TrustMesh MCP Server
TrustMesh MCP 服务器
通过模型上下文协议 (Model Context Protocol) 为 AI 智能体提供信任评分。
这是什么?
一个 MCP 服务器,使 AI 智能体(Claude、Cursor、Windsurf 等)能够在交易前检查信任评分并评价与其他智能体的交互。
为什么需要它?
当自主智能体交易 API、数据和服务时,它们需要知道:我可以信任这个交易对手吗? TrustMesh 提供了 AI 智能体生态系统中缺失的声誉层。
工具
工具 | 描述 |
| 评价与另一个智能体的交互 |
| 在交易前检查信任评分 |
| 批量检查多个智能体 |
| 针对不良评价提出争议 |
| 解决争议 |
| 查看谁信任谁 |
| 列出所有已知对等节点 |
安装
npm install -g trustmesh-mcp配置
Claude Desktop
添加到 claude_desktop_config.json:
{
"mcpServers": {
"trustmesh": {
"command": "npx",
"args": ["-y", "trustmesh-mcp"],
"env": {
"TRUSTMESH_NODE_ID": "my-agent-001",
"TRUSTMESH_STORAGE": "sqlite",
"TRUSTMESH_DB_PATH": "/path/to/trust.db"
}
}
}
}Cursor
添加到 .cursor/mcp.json:
{
"mcpServers": {
"trustmesh": {
"command": "npx",
"args": ["-y", "trustmesh-mcp"]
}
}
}Windsurf
添加到 .windsurf/mcp.json:
{
"mcpServers": {
"trustmesh": {
"command": "npx",
"args": ["-y", "trustmesh-mcp"]
}
}
}环境变量
变量 | 默认值 | 描述 |
| 随机 | 你的智能体身份 |
|
|
|
|
| SQLite 路径(如果使用 sqlite) |
使用示例
在与未知智能体交易前:
> Check trust score for agent-paybot-42
→ Trust Score: 0.23 (🔴 LOW)
→ ⚠️ WARNING: This agent has very low trust. Proceed with extreme caution.在成功调用 API 后:
> Rate agent-weather-api 0.9 for delivered-api-data
→ Rating recorded. Trust graph updated.批量检查交易对手:
> Check scores for [agent-a, agent-b, agent-c]
→ 🟢 agent-a: 0.85
→ 🟡 agent-b: 0.52
→ 🔴 agent-c: 0.18许可证
MIT
Related MCP Connectors
Trust infrastructure for AI agents. Portable reputation (JTS 0-5), agent discovery, vouching.
Trust infrastructure for AI agents: read a verifiable Trust Rating, claim an identity, earn a badge.
Agent reputation registry: check, register, and endorse AI agents
Signed agent identity, trust scoring, credit economy, and social layer for AI agents.