.

Generate a pilot-ready production/security report from local run artifacts:

npx @kryptosai/mcp-observatory enterprise-report \
  --account "Your Company" \
  --format html \
  --output observatory-enterprise-report.html

For clearer internal account attribution in CI, set:

MCP_OBSERVATORY_ORG=your-company.com
MCP_OBSERVATORY_CONTACT=your-team-contact

Testing Feishu/Lark integrations? See the Feishu/Lark MCP guide.

Lock Files

$ npx @kryptosai/mcp-observatory lock              # Snapshot all server schemas
$ npx @kryptosai/mcp-observatory lock verify        # Verify no drift since last lock

Lock files are the package-lock for AI tools: commit the MCP contract, then make every tool, schema, prompt, or resource drift visible in CI. See MCP lock files.

Trend Tracking

$ npx @kryptosai/mcp-observatory history            # Show health trends over time

Nightly Scans

$ npx @kryptosai/mcp-observatory ci-report          # Generate regression report for CI

MCP Server Mode

No other testing tool is itself an MCP server. Add Observatory as a server and your AI agent can autonomously test, diagnose, and monitor your other MCP servers.

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

Your agent gets 10 tools:

An AI tool that checks other AI tools. It is a tool testing tools that serve tools.

Security

The MCP server runs inside AI hosts where an LLM chooses which tools to call. To prevent prompt-injection attacks:

• Command allowlist: Only npx, node, python, python3, uvx, docker, deno, bun are permitted as base executables. The CLI has no restrictions.
• Path validation: File-reading tools are constrained to the runs/cassettes directories.
• No arbitrary execution: Use the CLI for unrestricted commands.

CLI vs MCP: Intentional Differences

Compatibility

Works with any MCP server that uses standard transports:

Servers needing API keys work via env in the target config. Python servers work via uvx. See the full compatibility matrix for tested servers and known issues.

Target config files

For more control (env vars, metadata, custom timeout):

{
  "targetId": "filesystem-server",
  "adapter": "local-process",
  "command": "npx",
  "args": ["-y", "@modelcontextprotocol/server-filesystem", "."],
  "timeoutMs": 15000,
  "skipInvoke": false
}

npx @kryptosai/mcp-observatory run --target ./target.json

HTTP / SSE targets

{
  "targetId": "my-remote-server",
  "adapter": "http",
  "url": "https://mcp.example.com/mcp",
  "authToken": "${MCP_SERVER_TOKEN}",
  "headers": {
    "X-Api-Key": "$MCP_SERVER_API_KEY"
  },
  "timeoutMs": 15000
}

Target configs support ${VAR}, $VAR, and env:VAR references in authToken, headers, and local-process env values.

How It Compares

Each tool has strengths. Observatory focuses on regression detection and CI-friendly workflows. mcp-recorder is great as a transparent proxy. MCPBench is the go-to for performance benchmarking. mcp-jest is ideal if you're already in a Jest workflow.

Prior Art

The record/replay/verify pattern is inspired by:

• VCR (Ruby) — pioneered cassette-based HTTP record/replay
• Polly.js (Netflix) — HTTP interaction recording for JavaScript
• mcp-recorder — MCP-specific traffic recording proxy
• MCPBench — MCP server benchmarking
• mcp-jest — Jest-style testing for MCP servers

Limitations

• Servers requiring interactive OAuth (e.g., Google Drive) need pre-authentication before Observatory can connect
• Custom WebSocket transports (e.g., BrowserTools MCP) are not supported
• A few servers time out or close before init — see known issues and compatibility

Works with mcp-seatbelt

Scan before you trust. Enforce at runtime with mcp-seatbelt — an MCP proxy that consumes Observatory receipts and blocks out-of-contract tool calls in production. Observatory validates; seatbelt enforces.

Works with agent-obs

Secure your servers with Observatory. Trace your agents with agent-obs — an open-source agent execution tracer that records every tool call, computes A-F session grades, and shows you exactly where your agents spend time, burn tokens, and hit errors. Observatory tells you if a server is safe. agent-obs tells you what your agent did with it.

Contributors ✨

Thanks to these amazing people who have contributed:

• leemeo3 — 3 Safety Index targets (Git, Chrome DevTools, Filesystem MCP)
• albatrossflyon-coder — GitHub MCP Safety Index (#201)
• tanishxdev — Legacy CLI deprecation warnings (#187)
• sansynx — CLI format validation (#182)

See all contributors →

Contributing

We welcome contributors! This project follows a Contributor Covenant Code of Conduct. The fastest way to get involved:

git clone https://github.com/KryptosAI/mcp-observatory.git && cd mcp-observatory && npm install && npm test

The most common first contribution is adding an MCP server to the Safety Index (10-15 minutes). See CONTRIBUTING.md for full guidelines, code standards, and the contributor recognition ladder.

If Observatory saved you a broken deploy, consider giving it a star. It helps others find the project.