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

# MCP Server

Connect AI assistants like Claude and ChatGPT to Feathery to work with your forms, submissions, document extractions, meetings, and more.

Feathery MCP lets AI assistants work directly with your Feathery data. Connect Claude, ChatGPT, Cursor, or another MCP-compatible tool, then ask it to find submissions, review forms, run document extractions, or summarize your meetings.

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Connect</strong></td><td>Add Feathery to Claude, ChatGPT, Claude Code, Cursor, VS Code, Codex, and more.</td><td><a href="/develop/mcp-server/connect-to-the-mcp-server.md">Connect to the MCP Server</a></td></tr><tr><td><strong>Supported Tools</strong></td><td>Every tool the assistant can use, and which ones change data.</td><td><a href="/develop/mcp-server/supported-tools.md">Supported Tools</a></td></tr><tr><td><strong>Security and Troubleshooting</strong></td><td>How access works, keeping API keys safe, and fixing common issues.</td><td><a href="/develop/mcp-server/security-limits-and-troubleshooting.md">Security, Limits and Troubleshooting</a></td></tr></tbody></table>

### Two Ways to Connect

{% columns %}
{% column %}

#### Sign in with Feathery

Recommended for most people. Your AI tool opens a Feathery page where you log in, choose an organization, and choose what the assistant can do. The assistant acts as you, within your role.
{% endcolumn %}

{% column %}

#### Use an API key

For AI tools that don't support signing in, or to work with a test environment. The assistant can access everything in the API key's environment.
{% endcolumn %}
{% endcolumns %}

### What You Can Do

| Area                 | Example prompt                                                                   |
| -------------------- | -------------------------------------------------------------------------------- |
| Forms                | "List my active forms and summarize what each one is for."                       |
| Submissions          | "Show incomplete submissions for this form from the last 7 days."                |
| Users                | "What step is this user currently on?"                                           |
| Hidden fields        | "Create a hidden field called `crm_status` if it does not already exist."        |
| Document extractions | "Run this document extraction on the attached PDF."                              |
| Team                 | "List team members and group them by role."                                      |
| Logs                 | "Check recent API connector errors for this form and group them by status code." |
| Meetings             | "List the action items from my meetings this week."                              |


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.feathery.io/develop/mcp-server.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.