brain-mcp

brain-mcp

Exposes a Brain wiki to other agents, enabling reading, searching, and append-only writes to notes and journals.

Category
Visit Server

README

brain-mcp

MCP server exposing the Brain wiki to other agents: read/search + append-only writes.

Run locally (stdio)

Register at user scope so it's available in every Claude Code session:

{
  "mcpServers": {
    "brain": {
      "command": "brain-mcp",
      "env": {
        "BRAIN_ROOT": "/Users/shanzer/Documents/Brain",
        "BRAIN_MANIFEST": "/Users/shanzer/source/brain/brain-mcp.config.json"
      }
    }
  }
}

BRAIN_MANIFEST must be an absolute path to brain-mcp.config.json in this repo — the manifest lives in the project directory, not inside the vault.

Stdio smoke test

cd ~/source/brain
printf '%s\n%s\n' \
  '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"smoke","version":"0"}}}' \
  '{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}' \
| BRAIN_ROOT="/Users/shanzer/Documents/Brain" \
  BRAIN_MANIFEST="/Users/shanzer/source/brain/brain-mcp.config.json" \
  brain-mcp

Expected: two JSON-RPC responses; the second lists 8 tools.

Run as a network service (HTTP)

BRAIN_TRANSPORT=http BRAIN_PORT=3005 \
BRAIN_TOKEN=… BRAIN_ALLOWED_HOSTS=localhost,yoyodyne.local \
BRAIN_ROOT=/path/to/synced/Brain \
BRAIN_MANIFEST=/path/to/brain-mcp/brain-mcp.config.json \
brain-mcp

Smoke test:

curl -s localhost:3005/health

Remote client stanza:

{ "mcpServers": { "brain": { "url": "http://storm.local:3005/mcp",
  "headers": { "Authorization": "Bearer <token>" } } } }

Tools

  • brain_search, brain_read, brain_map, brain_pending (read)
  • brain_submit_source, brain_append_journal, brain_add_note, brain_deposit (append/create-only)

brain_append_journal — entry placement

brain_append_journal inserts a timestamped bullet directly under the chosen ## Section heading — after any existing bullets in that section, immediately before the next ## heading (or EOF for the last section). The entry shape is:

- YYYY-MM-DD HH:MM — your content here

Downstream journal-processing agents should expect entries nested under their section headings (## Work, ## Personal, ## Notes & Ideas), not as labeled blocks at end of file.

Graph view (HTTP transport only)

  • GET /graph — full wikilink graph as JSON ({nodes, edges, stats}), gated by the same allowlist + bearer token as /mcp. Nodes are every .md page; unresolved [[targets]] appear as ghost: true nodes; attachment embeds are skipped.
  • GET /graph/view — self-contained Obsidian-style interactive viewer (static/graph.html). Allowlist-gated only; the page prompts for the bearer token (stored in that browser's localStorage) and fetches /graph same-origin.
curl -s -H "Authorization: Bearer <token>" localhost:3005/graph | jq .stats
open http://localhost:3005/graph/view

Deposit registry

Edit brain-mcp.config.json and restart to add targets. See the design spec.

launchd (macOS background service)

A plist template lives at docs/launchd/com.brain-mcp.plist. To install:

cp docs/launchd/com.brain-mcp.plist ~/Library/LaunchAgents/
# Edit the copy: replace REPLACE_WITH_NODE_PATH with the output of `which node`
# (e.g. an nvm path or /opt/homebrew/bin/node) and REPLACE_WITH_TOKEN with your bearer token.
chmod 600 ~/Library/LaunchAgents/com.brain-mcp.plist   # file holds the token
launchctl load ~/Library/LaunchAgents/com.brain-mcp.plist

Security: the plist holds BRAIN_TOKEN in plaintext — chmod 600 is required. Never commit a filled-in token. The template ships with REPLACE_WITH_TOKEN.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured