agent-trust
01MCP server Claude CodeCodexCursor +2
Tamper-evident action receipts, trust scoring & capability tokens for AI agents. 29 MCP tools. Runs locally from the @garl-protocol/mcp-server npm package. Needs 3 environment variables to run.
Cryptographic verification for AI agent actions — ECDSA-secp256k1 + RFC 6979 signed Action Receipts (v0.1), multi-dimensional Trust Vector, capability tokens (JWT-shaped + Biscuit-style attenuation), UETA §10(b) undo. 29 MCP tools. A2A v1.0 + ERC-8004 format compatible. Receipt-batch Merkle roots anchored on Base mainnet. Starting with code.
MCP server Claude CodeCodexCursor +2
Tamper-evident action receipts, trust scoring & capability tokens for AI agents. 29 MCP tools. Runs locally from the @garl-protocol/mcp-server npm package. Needs 3 environment variables to run.
MCP server Claude CodeCodexCursor +2
18 trust tools for AI agents — verify, score, route, compare, and delegate with confidence. Runs locally from the @garl-protocol/mcp-server npm package. Needs 2 environment variables to run.