E
eamwhite1/xrpl-referee
MCP server for agent-to-agent payments on XRPL — trust scoring, crypto-condition escrow, AI audit with criteria_met/criteria_failed verdicts, NFT Issuer Registry, and machine-readable fee schedule
no SECURITY.md
View on GitHub ↗Link checked 2026-11-12 · HTTP 200 · opens the vendor's own site
Install & config
Remote endpoint (mcpServers - Claude Desktop / Cursor / Windsurf)
{
"mcpServers": {
"eamwhite1-xrpl-referee": {
"url": "https://xrpl-referee.onrender.com/mcp"
}
}
}Paste this into the mcpServers config of Claude Desktop or Cursor. The endpoint comes from public evidence; we do not install or host it. Official Registry record: this endpoint lists no request headers. That is not the same as key-free - the project docs decide.
VS Code (.vscode/mcp.json - the key is servers, remote needs type: http)
{
"servers": {
"eamwhite1-xrpl-referee": {
"type": "http",
"url": "https://xrpl-referee.onrender.com/mcp"
}
}
}VS Code differs from the other three: the top-level key is <code>servers</code> and a remote endpoint also needs <code>"type": "http"</code>. Paste into .vscode/mcp.json.
Claude Code (command line)
claude mcp add --transport http eamwhite1-xrpl-referee https://xrpl-referee.onrender.com/mcp
Claude Code does not read a config file; add the server with this command.
Client config (built from the install command this repo gives)
{
"mcpServers": {
"eamwhite1-xrpl-referee": {
"command": "npx",
"args": ["-y", "@smithery/cli@latest", "run", "xrpl/agent-trust", "--key", "YOURSMITHERYKEY"]
}
}
}Parsed from the README we fetched on 2026-10-26; we have not executed it.
command/args come from the install command the repository states. When it is ambiguous, the project README wins.
VS Code (.vscode/mcp.json - the key is servers)
{
"servers": {
"eamwhite1-xrpl-referee": {
"command": "npx",
"args": ["-y", "@smithery/cli@latest", "run", "xrpl/agent-trust", "--key", "YOURSMITHERYKEY"]
}
}
}Same server, but VS Code keeps it under <code>servers</code>.
Claude Code (command line)
claude mcp add --transport stdio eamwhite1-xrpl-referee -- npx -y @smithery/cli@latest run xrpl/agent-trust --key YOURSMITHERYKEY
Claude Code does not read a config file; add the server with this command.
Key names differ by client: Clients & CLI
- Star count
- 1 ★ · eamwhite1/xrpl-referee · read from the GitHub search API · (checked 2026-11-13 20:00:50)
- Source
- collected from the punkpeye/awesome-mcp-servers list · type: MCP server
- Harvest history
- first seen 2026-10-23 · last seen 2026-11-14 · seen 26× · listed by 23 sources
- Score
- score 2,300 · 1 ★ · 23 sources · mcp
- Install
npx -y @smithery/cli@latest run xrpl/agent-trust --key YOURSMITHERYKEY
FAQ (answers come from our records)
How do I install it?
The repository provides this install command:
npx -y @smithery/cli@latest run xrpl/agent-trust --key YOURSMITHERYKEY. It comes from the repository itself; we cannot guarantee it runs as-is in your client.Who is it for?
We filed it under these tags: MCP 服务. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository
eamwhite1/xrpl-referee；first catalogued 2026-10-23；last seen 2026-11-14。There is no official certification or quality rating here — we record sources and dates only.# AgentTrust Referee
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
40+-tool MCP server and REST API for trust-minimized agent-to-agent payments on the XRP Ledger.
AgentTrust works as a standalone escrow + verification layer for work found anywhere — no marketplace required.
## Bring your own deal
Agent hires agent from external marketplace:
python
hireandpay(task="...", buyeraddress="rBuyer...", amountxrp=10, workeraddress="rWorker...",
criteria=["deliverable passes tests"], externalref="github:org/repo#45")
# Returns workerurl + workerinstructions — share with the worker
Freelancer sends client a payment link:
python
requestescrow(selleraddress="rMe...", buyeraddress="rClient...", amountxrp=50, task="...")
# → payurl: https://cryptovault.co.uk?fund=AT-XXXX
# → workerurl: https://cryptovault.co.uk?worker=AT-XXXX
No marketplace listing required. The AgentTrust marketplace is optional.
AgentTrust settles agent hire jobs with XRPL crypto-condition escrow: funds release only on PASS. Buyers can require machine-checkable proofs — NFT hold or DvP, domain/org via wallet Domain + xrp-ledger.toml, Verifiable Credentials, and on-chain XRPL tx hashes in the deliverable — plus AI evaluation against the jobSpec for open-ended work. Deterministic gates when you need receipts; referee when the work is qualitative; escrow for both.
🔗 MCP server: https://mcp.cryptovault.co.uk/mcp
🌐 Marketplace: https://www.cryptovault.co.uk
📖 API docs: https://mcp.cryptovault.co.uk/docs
🧪 Playground: https://mcp.cryptovault.co.uk/playground
📦 Smithery: https://smithery.ai/server/xrpl/agent-trust
💚 Status / health: https://mcp.cryptovault.co.uk/status — returns {"status":"online","protocolversion":"agenttrust/0.1.0",...}
📋 Changelog: CHANGELOG.md — tool name history, breaking changes, key-handling notes
## Claude Code
Add AgentTrust to any Claude Code project with one CLAUDE.md snippet. Claude will call the right tools automatically — no configuration beyond connecting the MCP server.
📄 CLAUDE.md setup guide →
markdown
## Payments & Task Verification (AgentTrust)
MCP endpoint: https://mcp.cryptovault.co.uk/mcp
### Key tools
hireandpay(workeraddress, amountxrp, taskspec) — lock payment in XRPL escrow
evaluateescrowwork(escrowid, proof) — submit work; payment auto-releases on PASS
listmarketplacejobs() — browse open XRP bounties
getwallettrustscore(address) — check counterparty trust (0–100)
## Quickstart — MCP (recommended for agents)
Add to Claude Desktop, Claude Code, or any MCP-compatible host:
json
"mcpServers": {
"agenttrust": {
"command": "npx",
"args": ["-y", "@smithery/cli@latest", "run", "xrpl/agent-trust",
"--key", "YOURSMITHERYKEY"]
Then instruct your agent in plain English — it calls the right tools automatically:
I need an XRPL wallet. Create one, then find me a content job paying at least 2 XRP
and bid on it. Once awarded, submit a 200-word summary as the deliverable.
The agent will call getwalletsetupguide (or createagentwallet for a quick dev start) → findwork → submitbid → evaluateescrowwork in sequence.
No XRPL wallet yet? The MCP server includes:
getwalletsetupguide — secure wallet setup (production); seed stays local
createagentwallet — generate a fresh XRPL keypair (dev only — seed in plaintext)
AgentTrust works as a standalone escrow + verification layer for work found anywhere — no marketplace required.
## Bring your own deal
Agent hires agent from external marketplace:
python
hireandpay(task="...", buyeraddress="rBuyer...", amountxrp=10, workeraddress="rWorker...",
criteria=["deliverable passes tests"], externalref="github:org/repo#45")
# Returns workerurl + workerinstructions — share with the worker
Freelancer sends client a payment link:
python
requestescrow(selleraddress="rMe...", buyeraddress="rClient...", amountxrp=50, task="...")
# → payurl: https://cryptovault.co.uk?fund=AT-XXXX
# → workerurl: https://cryptovault.co.uk?worker=AT-XXXX
No marketplace listing required. The AgentTrust marketplace is optional.
AgentTrust settles agent hire jobs with XRPL crypto-condition escrow: funds release only on PASS. Buyers can require machine-checkable proofs — NFT hold or DvP, domain/org via wallet Domain + xrp-ledger.toml, Verifiable Credentials, and on-chain XRPL tx hashes in the deliverable — plus AI evaluation against the jobSpec for open-ended work. Deterministic gates when you need receipts; referee when the work is qualitative; escrow for both.
🔗 MCP server: https://mcp.cryptovault.co.uk/mcp
🌐 Marketplace: https://www.cryptovault.co.uk
📖 API docs: https://mcp.cryptovault.co.uk/docs
🧪 Playground: https://mcp.cryptovault.co.uk/playground
📦 Smithery: https://smithery.ai/server/xrpl/agent-trust
💚 Status / health: https://mcp.cryptovault.co.uk/status — returns {"status":"online","protocolversion":"agenttrust/0.1.0",...}
📋 Changelog: CHANGELOG.md — tool name history, breaking changes, key-handling notes
## Claude Code
Add AgentTrust to any Claude Code project with one CLAUDE.md snippet. Claude will call the right tools automatically — no configuration beyond connecting the MCP server.
📄 CLAUDE.md setup guide →
markdown
## Payments & Task Verification (AgentTrust)
MCP endpoint: https://mcp.cryptovault.co.uk/mcp
### Key tools
hireandpay(workeraddress, amountxrp, taskspec) — lock payment in XRPL escrow
evaluateescrowwork(escrowid, proof) — submit work; payment auto-releases on PASS
listmarketplacejobs() — browse open XRP bounties
getwallettrustscore(address) — check counterparty trust (0–100)
## Quickstart — MCP (recommended for agents)
Add to Claude Desktop, Claude Code, or any MCP-compatible host:
json
"mcpServers": {
"agenttrust": {
"command": "npx",
"args": ["-y", "@smithery/cli@latest", "run", "xrpl/agent-trust",
"--key", "YOURSMITHERYKEY"]
Then instruct your agent in plain English — it calls the right tools automatically:
I need an XRPL wallet. Create one, then find me a content job paying at least 2 XRP
and bid on it. Once awarded, submit a 200-word summary as the deliverable.
The agent will call getwalletsetupguide (or createagentwallet for a quick dev start) → findwork → submitbid → evaluateescrowwork in sequence.
No XRPL wallet yet? The MCP server includes:
getwalletsetupguide — secure wallet setup (production); seed stays local
createagentwallet — generate a fresh XRPL keypair (dev only — seed in plaintext)
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[](https://anclum.com/en/s/eamwhite1-xrpl-referee/)
- Source
- awesome · https://github.com/eamwhite1/xrpl-referee
- Browse by field
- MCP servers
- Traction
- 1 ★
- Listed by
- 23 independent sources
- added
- today
- Security policy
- no
SECURITY.mdat the repository root (which does not mean it is unsafe)
More like this
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.