# satp-mcp

> satp-mcp — 0xbrainkid-satp-mcp. Use this tool when you need to query AI agent trust scores from AgentFolio, solving issues of agent reliability and trustworthiness in applications like Claude Code, Cursor, and Claude Desktop. It provides a server interface to retrieve trust scores, accepting queries as input and returning scores as output. Ideal for use cases requiring agent evaluation and ranking, such as AI model selection and deployment.

Canonical page: https://skillsregistry.net/skills/0xbrainkid-satp-mcp  
JSON: https://api.skillsregistry.net/v1/skills/0xbrainkid-satp-mcp

## Description

MCP server for SATP — query AI agent trust scores from AgentFolio. Works with Claude Code, Cursor, and Claude Desktop.

## Trust

- **Trust score (0–1):** 0.91
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/0xbrainkid/satp-mcp)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "0xbrainkid-satp-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/0xbrainkid-satp-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/0xbrainkid-satp-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt