Honcho MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Honcho MCP Serverlist my active sessions"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Honcho MCP Server
A remote MCP server for Honcho, providing AI memory and personalization tools to LLM clients like Claude Desktop.
Clients connect over HTTP SSE — no local process spawning, no stdio bridge needed.
Deploy
Docker (recommended)
docker build -t honcho-mcp .
docker run -d -p 3000:3000 \
-e HONCHO_API_URL=http://your-honcho-backend:8000 \
-e HONCHO_API_KEY=your-key \
honcho-mcpManual
bun install
HONCHO_API_URL=http://your-honcho-backend:8000 HONCHO_API_KEY=your-key bun startRelated MCP server: myBrAIn
Connect
Add the server URL to your MCP client config:
Note: User identity (peer_id) is set through Honcho tool calls — the
X-Honcho-*headers in the MCP config below are optional metadata and not consumed by the Honcho SDK. The server handles both SSE (GET) and JSON-RPC (POST) at the root/path.
VS Code — add to .vscode/mcp.json:
{
"servers": {
"honcho": {
"type": "http",
"url": "http://your-host:3000",
"headers": {
"X-Honcho-User-Name": "your-user-name",
"X-Honcho-Workspace-ID": "default",
"X-Honcho-Assistant-Name": "Assistant"
}
}
}
}Claude Desktop — edit claude_desktop_config.json:
{
"mcpServers": {
"honcho": {
"type": "http",
"url": "http://your-host:3000",
"headers": {
"X-Honcho-User-Name": "your-user-name",
"X-Honcho-Workspace-ID": "default",
"X-Honcho-Assistant-Name": "Assistant"
}
}
}
}Configuration
Server-side environment variables:
Variable | Default | Description |
| — | API key for Honcho backend (only needed if auth enabled) |
|
| Self-hosted Honcho backend URL |
|
| Workspace to operate in |
|
| MCP server listen port |
|
| MCP server listen host |
Client MCP config headers (use in .vscode/mcp.json or Claude Desktop config):
Header | Default | Description |
|
| Your user name in Honcho |
Available Tools
Workspace: inspect_workspace, list_workspaces, search, get_metadata, set_metadata
Peers: create_peer, list_peers, chat, get_peer_card, set_peer_card, get_peer_context, get_representation
Sessions: create_session, list_sessions, delete_session, clone_session, add_peers_to_session, remove_peers_from_session, get_session_peers, inspect_session, add_messages_to_session, get_session_messages, get_session_message, get_session_context
Conclusions: list_conclusions, query_conclusions, create_conclusions, delete_conclusion
System: schedule_dream, get_queue_status
Development
bun install
bun start # http://localhost:3000
bun run build # type-checkThis server cannot be deployed
Maintenance
Related MCP Connectors
Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.
- mcpOAuthai.butlerbrain
Persistent memory for AI assistants. Save once; recall from Claude, ChatGPT, or any MCP client.
An MCP memory server. One memory your agents share — across models, devices and apps.
Cloud-hosted MCP server for durable AI memory
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceAn MCP-native, local-first memory server that gives AI agents persistent, structured memory across sessions and tools, enabling them to maintain identity and context without reconfiguration.3MIT
- AlicenseNot gradedqualityDmaintenanceMCP server that provides persistent memory and contextual awareness to language models, enabling project onboarding, recall of architectural rules, and code consistency across sessions.32MIT
- FlicenseNot gradedqualityAmaintenanceAn MCP server that provides a shared memory layer for Claude across claude.ai, Claude Code CLI, and Desktop, storing revisioned memory entries, session timelines, handoffs, and uploaded artifacts in SQLite.-
- AlicenseNot gradedqualityAmaintenanceLocal-first MCP server providing persistent markdown memory with persona engine and fast search, designed to unify AI assistant memory across Claude Code, Cowork, and Dispatch.18 npm1MIT