Trustbench

What is Trustbench?

TrustBench is the public registry, routing layer, and signed-receipt audit trail for x402 agent payments. It provides three read-only MCP tools—get_rankings, get_receipt, and verify_receipt—to query provider rankings, fetch routing receipts, and verify Ed25519 signatures. It is designed for developers building agent-to-agent payment workflows.

How to use Trustbench?

Install via npx -y @trustbench/mcp for stdio-based MCP hosts (Claude Desktop, Cursor, Cherry Studio, Kimi) or use the hosted Streamable HTTP endpoint at https://trustbench.io/mcp for browser-based MCP clients. No API key is required for any of the MCP tools.

Key features of Trustbench

• Non-custodial — TrustBench never holds agent funds.
• Three read-only tools: rankings, receipts, verification.
• Ed25519 signature verification (lookup by ID or offline).
• No API key required for MCP tools.
• Supports both stdio and Streamable HTTP transports.

Use cases of Trustbench

• Query live x402 provider rankings by capability (search, inference, data, media, infra).
• Fetch a specific routing receipt by ID (rcpt_… or rrcpt_…).
• Verify an Ed25519 signature on a receipt JSON envelope received from a third-party agent.

FAQ from Trustbench

What are the runtime dependencies for Trustbench?

Trustbench requires Node.js (via npx) for stdio installations, or any HTTP client for the Streamable HTTP endpoint.

Does Trustbench require an API key?

No. All three MCP tools are available without any API key.

Where are TrustBench receipts and rankings stored?

Receipts and rankings are stored on the TrustBench public registry; the server queries this registry on behalf of the user.

What transports does the MCP server support?

It supports stdio (for desktop MCP hosts) and Streamable HTTP (for browser-based clients).

Does TrustBench handle agent funds?

No. It is non-custodial throughout and never holds agent funds.