# Feathery MCP

Feathery MCP lets AI tools securely work with your Feathery account. After you connect an MCP-compatible assistant, it can help you find forms, inspect submission data, manage hidden fields, run AI document extractions, and troubleshoot recent logs using your Feathery API key.

Instead of copying data into an AI chat, you can ask the assistant to retrieve the right information directly from Feathery.

### Common Use Cases

Use Feathery MCP to:

* List forms and summarize how they are configured.
* Review a form's fields, steps, rules, integrations, and translations.
* Find submissions by date, completion status, or field value.
* Create or update a submission for testing or operations.
* Review a user's submitted data and form progress.
* Create, edit, or remove hidden fields.
* List document templates.
* Run an AI document extraction on a file.
* Invite team members or update account roles.

### Example Prompts

* "List my active forms and summarize what each one is for."
* "Show incomplete submissions for this form from the last 7 days."
* "Fetch the form schema and tell me which fields are required."
* "Create a hidden field called `crm_status` if it does not already exist."
* "Run this document extraction on the attached PDF."
* "Check recent API connector errors for this form and group them by status code."

### How Access Works

Feathery MCP uses the Feathery API key you provide when setting up the connection. The assistant can only access the Feathery account and environment associated with that key.

Use a test environment API key when experimenting. Use a live API key only when you want the assistant to work with live production data.

### What Is Supported

Feathery MCP currently supports tools for:

* Forms
* Submissions
* Users
* Fields and hidden fields
* Team accounts
* AI document extractions
* Document templates
* Logs


---

# 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.feathery.io/develop/feathery-mcp.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.