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.

1131servers audited
781safe
201caution
144avoid

Verdicts

safe
781
caution
201
avoid
144
unknown
5

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

Top safety flags

unpopular
916
install_script
136
no_repo
114
abandoned
43
no_license
22
unreachable
8
heavy_deps
7
no_target
5

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

Top trusted MCP servers

ServerTypenpm dl/wkTrust
@modelcontextprotocol/sdknpm45,520,029100
ainpm18,704,349100
@ai-sdk/mcpnpm1,935,494100
@storybook/mcpnpm1,975,587100
@storybook/addon-mcpnpm1,645,260100
@assistant-ui/reactnpm1,472,507100
@copilotkit/aimocknpm832,758100
fallownpm630,425100
add-mcpnpm225,622100
evenpm356,626100
@modelcontextprotocol/servernpm188,403100
figma-developer-mcpnpm82,379100
n8n-mcpnpm97,264100
@raishin/vanguard-frontier-agenticnpm210,710100
@sap-ux/fiori-docs-embeddingsnpm110,908100
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.