Skip to content

MCP Observatory

Independent safety audit of the MCP server ecosystem · by PulseFeed

Thousands of MCP servers ship with almost no vetting — and a bad one can run arbitrary code on your machine or exfiltrate data. Before you connect your AI agent to an MCP server, check it. We audit maintenance, install-script risk, provenance, abandonment and liveness.

6597servers audited
5802safe
301caution
489avoid

Verdicts

safe
5802
caution
301
avoid
489
unknown
5

npm servers get deep signals; remote servers get liveness + HTTPS only (can't fully verify a black-box remote).

Top safety flags

downloads_unknown
2752
no_repo
708
install_script
478
abandoned
195
unpopular
156
no_license
91
heavy_deps
43
unreachable
11

install_script = arbitrary code on npm i; abandoned = stale; unreachable = dead remote.

Top trusted MCP servers

ServerTypenpm dl/wkTrust
@modelcontextprotocol/sdknpm91,218,859100
ainpm47,150,887100
@ai-sdk/mcpnpm10,060,406100
@storybook/mcpnpm2,476,851100
@storybook/addon-mcpnpm3,623,998100
mcporternpm653,502100
@assistant-ui/reactnpm3,359,715100
mcp-handlernpm2,146,523100
@copilotkit/aimocknpm618,753100
fallownpm2,622,213100
mcp-remotenpm1,455,288100
@langchain/mcp-adaptersnpm466,494100
add-mcpnpm451,194100
evenpm2,272,263100
@modelcontextprotocol/servernpm31,960,333100
Check any MCP server: GET /mcp/verify?package=<npm-name> — free. Returns a safety verdict, score and flags (install scripts, abandonment, provenance, license, repo).
📊 Read the State of MCP Security report — how much of the ecosystem runs arbitrary code on install, updated daily. Building on MCP and want an API + CI check? Get early access →

Methodology: PulseFeed discovers servers from the official MCP registry, audits each via npm metadata (install scripts, provenance, license, downloads, freshness) and liveness for remotes. Same independent-audit approach as our x402 trust oracle. Machine-readable: /mcp.json. Updated daily.