MCP Observatory
███╗ ███╗ ██████╗██████╗
████╗ ████║██╔════╝██╔══██╗
██╔████╔██║██║ ██████╔╝
██║╚██╔╝██║██║ ██╔═══╝
██║ ╚═╝ ██║╚██████╗██║
╚═╝ ╚═╝ ╚═════╝╚═╝
O B S E R V A T O R Y
The CI and security gate for MCP servers before agents depend on them.
Agents should not depend on tools nobody tests. MCP Observatory gives MCP servers the production safety rails every dependency eventually needs: CI checks, security scans, schema drift detection, PR reports, score badges, and agent-accessible diagnostics.
Add MCP CI in one command:
npx @kryptosai/mcp-observatory init-ci --all --command "npx -y my-mcp-server"
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.
<p align="center"> <img src="./docs/demo.svg" alt="MCP Observatory scan output" width="820"> </p>
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
init-ci --all - GitHub PR comments for compatibility, drift, and security 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 pilot path for hosted history, private repo reporting, certification, support, and fleet visibility
See the MCP server security field guide, Safety Methodology, MCP Server Safety Index, reference evaluations, MCP lock files, public proof, the certification distribution loop, local metrics dashboard, and commercial pilots.
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, and a path toward certification or fleet visibility. Local OSS use stays free; production, private repo, and fleet usage can move through a paid pilot.
Production / Enterprise
Free for local OSS use. Paid pilots are available for hosted reporting, private repo CI, recurring security reports, certification, support, and MCP fleet visibility.
| Pilot | Starts At | Best Fit |
|---|---|---|
| Team Pilot | $299/month | Small teams adding MCP checks to CI |
| Business Pilot | $999/month | Private repos and recurring security reports |
| Enterprise Pilot | $3k/month | Private MCP readiness reports, support, and fleet visibility |
| Strategic Accounts | Custom, $250k+/year | Major companies running MCP in production |
Run npx @kryptosai/mcp-observatory cloud or contact william@banksey.com for production MCP usage. The primary paid pilot is a private MCP readiness review.
See commercial pilots, privacy and telemetry, and terms for production use. For a fuller narrative, see the project case study.
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 from config files and check them all (default) |
scan deep | Scan and also invoke safe tools to verify they execute |
test <cmd> / test --target <file> | Test a specific server by command or target config |
record <cmd> | Record a server session to a cassette file for offline replay |
replay <cassette> | Replay a cassette offline — no live server needed |
verify <cassette> <cmd> | Verify a live server still matches a recorded cassette |
diff <base> <head> | Compare two run artifacts for regressions and schema drift |
watch <config> | Watch a server for changes, alert on regressions |
suggest | Detect your stack and recommend MCP servers from the registry |
serve | Start as an MCP server for AI agents |
lock | Snapshot MCP server schemas into a lock file |
lock verify | Verify live servers match the lock file |
history | Show health score trends for your MCP servers |
init-ci | Create a GitHub Action and badge snippet for MCP compatibility/security checks |
ci-report | Generate CI report for GitHub issue creation |
enterprise-report | Generate a static production/security report from run artifacts |
score <cmd> | Score an MCP server's health (0-100) |
badge <cmd> | Generate an SVG health score badge for README |
cloud | Show hosted reporting, security review, and enterprise pilot options |
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.jsonand.mcp.json(current directory)
CI / GitHub Action
Add Observatory to your MCP server's CI pipeline:
npx @kryptosai/mcp-observatory init-ci --all --command "npx -y my-mcp-server"
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/action@v0.24.0
with:
command: npx -y my-mcp-server
deep: true
security: true
comment-on-pr: false
set-status: false
Action inputs:
| Input | Description | Default |
|---|---|---|
command | Server command to test | (required if no target) |
target | Path to target config JSON | |
targets | Path to MCP config file for multi-server matrix scan | |
deep | Also invoke safe tools | false |
security | Run security analysis | false |
fail-on-regression | Fail the action on issues | true |
fail-on-baseline-drift | Fail the action when baseline verification detects drift | true |
comment-on-pr | Post report as PR comment. Requires pull-requests: write. | true |
set-status | Set a commit status check (green/red) on the HEAD SHA. Requires statuses: write. | true |
github-token | Token for PR comments and commit statuses | ${{ github.token }} |
The action can comment on PRs and set commit statuses when the workflow grants write permissions. init-ci generates read-only third-party-friendly workflows by default and lets maintainers opt into comments/statuses later. 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 for pilot options.
Certified by MCP Observatory
MCP server maintainers can add a public compatibility/security signal to their README:
[](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=mcp-owner@your-company.com
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:
| Tool | When to use it |
|---|---|
scan | Check if all your configured MCP servers are healthy |
check_server | Test a specific server before installing or after updating |
score_server | Get a quick health score and grade for a server |
record | Capture a baseline of a working server for future comparison |
replay | Test against a recorded session — no live server needed |
verify | Confirm a server update didn't break anything |
watch | Check a server and see what changed since the last check |
diff_runs | Find regressions between two check results |
get_last_run | Retrieve previous check results for a server |
suggest_servers | Discover MCP servers that match your project stack |
An AI tool that checks other AI tools. It's a tool testing tools that serve tools.*
<sub>* I'm a dude playing a dude disguised as another dude.</sub>
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,bunare 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
| Feature | CLI | MCP Server | Why |
|---|---|---|---|
watch | Polling loop | Single check + diff | Request/response doesn't support long-polling |
| Interactive menu | Arrow-key navigation | Not available | MCP has no interactive UI |
| Color output | --no-color flag | Always plain text | MCP returns structured content |
report | Renders saved artifacts | Not available | Agents read artifacts directly |
serve | Starts MCP server | N/A | Is the MCP server |
run | Reads target config files | Inline params | MCP tools accept params directly |
get_last_run | Not available (use ls + diff) | Available | Convenience for agents |
Compatibility
Works with any MCP server that uses standard transports:
| Transport | Examples | Adapter |
|---|---|---|
| stdio (most servers) | filesystem, memory, context7, brave-search, sentry, notion, stripe | local-process |
| HTTP/SSE (remote) | Cloudflare, Exa, Tavily | http |
| Docker | All @modelcontextprotocol/server-* images | local-process via docker run -i |
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": "http://localhost:3000/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
| Feature | Observatory | mcp-recorder | MCPBench | mcp-jest |
|---|---|---|---|---|
| Auto-discover servers | ✅ | — | — | — |
| Check capabilities | ✅ | — | ✅ | ✅ |
| Invoke tools | ✅ | — | — | ✅ |
| Schema drift detection | ✅ | — | — | — |
| Record / replay | ✅ | ✅ | — | — |
| Verify against cassette | ✅ | — | — | — |
| Response snapshot diffs | ✅ | — | — | — |
| Benchmarking / latency | — | — | ✅ | — |
| Jest integration | — | — | — | ✅ |
| MCP proxy mode | — | ✅ | — | — |
| Works as MCP server | ✅ | — | — | — |
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
Contributing
See CONTRIBUTING.md for guidelines. The fastest way to contribute is to add a real passing target with a distinct capability shape, a clearer report surface, or a cleaner startup diagnosis.
If Observatory saved you a broken deploy, consider giving it a star. It helps others find the project.