> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.reka.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.reka.ai/_mcp/server.

# MCP Server

> Connect agent clients to Reka Vision with MCP for video upload, search, inspection, and Q&A.

The Reka Vision MCP server lets agent clients such as Claude Code work with your video library. Agents can upload videos, index them for search and Q\&A, find relevant moments, inspect transcripts and captions, and ask focused questions about video content.

Use MCP when you want an agent to research across videos from a local workspace or chat client, without wiring each Vision API endpoint into the agent yourself.

## Prerequisites

Before you start, make sure you have:

* A Reka API key from [platform.reka.ai](https://platform.reka.ai)
* Python 3.12 or later
* [`uv`](https://docs.astral.sh/uv/getting-started/installation/) installed so you can run the server with `uvx`

Check your local versions:

```bash
python --version
uv --version
```

## Configure your MCP client

MCP clients start the Reka MCP server from their configuration. Add the server to the client you want to use.

## Claude Code

Register the server from the command line:

```bash
claude mcp add reka-mcp -e REKA_VISION_API_KEY=YOUR_API_KEY -- uvx reka-mcp
```

## Claude Desktop

Add the server to `~/Library/Application Support/Claude/claude_desktop_config.json`:

```json
{
  "mcpServers": {
    "reka-mcp": {
      "command": "uvx",
      "args": ["reka-mcp"],
      "env": {
        "REKA_VISION_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}
```

Restart Claude Desktop after updating the config.

## Codex

Register the server from the command line:

```bash
codex mcp add --env REKA_VISION_API_KEY=YOUR_API_KEY reka-mcp -- uvx reka-mcp
```

## Cursor

Add the server to `.cursor/mcp.json`:

```json
{
  "mcpServers": {
    "reka-mcp": {
      "command": "uvx",
      "args": ["reka-mcp"],
      "env": {
        "REKA_VISION_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}
```

## Verify installation

After configuring your MCP client, restart it and confirm that the Reka MCP server is available.

| Client         | How to verify                                                                                   |
| -------------- | ----------------------------------------------------------------------------------------------- |
| Claude Code    | Run `claude mcp list` and confirm `reka-mcp` is listed.                                         |
| Codex          | Run `codex mcp list`, restart your Codex session, and confirm the Reka MCP tools are available. |
| Claude Desktop | Open the tools menu from the chat input and confirm the Reka tools are available.               |
| Cursor         | Open MCP settings and confirm `reka-mcp` is enabled without errors.                             |

## Updating

Check which version you're running:

```bash
uvx reka-mcp --version
```

To update to the latest version, clear the cached package and restart your MCP client:

```bash
uv cache clean reka-mcp
```

## Available tools

With the MCP server connected, your agent can:

* **Manage videos**: Upload, list, inspect, update, and delete videos
* **Organize video libraries**: Create, list, and delete video groups
* **Prepare videos for analysis**: Index videos for search, Q\&A, or full analysis
* **Research and search**: Find timestamped moments across indexed videos
* **Understand video content**: Ask visual questions about one or more videos
* **Inspect source context**: Read transcripts, captions, scenes, and feature status
* **Detect objects**: Locate prompted visual elements in short video segments

| Tool                  | Use it to                                                    |
| --------------------- | ------------------------------------------------------------ |
| `upload_video`        | Upload a video from a URL or local file path                 |
| `list_videos`         | List videos in your account or in a video group              |
| `get_video`           | Check video metadata, upload status, and feature status      |
| `update_video`        | Update video name, title, description, or group              |
| `delete_video`        | Permanently delete a video and its indexed data              |
| `create_group`        | Create a video group                                         |
| `list_groups`         | List video groups                                            |
| `delete_group`        | Delete a video group without deleting its videos             |
| `index_video`         | Prepare a video for search, Q\&A, or full analysis           |
| `search_videos`       | Find timestamped moments across indexed videos               |
| `ask_video`           | Ask questions about one or more videos with visual analysis  |
| `get_transcript`      | Read spoken words as text, segments, or words                |
| `get_captions`        | Read AI-generated visual descriptions with timestamps        |
| `get_scenes`          | Get detected scene boundaries                                |
| `segment_video`       | Detect objects in short video segments with bounding boxes   |
| `get_feature_catalog` | List available video analysis features and dependencies      |
| `summarize_video`     | Get a compact overview of video status and available context |

The MCP server is open source at [github.com/reka-ai/reka-mcp](https://github.com/reka-ai/reka-mcp).