mcp-observatory
About
CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.
Details
- Author
- kryptosai
- Categories
- Developer Tools
Jump to
Setup
Install mcp-observatory in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/kryptosai/mcp-observatory
Follow the installation instructions in the repository README, then restart your MCP client.
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:Usemcp-seatbeltto block dangerous MCP tool calls at runtime based on observatory scan results.
npx -y @kryptosai/mcp-observatory@latest
Grades your configured MCP servers, or a packaged demo if you have none.
npx -y @kryptosai/mcp-observatory@latest test npx -y @modelcontextprotocol/server-everything
- uses: KryptosAI/mcp-observatory/action@v1
If this repo is an MCP package, that testsnpx -y <package.json name>. Otherwise setcommand:.
Or generate a full workflow:npx -y @kryptosai/mcp-observatory@latest setup-ci --all --command "npx -y my-mcp-server" --sarif
Install:npx -y @kryptosai/mcp-observatory@latest·brew tap kryptosai/mcp-observatory https://github.com/KryptosAI/mcp-observatory && brew install mcp-observatory·docker pull ghcr.io/kryptosai/mcp-observatory:latest·curl -fsSL https://raw.githubusercontent.com/KryptosAI/mcp-observatory/main/scripts/install.sh | sh
docker run --rm ghcr.io/kryptosai/mcp-observatory:latest demo docker run --rm ghcr.io/kryptosai/mcp-observatory:latest test npx -y @modelcontextprotocol/server-everything
Scanning a server on the host needs network and, for local files, a volume mount (-v "$PWD:$PWD" -w "$PWD").
Agents:npx -y @kryptosai/mcp-observatory@latest serve
Default-deny connect:npx -y @kryptosai/mcp-observatory@latest protectrewrites every discovered client config (Cursor, Claude, VS Code,.mcp.json, …). Undo:protect --undo. HTTP/SSE servers are left alone.
Runtime deny-default:npx -y @kryptosai/mcp-observatory@latest enforce --start-proxywrites a Seatbelt policy from the scan and starts the proxy. Local scan stays free.
Proof:Safety Index. Hosted history:$29·$299.
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 setupwithsetup-ci --all
- Profile-mapped auditswithaudit --profile nsa-mcp
- MCP receiptsthat package target, evidence, verdict, action, and reproduction commands
- MCP risk graphsthat group servers by capability boundary, receipt state, CI posture, and recommended action
- Action receiptsthat sayallow,gate,rerun,quarantine, orescalate
- GitHub PR commentsfor compatibility, drift, and security findings
- GitHub Code Scanning SARIFfor normalized MCP findings
- Health score badgesfor public trust signals
- Record/replay/verifyworkflows for regression testing
- MCP server modeso agents can inspect other MCP servers directly
- Production support pathfor hosted history, private repo reporting, owner-ready remediation, support, and fleet visibility
SeeGitHub Code Scanning for MCP servers,MCP Receipts,Troubleshooting,Safety Methodology,MCP Server Safety Index,MCP Observatory Contributors,hosted client contract,repository boundary,open core boundary, andcommercial support.
We scan ourselves with mcp-observatory on every release.See results →
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 firstnpxcommand to production deployment. Local development stays free; teams with a near-term production approval decision can use the fixed-scopeMCP Release Gate Pilot.
Local OSS use stays free under MIT. Teams running MCP in production can use theMCP Release Gate Pilotfor safe-mode evidence, SARIF/Code Scanning setup, CI rollout, private reporting, and owner-ready remediation notes. The fixed public entry offer is$15,000for 1-3 critical MCP servers over ten business days; broader work is scoped after the release decision.
The open source repo is the portable evidence engine. Hosted authentication, retention, organization workflows, fleet coordination, and private intelligence stay outside the OSS package; see therepository boundary.
Runnpx @kryptosai/mcp-observatory cloud, open a pilot request from the issue chooser, or seeCOMMERCIAL.md. Also seeprivacy,campaign attribution, andterms for production use.
Run a first check. No arguments startsdemo(your servers, or the packaged local demo):
Go deeper — also invoke safe tools to verify they actually run:
npx @kryptosai/mcp-observatory scan deep
npx @kryptosai/mcp-observatory test npx -y @modelcontextprotocol/server-everything
claude mcp add mcp-observatory -- npx -y @kryptosai/mcp-observatory serve
{ "mcpServers": { "mcp-observatory": { "command": "npx", "args": ["-y", "@kryptosai/mcp-observatory", "serve"] } } }
Run with no arguments to startdemo. Use--menufor the interactive catalog.
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 registryto suggest servers you're missing.
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
…
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
