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
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。