TrustBench is an MCP server with 3 tools an agent can call, among them get_rankings, get_receipt, verify_receipt. It answers at https://trustbench.io/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 22 October 2026, succeeded.
x402 provider rankings + Ed25519-signed payment receipts + signature verification (3 tools).
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
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), n Inputs: capability |
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 Inputs: receipt_id |
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 rece Inputs: receipt_id, receipt_json |
Every block below points at https://trustbench.io/mcp. Pick your client and copy.
claude mcp add --transport http trustbench https://trustbench.io/mcp
{
"mcpServers": {
"trustbench": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://trustbench.io/mcp"]
}
}
}{
"mcpServers": {
"trustbench": {
"url": "https://trustbench.io/mcp"
}
}
}{
"servers": {
"trustbench": {
"type": "http",
"url": "https://trustbench.io/mcp"
}
}
}{
"context_servers": {
"trustbench": {
"url": "https://trustbench.io/mcp"
}
}
}{
"mcpServers": {
"trustbench": {
"serverUrl": "https://trustbench.io/mcp"
}
}
}{
"mcpServers": {
"trustbench": {
"url": "https://trustbench.io/mcp"
}
}
}name: TrustBench
version: 0.0.1
schema: v1
mcpServers:
- name: TrustBench
type: streamable-http
url: https://trustbench.io/mcp{
"mcpServers": {
"trustbench": {
"httpUrl": "https://trustbench.io/mcp"
}
}
}{
"mcpServers": {
"trustbench": {
"type": "http",
"url": "https://trustbench.io/mcp"
}
}
}{
"mcpServers": {
"trustbench": {
"url": "https://trustbench.io/mcp"
}
}
}goose://extension?url=https%3A%2F%2Ftrustbench.io%2Fmcp&type=streamable_http&id=trustbench&name=TrustBench
It answered our last check on 22 October 2026 in 299 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
3, as returned by the server's own tools/list on 15 September 2026: get_rankings, get_receipt, verify_receipt.
It answered our last check on 22 October 2026 in 299 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://trustbench.io/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.lithvall. Endpoint host: trustbench.io. ARD identifier: urn:air:io.github.lithvall:mcp:trustbench.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.