mcp-proxy

<div align="center">

[](LICENSE) [](https://go.dev/)

Audit, govern, and sign every AI agent action.

SDK &bull; Spec &bull; agentreceipts.ai

</div>

---

mcp-proxy sits between an MCP client (Claude, etc.) and an MCP server, transparently intercepting every tool call. For each call it:

1. Classifies the operation (read/write/delete/execute) and scores risk (0-100)
2. Evaluates policy rules (pass/flag/pause/block) with approval workflows
3. Groups related calls by temporal proximity (intent tracking)
4. Signs a cryptographic receipt (Ed25519, hash-chained, W3C Verifiable Credential)
5. Redacts sensitive data (JSON-aware + pattern-based) before storage
6. Stores everything in a local SQLite audit trail

Single binary. No external dependencies. Drop-in for any MCP server.

go install github.com/agent-receipts/mcp-proxy/cmd/mcp-proxy@latest

# Wrap any MCP server
mcp-proxy node /path/to/mcp-server.js

# With options
mcp-proxy \
  --name github \
  --key private.pem \
  --taxonomy taxonomy.json \
  --rules rules.yaml \
  --issuer did:agent:my-proxy \
  --principal did:user:alice \
  node /path/to/github-mcp-server.js

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "github-audited": {
      "command": "mcp-proxy",
      "args": [
        "--name", "github",
        "node", "/path/to/github-mcp-server.js"
      ]
    }
  }
}

mcp-proxy list                          # List receipts
mcp-proxy list --risk high              # Filter by risk
mcp-pro