chore: new mcp docs (#169)

This commit is contained in:
doria 2025-07-25 15:18:27 -04:00 committed by GitHub
parent 83cf0512c6
commit af10ec804c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 56 additions and 32 deletions

View File

@ -7,43 +7,67 @@ sidebarTitle: 'MCP Integration'
You can let Claude use Honcho to manage its own memory in the native desktop app by using the Honcho MCP integration! Follow these steps:
1. Clone the `honcho` repo:
1. Go to https://app.honcho.dev and get an API key. Then go to Claude Desktop and navigate to custom MCP servers.
```
git clone https://github.com/plastic-labs/honcho.git
<Note>
If you don't have node installed you will need to do that. Claude Desktop or Claude Code can help!
</Note>
2. Add Honcho to your Claude desktop config. You must provide a username for Honcho to refer to you as -- preferably what you want Claude to actually call you.
```json
{
"mcpServers": {
"honcho": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.honcho.dev",
"--header",
"Authorization:${AUTH_HEADER}",
"--header",
"X-Honcho-User-Name:${USER_NAME}"
],
"env": {
"AUTH_HEADER": "Bearer <your-honcho-key>",
"USER_NAME": "<your-name>"
}
}
}
}
```
2. Navigate into the `mcp` folder.
You may customize your assistant name and/or workspace ID. Both are optional.
```
cd mcp
```json
{
"mcpServers": {
"honcho": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.honcho.dev",
"--header",
"Authorization:${AUTH_HEADER}",
"--header",
"X-Honcho-User-Name:${USER_NAME}",
"--header",
"X-Honcho-Assistant-Name:${ASSISTANT_NAME}",
"--header",
"X-Honcho-Workspace-ID:${WORKSPACE_ID}"
],
"env": {
"AUTH_HEADER": "Bearer <your-honcho-key>",
"USER_NAME": "<your-name>",
"ASSISTANT_NAME": "<your-assistant-name>",
"WORKSPACE_ID": "<your-custom-workspace-id>"
}
}
}
}
```
3. Sync the virtual environment. This package uses [uv](https://docs.astral.sh/uv/), [install](https://docs.astral.sh/uv/#installation) if you haven't.
3. Restart the Claude Desktop app. Upon relaunch, it should start Honcho and the tools should be available!
```
uv sync
```
4. Finally, Claude needs instructions on how to use Honcho. The Desktop app doesn't allow you to add system prompts directly, but you can create a project and paste these [instructions](https://raw.githubusercontent.com/plastic-labs/honcho/refs/heads/main/mcp/instructions.md) into the "Project Instructions" field.
4. Get an API key from [honcho.dev](https://app.honcho.dev)
5. Run FastMCP to install the Honcho MCP server in Claude Desktop:
```
uv pip install fastmcp
fastmcp install claude-desktop server.py --env-var HONCHO_API_KEY=<your-api-key>
```
<Note>You can easily install Honcho MCP in claude-code or cursor by replacing `claude-desktop` in the above command with either of those values</Note>
<Warning>Make sure Claude Desktop has access to `uv` on your system. You can get the location by running `which uv` on MacOS/Linux or `where uv` on Windows.</Warning>
6. Restart the Claude Desktop app. Upon relaunch, it should start Honcho and the tools should be available!
## Project Instructions
Finally, Claude needs instructions on how to use Honcho. The Desktop app doesn't allow you to add system prompts directly, but you can create a project and paste these [instructions](https://github.com/plastic-labs/honcho-mcp/blob/main/instructions.txt) into the "Project Instructions" field.
<Note>Be sure to update the \<app_name\> and \<user_name\> variables in the instructions.txt file.</Note>
Claude should then query for insights before responding and write your messages to storage! If you come up with more creative ways to get Claude to manage its own memory with Honcho, feel free to [let us know](https://discord.gg/plasticlabs) or make a PR on this [repo](https://github.com/plastic-labs/honcho-mcp/tree/main)!
Claude should then query for insights before responding and write your messages to storage! If you come up with more creative ways to get Claude to manage its own memory with Honcho, feel free to [let us know](https://discord.gg/plasticlabs) or make a PR on this [repo](https://github.com/plastic-labs/honcho/tree/main/mcp)!