MCP Observatory MCP Server

1

Add it to Claude Code

Run this in a terminal.

Run in terminal
claude mcp add mcp-observatory -- npx -y @kryptosai/mcp-observatory serve
README.md

The first testing tool that is itself an MCP server.

MCP Observatory

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

The first testing tool that is itself an MCP server. Your AI agent can scan, test, record, replay, and verify other MCP servers autonomously — catching regressions, schema drift, and security issues without human intervention.

Use it as a CLI, a CI action, or give it to your agent as an MCP server and let it test your other servers for you.

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 a specific server by command
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

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 @

Configuration

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

Try it

Scan all my configured MCP servers for potential issues and schema drift.
Perform a deep scan of my MCP servers to verify that tools are actually executing correctly.
Check my project stack and suggest new MCP servers that I should add to my configuration.
Run a security scan on my local MCP server to check for shell injection or credential leakage risks.
Record a session with my current MCP server to create a cassette for offline regression testing.

Frequently Asked Questions

What are the key features of MCP Observatory?

Auto-discover and scan MCP servers from configuration files. Deep scan mode to invoke and verify tool execution. Detect schema drift and breaking parameter changes between runs. Security scanning for shell injection and credential leakage. Record and replay sessions for offline regression testing.

What can I use MCP Observatory for?

Automating regression testing for MCP server development in CI pipelines. Verifying that third-party MCP servers are functioning correctly before deployment. Detecting breaking changes in MCP server schemas during updates. Auditing MCP server configurations for security vulnerabilities. Generating recommendations for new MCP servers based on project dependencies.

How do I install MCP Observatory?

Install MCP Observatory by running: npx @kryptosai/mcp-observatory

What MCP clients work with MCP Observatory?

MCP Observatory works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep MCP Observatory docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.
Open Conare