# The Brigge MCP server

## Introduction

The Brigge MCP (Model Context Protocol) server gives AI clients programmatic access to your Brigge workflow automation platform. Once connected, the AI client can manage systems, execute operations, and inspect pipelines directly, without leaving the chat interface.

## What can I do with the MCP?

Having integrated the Brigge MCP server, you can:

* Search for systems and view their available operations
* Execute operations against systems, with or without authentication
* Inspect pipeline structure and run history
* Investigate pipeline failures

## Supported clients

You can connect any AI client that supports token authentication, including:

* [Claude Code](https://docs.anthropic.com/en/docs/claude-code)
* [Cursor](https://cursor.sh/)
* [Continue](https://cursor.com/docshttps://cursor.com/docs)
* [Windsurf](https://www.codeium.com/windsurf)
* [Opencode](https://opencode.ai/)

## Before you start

To [get started](/the-brigge-mcp-server/getting-started.md), you need:

* An active Brigge account with [dashboard access](https://brigge.ai/).
* An MCP-compatible client that's installed and running.


---

# Agent Instructions: 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:

```
GET https://docs.brigge.ai/the-brigge-mcp-server.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.