TrustBench
About
x402 provider rankings + Ed25519-signed payment receipts + signature verification (3 tools).
Details
- Transport
- SSE
Explore
- 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.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
TrustBenchCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
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.
get_rankings
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).
get_receipt
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_receipt
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.
- get_rankings: 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).
- get_receipt: 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_receipt: 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.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"trustbench": {
"server": {
"command": "npx",
"args": [
"-y",
"@trustbench/mcp"
]
}
}
}
}McpServers
{
"server": {
"command": "npx",
"args": [
"-y",
"@trustbench/mcp"
]
}
}Transport
"stdio"Package
"@trustbench/mcp"Registry
"npm"Native MCP server forTrustBench— a non-custodial routing and audit layer for x402 agent payments.
Adds three read-only tools to any MCP-capable host:
Works inClaude Desktop, Claude Cowork, Grok(xAI Connectors),Kimi Code CLI,Cherry Studio,Cursor, and any MCP-compatible host.
Add to your host's MCP config file (e.g.claude_desktop_config.jsonfor Claude Desktop,~/.kimi/mcp.jsonfor Kimi):
{ "mcpServers": { "trustbench": { "command": "npx", "args": ["-y", "@trustbench/mcp"] } } }
Restart the host app. The three tools above become available immediately — no API key, no account required.
get_rankings— JSON array of scored providers for the requested capability. Capabilities:search,inference,data,media,infra. Scores are derived from HEAD-probe liveness checks (3 samples from one host). Seetrustbench.io/methodologyfor the full scoring formula.
get_receipt— Full signed receipt envelope. Receipts are immutable after issuance. Phase 3 IDs start withrcpt_, Phase 4 routing receipts start withrrcpt_.
verify_receipt— Two modes (provide exactly one input):
- Lookup mode(receipt_id) — fetches the receipt fromtrustbench.ioand re-runs Ed25519 + on-chain verification. Useful when the agent only has an ID.
- Offline mode(receipt_json) — verifies a full{receipt, signature}envelope an agent received from a third party against the published public key, without trusting the database. The third-party-verifier path.
Both modes return a JSON summary withsignature_valid(boolean),on_chain_verified(boolean where applicable),signature_alg(ed25519), andpubkey_url. For zero-network verification with no round-trip to TrustBench, use the@trustbench/verify-receiptnpm package instead.
route_quoteandroute_settle(the paid routing flow) require atb_live_…API key and ship in the next release. Request access by DM'ing@TrustBench on X.
- Transport: stdio (JSON-RPC 2.0) — the MCP standard
- No external dependencies beyond Node.js built-ins
- Node ≥ 18 required (uses nativefetchandreadline)
- Source:github.com/lithvall/TrustBench
- @trustbench/verify-receipt— standalone offline Ed25519 receipt verifier
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
MCP tools for agent security audits and OG images, paid per call in USDC over x402 on Base
Proof-of-Work + Lightning Network authentication for AI agents. Wraps paid MCP tools with L402-signed receipts.
Trust intelligence platform for AI agents — identity certification, trust scoring, forensic audit trails, and x402 micropayments. 14 MCP tools.
Cryptographic identity for MCP clients — Ed25519 keypairs, DID-based verification, trust scoring, encrypted messaging, and artifact signing.
53 production-ready AI tools via MCP with x402 USDC payments on Base L2 — web scraping, crypto data, AI generation, OCR, and more.
MCP server providing x402 micropayment-powered developer tools including screenshot capture, AI analysis, PDF generation, code security scanning, and dependency auditing via USDC payments on Base.
The Behavioural Prediction MCP Server provides AI-powered tools to analyze wallet behaviour prediction,fraud detection and rug pull prediction.
AI inference via x402. Pay with Solana USDC. No registration. No API keys.
A server for cryptographic operations like encryption, decryption, and hashing.
An MCP server for accessing useful Bitcoin Lightning tools.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
