# brain-mcp

> Use this tool when you need to enhance AI agent cognition with a searchable conversation history and advanced analysis capabilities. It solves problems related to context switching, idea tracking, and decision alignment by providing 25 specialized tools, including tunnel_state and alignment_check. With fast 12ms recall and local-first design, it integrates with various AI interfaces, accepting conversation histories and outputting actionable insights.

Canonical page: https://skillsregistry.net/skills/mordechaipotash-brain-mcp  
JSON: https://api.skillsregistry.net/v1/skills/mordechaipotash-brain-mcp

## Description

Cognitive prosthetic for AI agents. Indexes conversation history from ChatGPT, Claude Code, Cursor, and Gemini CLI into searchable embeddings. 25 MCP tools including tunnel_state (resume where you left off), switching_cost (quantify context-switch penalty), thinking_trajectory (track idea evolution), and alignment_check (decisions vs principles). LanceDB + Parquet, 12ms recall, local-first.

## Trust

- **Trust score (0–1):** 0.59
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/w60bxx2bkq)
- **Repository:** <https://github.com/mordechaipotash/brain-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": "mordechaipotash-brain-mcp"
    }
  }
}
```

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