Clawmon

# Trusted ClawMon

A read-only trust registry lookup for MCP skills, built on ERC-8004 and Monad.

## What it does

Trusted ClawMon is a trust score lookup service. It lets agents query reputation data for MCP skills before using them. All lookups are read-only HTTPS GET requests that return JSON — no signing, no wallet connection, no credentials required.

## Connection

| Setting | Value |
|---------|-------|
| **Base URL** | `https://trusted-clawmon-api.up.railway.app` |
| **Protocol** | HTTPS only (TLS required) |
| **WebSocket** | `wss://trusted-clawmon-api.up.railway.app/ws` (read-only event stream) |
| **Authentication** | None — all read endpoints are public |
| **Rate limit** | Standard HTTP rate limiting applies |

## Required environment variables

None. This skill performs read-only HTTPS lookups against the public ClawMon API. No API keys, private keys, wallet connections, RPC endpoints, or signing credentials are needed.

## What data is sent

Read-only lookups send only the skill ID in the URL path (e.g., `GET /api/agents/gmail-integration`). No user data, wallet addresses, input context, or usage telemetry is transmitted.

The optional feedback endpoint (`POST /api/feedback`) sends a skill ID, a pseudonymous reviewer address, and a numeric score. This is opt-in and never triggered automatically.

## Wallet address

The `wallet` field in the frontmatter (`0x3e4A...d7Ed`) is the **publisher's Monad testnet address** for receiving ClawMon protocol revenue. It is not used by the agent, not required for any lookup, and does not grant signing authority. Agents never need to interact with this address.

## When to use this skill

When a user asks you to evaluate whether an MCP skill is safe or trustworthy, query ClawMon for its trust score. Do not query ClawMon automatically before every skill call — only when the user requests a trust check or when invoking a skill you have not used before and want to verify.

## Read-only API (no credentials needed)

###...