openclaw-trust-scorer
Trust scoring for AI agents on the Solana agent registry. Send a wallet address or agent URL and get a trust profile based on on-chain transaction history, endpoint liveness, and hallucination detection. Built from 100+ experiments on agent-to-agent trust.
README
OpenClaw Trust Scorer — MCP Server
MCP server for Solana agent trust scoring.
Query any Solana wallet address to get a trust profile based on real on-chain data: transaction count, last activity, and SOL balance.
What it does
The get_trust_score tool queries the Solana mainnet-beta RPC and returns:
{
"wallet_address": "9WzDXwBbmkg8ZTbNMqUxvQRAyrZzDsGYdLVL9zYtAWWM",
"trust_score": 0.784,
"tier": "verified",
"signals": {
"transaction_count": 847,
"last_activity": "2026-04-11T14:22:31Z",
"balance_sol": 6.19,
"account_exists": true
},
"related_agents": [...]
}
Tiers: unknown → emerging → established → verified
Tools
| Tool | Description |
|---|---|
get_trust_score |
Trust score + signals for a Solana wallet address |
list_recent_queries |
Anonymized list of recently scored wallets |
Usage
With Claude Desktop (remote endpoint)
Add to claude_desktop_config.json:
{
"mcpServers": {
"openclaw-trust-scorer": {
"command": "npx",
"args": ["-y", "openclaw-trust-scorer"]
}
}
}
With Cursor / Zed / Continue
Add the remote MCP endpoint: http://178.104.131.84:8082/mcp
Direct HTTP (REST-compatible)
# Health check
curl http://178.104.131.84:8082/health
# MCP protocol (initialize)
curl -X POST http://178.104.131.84:8082/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'
# A2A agent card
curl http://178.104.131.84:8082/.well-known/agent.json
Local Development
npm install
node server.js --stdio # stdio mode (for Claude Desktop local)
node server.js --http # HTTP mode (default, port 3000)
Why trust scoring?
In the emerging agent economy, LLM-based buyers need to evaluate service providers before delegating tasks or making payments. On-chain activity is a verifiable, tamper-resistant signal of an agent's track record. This service makes that signal accessible via standard MCP protocol.
Data sources
- Solana mainnet-beta RPC: transaction history, account balance
- Scoring formula:
trust_score = 0.5 × activity + 0.35 × recency + 0.15 × balance - Privacy: no personal data, only public on-chain records
Related
- A2A endpoint:
http://178.104.131.84:8082/.well-known/agent.json(A2A protocol) - OpenClaw Research: Agent trust & verification experiments
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.