`beemcp` from. 2. Add the following line to the `.env` file, replacing `your_actual_bee_api_key_here` with your real key: ```dotenv BEE_API_TOKEN="your_actual_bee_api_key_here" ``` Alternatively, you can set the `BEE_API_TOKEN` environment variable directly in your system or shell: ```bash export BEE_API_TOKEN="your_actual_bee_api_key_here" # Now run the server in the same shell session uvx beemcp ``` **The server will exit with an error if the `BEE_API_TOKEN` 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"], "env": {"BEE_API_TOKEN": ""} } } ```

Using pip installation

```json "mcpServers": { "bee": { "command": "python", "args": ["-m", "beemcp.beemcp"], "env": {"BEE_API_TOKEN": ""} } } ```

If you go to the `Settings` window in Claude Desktop and open the `Developer` tab, you should see something like this: ![Example Claude Desktop Configuration](https://github.com/OkGoDoIt/beemcp/raw/master/claude-desktop-configuration.png) #### Configure for Zed Add the following to your Zed `settings.json`:

Using uvx (Recommended)

```json "context_servers": [ { "name": "beemcp", "command": "uvx", "args": ["beemcp"], "env": {"BEE_API_TOKEN": ""} } ], ```

Using pip installation

```json "context_servers": [ { "name": "beemcp", "command": "python", "args": ["-m", "beemcp.beemcp"], "env": {"BEE_API_TOKEN": ""} } ], ```

## Available Tools These are the actions the LLM can request from `beemcp`. ### Conversations * `list-all-conversations` * **Description:** List all conversations the user has had including short summaries. Use this to get an overview of the user's conversation history for context. Then you can use the get-conversation tool to get the full details of a specific conversation. * `get-conversation` * **Description:** Get the full details of a conversation by its ID. Use this to retrieve specific conversation details when the user asks about a particular conversation. You can use the list-all-conversations tool to get the id of the conversation you want to look up. * **Arguments:** * `id` (integer): The ID of the conversation. ### Facts * `list-all-user-facts` * **Description:** List all facts the user has recorded. Use this to get an overview of the user's recorded facts for context. Then you can use the get-user-fact tool to get the full details of a specific fact. * `get-user-fact` * **Description:** Get the full details of a fact by its ID. Use this to retrieve specific fact details when the user asks about a particular fact. You can use the list-all-user-facts tool to get the id of the fact you want to look up. * **Arguments:** * `id` (integer): The ID of the fact. * `record-user-fact` * **Description:** Create a new fact. Use this to record new information about the user, their preferences, and other details that might be relevant to answering other questions. * **Arguments:** * `text` (string): The content of the fact. * `update-user-fact` * **Description:** Update an existing fact. Use this to update information about the user, their preferences, and other details that might be relevant to answering other questions. Set confirmed to true if the user has explicitly confirmed the fact, otherwise if it's just an implied fact gathered from context then set confirmed to false. * **Arguments:** * `id` (integer): The ID of the fact to update. * `text` (string): The new content for the fact. * `confirm

#lifelogging

BeeMCP - A Bee MCP Server