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.
@lithvall
基本信息
x402 provider rankings + Ed25519-signed payment receipts + signature verification (3 tools).
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"trustbench": {
"command": "npx",
"args": [
"-y",
"@trustbench/mcp"
]
}
}
}Get TrustBench liveness rankings for x402 providers by capability. Returns a scored list of providers with latency and success-rate telemetry. Methodology note: scores are derived from HEAD-probe liveness checks (3 samples from one host), not a rigorous benchmark. See trustbench.io/methodology. Output: returns a JSON array. Each object has name (string, provider name), score (number 0-100, composite liveness score), latency_p50 (number, ms), success_rate (number 0.0-1.0, last 7 days), endpoint (string, URL), capabilities (array of strings).
Fetch a TrustBench routing receipt by ID. Receipts are immutable, Ed25519-signed records of a routing or payment event. Use to verify what was paid, to whom, for what capability, and what the on-chain settlement reference is. IDs start with rcpt_ (Phase 3) or rrcpt_ (Phase 4). Output: returns the signed receipt envelope as JSON. Phase 3 (rcpt_) returns a SignedReceipt with receipt (call metadata + settlement ref) and signature (Ed25519 over JCS-canonicalized receipt body). Phase 4 (rrcpt_) returns {receipt, signature} where receipt.paid contains routing details and signature covers the canonical envelope. To verify an envelope offline use the verify_receipt tool with the returned JSON, or @trustbench/verify-receipt npm.
Verify the Ed25519 signature on a TrustBench receipt. Two modes: (1) Lookup mode — pass receipt_id and the server fetches the receipt from trustbench.io and re-runs verification (handy when you only have an ID). (2) Offline mode — pass receipt_json (the full {receipt, signature} envelope an agent received from a third party) and the server verifies the Ed25519 signature against the published public key at trustbench.io/.well-known/trustbench-pubkey without trusting the database. Exactly one of receipt_id or receipt_json must be provided. Output: returns JSON with receipt_id, signature_valid (boolean), on_chain_verified (boolean, where present), signature_alg ("ed25519"), verify_url, pubkey_url. For non-server-mediated verification with no network round-trip, use the @trustbench/verify-receipt npm package.
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.
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.
rcpt_… or rrcpt_…).Trustbench requires Node.js (via npx) for stdio installations, or any HTTP client for the Streamable HTTP endpoint.
No. All three MCP tools are available without any API key.
Receipts and rankings are stored on the TrustBench public registry; the server queries this registry on behalf of the user.
It supports stdio (for desktop MCP hosts) and Streamable HTTP (for browser-based clients).
No. It is non-custodial throughout and never holds agent funds.
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
🚀 The fast, Pythonic way to build MCP servers and clients.

Model Context Protocol Servers
评论