Prerequisites
- A running Breadbox instance (local binary, Docker, or remote server)
- An API key if you’re connecting over HTTP — generate one from the API Keys section of the admin dashboard (API keys)
Option A: Claude Desktop via Streamable HTTP
Use this option when Breadbox is running in Docker or on a remote server. Claude Desktop connects to the/mcp endpoint over HTTP and authenticates with your API key.
Open the Claude Desktop config file. On macOS, it is at:
mcpServers:
localhost:8080 with the actual host and port where Breadbox is running. For a remote server with HTTPS, use https://your-domain.com/mcp.
Restart Claude Desktop after saving the file.
Option B: Claude Desktop via Stdio
Use this option when thebreadbox binary is installed locally on the same machine as Claude Desktop. Stdio mode connects directly to the database — no HTTP server or API key needed.
breadbox binary must be on your PATH. Stdio mode uses the same database credentials configured in Breadbox’s environment.
Restart Claude Desktop after saving the file.
Option C: Claude Code
Claude Code reads MCP configuration from.mcp.json in your project root, or from ~/.config/claude/mcp.json for a user-level config that applies to all projects.
- Streamable HTTP
- Stdio
Option D: Any MCP-compatible agent
Any agent that supports MCP over Streamable HTTP can connect to Breadbox. Point your client at the/mcp endpoint and include your API key:
POST /mcp— JSON-RPC messagesGET /mcp— SSE stream (with session resumption support)DELETE /mcp— terminates the session
Connection URL reference
| Deployment | Transport | URL or command |
|---|---|---|
| Docker Compose (local) | HTTP | http://localhost:8080/mcp |
| Remote server | HTTP | https://your-domain.com/mcp |
| Local binary | Stdio | breadbox mcp-stdio |
Read-only vs. read-write
API keys have a scope that controls what the connected agent can do. A read-only key gives the agent access to all query tools — listing accounts, searching transactions, checking sync status — but prevents it from triggering syncs or submitting reports. A full access key allows the agent to trigger manual syncs and submit reports in addition to reading data.For most analysis and Q&A use cases, a read-only key is sufficient and limits what the agent can affect. Use a full access key only when you want the agent to trigger syncs or submit reports on your behalf.