MCP Hangar
Policy enforcement plane for MCP: every tool call ends in a verdict. Self-hosted, MIT.
Using MCP Hangar in Claude, Cursor, Gemini CLI, Cline, or Zed?
MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).
Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less
uv tool install mcpindex-gate && mcpindex-config-wireVerdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.
Own this server? Screen its description →
That verdict was true at screening time (snapshot 2026-08-16).
Contracts can change after screening, with no version bump. The gate pins MCP Hangar’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.
See your first HOLD in 2 minutes →
Related: how to trust an MCP server · screen before install · silent contract drift
MCP_CONFIGPath to config.yaml declaring the upstream MCP servers and policy. Without it the gateway starts on a demo config that serves no real upstream.
Manage your ConnectMachine contacts, networks, events, and digital business cards.
Measured share of answer for 24 crypto and Web3 brands. An open dataset, not an audit of your site.
Trust scoring for MCP servers, AI skills & npm packages — 15 signals + safety scanning.