> ## Documentation Index
> Fetch the complete documentation index at: https://docs.filefeed.io/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP Server

> Use FileFeed with AI assistants via the Model Context Protocol

## Overview

The `@filefeed/mcp-server` package exposes all FileFeed SDK capabilities as **MCP (Model Context Protocol) tools**, enabling AI assistants to manage your pipelines, clients, schemas, webhooks, and data directly.

<CardGroup cols={3}>
  <Card title="Claude Desktop" icon="message-bot">
    Chat with your FileFeed data in Claude Desktop.
  </Card>

  <Card title="Cursor" icon="code">
    Manage pipelines from your IDE with Cursor.
  </Card>

  <Card title="VS Code" icon="window">
    Use FileFeed tools in VS Code Copilot Chat.
  </Card>
</CardGroup>

## What is MCP?

The [Model Context Protocol](https://modelcontextprotocol.io) is an open standard that lets AI assistants call external tools. The FileFeed MCP server translates your natural language requests into FileFeed API calls — listing runs, creating pipelines, reprocessing files, and more.

## Quick Start

### 1. Get your API key

Retrieve your API key from the FileFeed dashboard under **Profile > API Key**.

### 2. Configure your AI client

<Tabs>
  <Tab title="Claude Desktop">
    Add to your `claude_desktop_config.json`:

    ```json theme={null}
    {
      "mcpServers": {
        "filefeed": {
          "command": "npx",
          "args": ["@filefeed/mcp-server"],
          "env": {
            "FILEFEED_API_KEY": "your-api-key"
          }
        }
      }
    }
    ```
  </Tab>

  <Tab title="Cursor">
    Add to your Cursor MCP settings (`.cursor/mcp.json`):

    ```json theme={null}
    {
      "mcpServers": {
        "filefeed": {
          "command": "npx",
          "args": ["@filefeed/mcp-server"],
          "env": {
            "FILEFEED_API_KEY": "your-api-key"
          }
        }
      }
    }
    ```
  </Tab>

  <Tab title="VS Code">
    Add to your VS Code settings (`.vscode/settings.json`):

    ```json theme={null}
    {
      "mcp": {
        "servers": {
          "filefeed": {
            "command": "npx",
            "args": ["@filefeed/mcp-server"],
            "env": {
              "FILEFEED_API_KEY": "your-api-key"
            }
          }
        }
      }
    }
    ```
  </Tab>
</Tabs>

### 3. Start asking questions

Once configured, you can ask your AI assistant things like:

* *"Show me all failed pipeline runs"*
* *"List my clients and their connection status"*
* *"Create a new pipeline for client Acme with the Employees schema"*
* *"Reprocess the last failed run"*
* *"What webhooks are configured?"*

## Configuration

| Environment Variable  | Required | Default                   | Description                     |
| --------------------- | -------- | ------------------------- | ------------------------------- |
| `FILEFEED_API_KEY`    | Yes      | —                         | Your FileFeed API key           |
| `FILEFEED_BASE_URL`   | No       | `https://api.sftpsync.io` | API base URL                    |
| `FILEFEED_TIMEOUT_MS` | No       | `30000`                   | Request timeout in milliseconds |

You can also pass the API key via CLI flag:

```bash theme={null}
filefeed-mcp --api-key your-api-key
```

## Next steps

<CardGroup cols={2}>
  <Card title="Available Tools" icon="wrench" href="/mcp-server/tools">
    See all 38 tools organized by resource.
  </Card>

  <Card title="API Library" icon="code" href="/api-library/overview">
    Use the TypeScript SDK for programmatic access.
  </Card>
</CardGroup>