OkGoDoIt/beemcp

Unofficial Model Context Protocol (MCP) server for interacting with your Bee wearable lifelogging data. More context on my blog.
This server acts as a bridge, allowing Large Language Models (LLMs) like Claude or custom AI agents to access and interact with your personal data stored in Bee, including conversations, facts, to-dos, and location history.
Disclaimer: This is an unofficial project and is not affiliated with Bee. Use it at your own risk. Ensure you understand the security implications of granting AI access to your personal data via the API key.
## Core Concept
Bee.computer helps you capture moments from your life (conversations, places visited, notes). beemcp makes this data available to your AI assistant through the Model Context Protocol. This means you can ask your AI questions like:
"What important things did I discuss last week?"
"Remind me about Brad's dietary preferences."
"Where was I last Tuesday afternoon?"
"Add 'Book flight tickets' to my reminders."
The AI, using beemcp, can securely fetch or modify this information from your Bee.computer account.
## Prerequisites
1. Python: Version 3.10 or higher.
2. Bee.computer API Key: You need an API key from your Bee account settings.
## Installation
You can install and run beemcp using uv (recommended) or pip.
### Using uv (recommended)
uv is a fast Python package installer and resolver. If you have uv installed, you don't need to install beemcp separately. You can run it directly using uvx:
bash
# Example of running directly (requires API key configured, see below)
uvx beemcp
### Using PIP
Alternatively, you can install beemcp using pip:
bash
pip install beemcp
After installation, you can run it as a Python module:
bash
python -m beemcp.beemcp
Or, if the entry point is correctly added to your system's PATH during installation, you might be able to run it directly:
bash
beemcp
## Configuration
### 1. API Key Setup (required)
beemcp requires your Bee API key to function. Never share this key publicly or commit it to version control.
Get your API key from the Bee developer website here.
If running in Claude or another MCP client, you will likely provide the BEEAPITOKEN environment variable in the client's configuration.
If running directly from the command line, provide the key is using a .env file in the directory where you run the beemcp server:
1. Create a file named .env in the same directory you intend to run beemcp from.
2. Add the following line to the .env file, replacing youractualbeeapikeyhere with your real key:
dotenv
BEEAPITOKEN="youractualbeeapikeyhere"
Alternatively, you can set the BEEAPITOKEN environment variable directly in your system or shell:
bash
export BEEAPITOKEN="youractualbeeapikeyhere"
# Now run the server in the same shell session
uvx beemcp
The server will exit with an error if the BEEAPITOKEN is not found.
### 2. Connecting to LLM Clients
You need to tell your LLM client (like Claude.app or Zed) how to start and communicate with the beemcp server.
#### Configure for Claude.app
Add the following to your Claude settings (settings.json):
>Using uvx (Recommended):
json
"mcpServers": {
"beemcp": {
"command": "uvx",
"args": ["beemcp"],