# driftguard-mcp

> driftguard-mcp — jschoemaker-driftguard-mcp. Use this tool when you need to monitor and manage AI conversation drift in real-time, solving issues with conversation quality and session health. It exposes drift scores and session data to compatible clients like Claude Desktop, providing valuable insights for improvement. Ideal for use cases requiring proactive conversation management and optimization, with inputs from AI conversations and outputs to MCP clients.

Canonical page: https://skillsregistry.net/skills/jschoemaker-driftguard-mcp  
JSON: https://api.skillsregistry.net/v1/skills/jschoemaker-driftguard-mcp

## Description

MCP server for DriftGuard — exposes AI conversation drift scores and session health to Claude Desktop and other MCP clients

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-20

## Source

- **Source listing:** [GitHub](https://github.com/jschoemaker/driftguard-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": "jschoemaker-driftguard-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jschoemaker-driftguard-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jschoemaker-driftguard-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