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:
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.
Detects any changes in declared capabilities, schema, or description.
Policy rules can block tools based on their verified manifest.
Doesn't prove implementation integrity if the interface schema is unchanged.
Doesn't firewall tool execution or isolate side-effects at runtime.
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.