How MCPTrust guarantees integrity and authenticity in the agent supply chain.
MCPTrust is designed to protect against specific supply-chain attacks targeting Model Context Protocol servers. We assume the following threats:
We don't just hope for security; we engineer it. Every commit runs through "The Gauntlet"—our internal suite of 17 adversarial test phases designed to break runtimes.
Beyond the core threat model, MCPTrust implements depth-in-defense features often missing from standard runtimes:
Understand exactly what MCPTrust provides—and what it doesn't.
Signed lockfile tamper detection ensures files haven't changed.
Cryptographic proof that the lockfile was approved (signed) by the holder of the signing key.
Server never sees host request IDs, preventing spoofing attacks.
Unknown/duplicate responses dropped. Deny on saturation.
Proxy blocks all unapproved tools and resource access.
17-phase stress test suite run on every commit.
Does not verify the internal correctness of the server code (unless pinned/verified).
Does not firewall tool execution side-effects (e.g., file deletion) if authorized.
Trust depends entirely on private key management practices.
Security relies entirely on the safety of your signing keys.
The verify command performs a purely cryptographic check of the lockfile against the signature. It does not talk to the live MCP server.
To check if the live server matches the lockfile, you must use the diff command.
If you find a security vulnerability in MCPTrust itself, please do not open a public issue. Email us at security@mcptrust.dev or use ourGitHub Security Advisory form.