myBrain

io.github.mybrain-aiv0.1.0Updated Oct 8, 2026

Your personal knowledge base and memory for AI agents: search, explore and feed your myBrain.

VerifiedStreamable HTTPWeb executableProductivity & WorkflowKnowledge & Memory

Overview

AI-generated overview

Connects an assistant to a personal myBrain knowledge base so it can search, explore, and add sources to a private knowledge graph.

What it does
Exposes read tools such as recall_memories, search_user_knowledge, search_passages, explore_node, trace_path, and get_knowledge_overview for searching and navigating a personal knowledge graph. Write tools (add_source_text, add_source_url, add_source_youtube, approve_source, import_memories) add material that lands as a source pending the user's approval. An ask_mybrain tool synthesizes a cited answer over the brain.
When to use it
Useful when an assistant should consult your own uploaded, linked, recorded, or written material instead of asking you again, or when you want it to feed new sources into that knowledge base. Best for people who already keep a myBrain knowledge base and want agents to reason over it.
Requirements
A remote Streamable HTTP endpoint at (keep the trailing slash). Requires an MCP API key created in myBrain under Settings, Connected Apps, MCP Integrations, sent as the Authorization header in the form Bearer plus the key. Keys carry scopes: mcp:read, mcp:write, and mcp:orchestrator. Network access is needed.
Before you install
The Authorization header carries a secret MCP API key; scope it to only what you need, since mcp:write lets the assistant add sources and mcp:orchestrator spends plan quota and is rate limited. Writes become sources pending your approval and are processed only after you approve them. Content you add is sent to the myBrain service.

Installation

In SourceWeft

  1. Open myBrain in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.mybrain.ai/mcp/"
    }
  }
}

README

myBrain MCP

myBrain is your personal knowledge base: everything you upload, link, record or write becomes a knowledge graph you can search, explore and reason over. This repository is the public home of the MCP server entry and of the files that teach an AI agent how to use your brain well.

EndpointTransportAuth
https://mcp.mybrain.ai/mcp/Streamable HTTPAuthorization: Bearer <MCP API key>

Create the key in myBrain: Settings → Connected Apps → MCP Integrations. Keys carry scopes: mcp:read (search and read tools), mcp:write (add sources, approve, import memories), mcp:orchestrator (ask_mybrain). Keep the trailing slash in the URL.

Connect

Claude Code

bash
claude mcp add mybrain --transport http --url https://mcp.mybrain.ai/mcp/ --header "Authorization: Bearer YOUR_MCP_API_KEY"

Claude Desktop, Cursor, VS Code (mcpServers in the client config):

json
{  "mcpServers": {    "mybrain": {      "url": "https://mcp.mybrain.ai/mcp/",      "headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }    }  }}

Teach your agent to use it

Connecting the server is not enough. The agent also has to know when to search your brain instead of asking you, which tool is the cheap one, and that every write becomes a source pending your approval. Pick what fits your client:

FileUse
skill/mybrain/SKILL.mdClaude Code skill. Copy the skill/mybrain/ folder into ~/.claude/skills/ (personal) or <project>/.claude/skills/ (project).
templates/CLAUDE.mdBlock to paste into a project or global CLAUDE.md.
templates/AGENTS.mdSame guidance for clients that read AGENTS.md (Codex, Cursor, others).

All three assume the server is connected as mybrain (tool names mcp__mybrain__* in Claude Code).

Tools

Read (mcp:read): recall_memories, list_memories, search_user_knowledge, search_passages, read_source_passages, search_knowledge, search_sources, list_sources, explore_node, trace_path, get_knowledge_overview, list_knowledge_fields, get_knowledge_node, get_related_concepts, list_chat_threads, get_chat_history, get_suggested_questions, get_ingestion_status, get_usage_summary.

Write (mcp:write): add_source_text, add_source_url, add_source_youtube, approve_source, import_memories. Writes land as a source pending your approval in myBrain and are processed only after you approve.

Ask (mcp:orchestrator): ask_mybrain, a full answer synthesized over your brain with citations. It is rate limited and spends your plan quota.

Registry

server.json is the manifest published to the official MCP Registry as io.github.mybrain-ai/mcp.

Publishing (maintainers only) needs an Owner of the mybrain-ai org. The interactive mcp-publisher login github only grants the personal namespace (registry#1468); log in with a PAT instead (classic with read:org, or fine-grained with "Organization → Members → Read-only"), on mcp-publisher 1.8.1 or newer:

bash
./mcp-publisher login github --token "$GH_PAT"./mcp-publisher publish

License

The files in this repository are released under the MIT License. See TRADEMARKS.md for the marks. The myBrain service and the server code behind mcp.mybrain.ai are not part of this repository.

Source: README.md at commit eead683

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v0.1.0LatestOct 8, 2026