> For the complete documentation index, see [llms.txt](https://docs.protoboard.xyz/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.protoboard.xyz/agent-bridge-mcp/overview.md).

# Overview

Connect Claude Code, Codex, or any MCP-compatible agent to a live Protoboard session and run the same tools ProtoBot runs

The Agent Bridge is a Model Context Protocol (MCP) server that lets an external AI coding agent operate on your live Protoboard session. Once connected, your agent can search the parts library, place and wire parts, run DRC, and manage your BOM, driven from Claude Code, OpenAI Codex, Gemini CLI, or any MCP-compatible client. It is the bring-your-own-agent alternative to ProtoBot: use a subscription and model you already pay for instead of Protoboard Pro.

**Reach for the bridge when** you work mostly in a terminal or IDE, want a specific model (for example Claude Opus in Claude Code), or want to edit board designs and code in the same agent session. **Reach for ProtoBot when** you want the zero-setup option with visual feedback inside Protoboard.

## Good to know

* **Keep a Protoboard tab open.** Most tools run in your live browser session; board edits time out after 30 seconds with no open tab. Read-only research tools (`search_web`, `search_docs`, `fetch_url`) keep working without one.
* **It inherits your permissions.** The bridge acts only on boards you can already access, and only on board operations: it cannot touch billing, settings, or account data.
* **Revocation is instant.** Revoke a key in **Settings > Developer** and the next call fails immediately.
* **Tools match ProtoBot's.** Your agent gets the same toolset ProtoBot uses. Run `/mcp` (or your client's equivalent) after connecting to list the current tools.

## Next step

[**Set up the Agent Bridge**](/agent-bridge-mcp/setup.md): create a key, configure your agent, and verify the connection.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.protoboard.xyz/agent-bridge-mcp/overview.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.