About FastMCP server for Overseerr
FastMCP server for Seerr lets AI clients inspect movie and TV requests and submit new requests to configured libraries. It also provides server status, media search, library, and user information.
Key features
- 01Check Seerr server status
- 02List paginated movie and TV requests
- 03Search movies and TV shows
- 04Submit requests to configured libraries
- 05Retrieve library and user details
Use cases
- 01Review pending or recently available requests
- 02Find a movie or series in Seerr
- 03Request a title for a user and library
- 04Check configured libraries and users
MCP support
Exposes Seerr API operations as MCP tools for status, request lists, media search, library and user details, and submitting movie or TV requests.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEFastMCP server for Seerr
FastMCP server to interact with the Seerr API for movie and TV show requests management, built using the fastmcp library.
Project Repository: https://github.com/ptbsare/seerr-mcp-server
Components
Tools
The server implements the following tools to interact with Seerr:
seerr_status: Get the status of the Seerr server.seerr_movie_requests: Get a paginated list of movie requests. Accepts optionalstatus,start_date(YYYY-MM-DDTHH:MM:SS.mmmZ format),take(default 7), andskip(default 0).seerr_tv_requests: Get a paginated list of TV show requests. Accepts optionalstatus,start_date(YYYY-MM-DDTHH:MM:SS.mmmZ format),take(default 7), andskip(default 0).seerr_request_movie_to_library: Submit a movie request using its TMDB ID to a specific library, on behalf of a specific user. Requirestmdb_id,library_name, anduser_display_name. Available library names and user display names (unique ones only) are fetched at server startup and included in the tool's argument descriptions.seerr_request_tv_to_library: Submit a TV show request using its TMDB ID to a specific library, on behalf of a specific user. Requirestmdb_id,library_name, anduser_display_name. Optionally acceptsseasons(list of integers). Available library names and user display names (unique ones only) are fetched at server startup and included in the tool's argument descriptions.seerr_search_media: Search for movies and TV shows available on Seerr. Acceptsqueryand optionalpage(default 1).seerr_get_available_libraries: Get the configured Sonarr (TV) and Radarr (Movie) server IDs and names from Seerr.seerr_get_users: Get a list of all users configured in Seerr, including their ID, username, email, displayName, etc.
Example prompts
It's good to first instruct your AI assistant (e.g., Claude) to use the Seerr tools. Then it can call the appropriate tool when needed.
Try prompts like these:
- Get the status of our Seerr server.
- Show me the first 5 movie requests that are currently pending.
- List all TV show requests from 2024-01-01 that are now available.
- What movies have been requested but are not available yet?
- What TV shows have recently become available in our library?
- Search for the movie "Dune: Part Two" on Seerr.
- What movie and TV libraries are configured in Seerr?
- List all users in Seerr.
- Request the movie with TMDB ID 693134 for the user 'John Doe' in the 'Movies HD' library. (Uses
user_display_name='John Doe',library_name='Movies HD') - Request seasons 1 and 2 for the TV show with TMDB ID 1396 for user 'Jane Smith' in the 'TV Shows 4K' library. (Uses
user_display_name='Jane Smith')
Quickstart
Prerequisites
uv(installation instructions: https://github.com/astral-sh/uv)- An Seerr instance running.
- API Key from your Seerr instance (Settings → API Keys).
Run with uvx (Recommended - No Installation Required)
You can run the server directly from the git repository using uvx — no clone or install needed:
uvx --from git+https://github.com/ptbsare/seerr-mcp-server.git seerr-mcp-server
Claude Desktop Configuration
Add the following to your claude_desktop_config.json:
{
"mcpServers": {
"seerr-mcp-server": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/ptbsare/seerr-mcp-server.git",
"seerr-mcp-server"
],
"env": {
"SEERR_API_KEY": "<your_api_key_here>",
"SEERR_URL": "<your_seerr_url>"
}
}
}
}
Replace <your_api_key_here> and <your_seerr_url> with your actual Seerr API key and URL.
Environment Variables
The following environment variables are required:
SEERR_API_KEY: Your Seerr API key (found in Seerr Settings → API Keys)SEERR_URL: The URL of your Seerr instance (e.g.,http://localhost:5055)
For clients like Claude Desktop, add these to the env field as shown above. For local use, you can export them or use a .env file:
SEERR_API_KEY=your_api_key_here
SEERR_URL=http://localhost:5055
Local Development Installation
If you prefer to install locally for development:
git clone https://github.com/ptbsare/seerr-mcp-server.git
cd seerr-mcp-server
uv venv
source .venv/bin/activate # On Windows use `.venv\Scripts\activate`
uv pip install -e .
Development
Setup
Follow the installation steps using uv pip install -e . for an editable install.
Dependencies
Install or sync dependencies using uv:
uv sync
# or
uv pip install -e .
Debugging
Since MCP servers run over stdio, debugging can be challenging.
-
MCP Inspector: The MCP Inspector is highly recommended.
Launch it pointing to your server script:
# Using uvx (no local installation needed) npx @modelcontextprotocol/inspector uvx --from git+https://github.com/ptbsare/seerr-mcp-server.git seerr-mcp-server # Or using uv run (from local project directory) npx @modelcontextprotocol/inspector uv run seerr-mcp-serverAccess the URL provided by the Inspector in your browser.
-
Logging: The server logs basic information to stdout/stderr. Check the terminal where you ran
uv run seerr-mcp-server. For clients like Claude Desktop, check the client's log files (e.g.,~/Library/Logs/Claude/mcp-server-seerr-mcp.logon macOS, but the name might vary based on your config).
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.