Model Context Protocol · bring your own agent

Connect a compatible AI
to your books.

LedgerBeaver speaks MCP — the open standard for connecting an AI agent to real tools and data. Use a client that supports the published transport and OAuth or scoped bearer-key authentication. Complete a read-only handshake and versioned smoke test before enabling governed writes.

Connect MCP

Three steps. Then verify.

Use the endpoint with the authentication path supported by your client. Current setup guidance lives inside the app.

1

Copy the endpoint

This is the published remote endpoint for clients that support the required MCP transport; authentication varies by client.

MCP endpoint
https://mcp.ledgerbeaver.com/mcp
2

Sign up & generate your key

Create a free account, then open Connect AI in the app and generate a company-scoped API key. It’s the only credential your agent needs.

Sign up free →

Use OAuth where the client supports it; otherwise use a scoped bearer key. Start read-only and verify the handshake.

3

Paste into your agent

Current setup examples for supported client paths are inside the app under Connect AI. Verify your installed version before relying on the configuration.

Get started →
MCP compatibility

One server. Client-specific verification.

These clients expose compatible MCP paths. A named version is only Verified after it passes the LedgerBeaver smoke test.

ClaudeDesktop, Code, Web
CodexOpenAI · CLI + MCP
Cursorvia .cursor/mcp.json
Gemini CLI+ Vertex AI
OpenCodeopen-source agent
Openclawopen-source agent
Hermes Agentautonomous workflows
Your own agentany MCP-speaking client
No AI yet?

Three ways to get one.

You don't need to be technical. Pick the path that matches how hands-on you want to be.

Browser-based

ChatGPT or Claude

Use ChatGPT, Claude.ai, or another browser experience that supports custom MCP servers. Add LedgerBeaver's MCP URL and authorize it.

Set up your connection →
Complex workflows

MCP-capable agents

Claude Code, Codex, Cursor, Gemini CLI, and other MCP clients expose compatible paths. Verify the installed version and approval behavior before write workflows.

Connect an agent →
Max privacy

A local model

Run a model on your own hardware with Ollama, LM Studio, vLLM, or llama.cpp — they serve the model only. Connect it through an MCP-capable agent like Continue, OpenCode, or Cline, which bridges your local model to LedgerBeaver.

See OpenCode →

Using Claude Code, Codex, or another CLI agent? Your account’s Connect AI page has one-line setup commands for each.

Sign up to get yours →