IMDb MCP Server

Verified on MCP Review

A Python server implementing Model Context Protocol (MCP) for movie and TV show information using the IMDb API service.

Table of Contents

• Overview
• Features
• Requirements
• Configuration
• Tools
  • Search Tools
  • IMDb ID Tools
  • Configuration Tools
  • Movies Tools
  • TV Shows Tools
  • Upcoming Releases Tools
  • India Spotlight Tools
• Example Prompt and Response
• Installation
• Starting the Server
• Technical Details
  • Transport Modes
  • Pagination System
  • Caching System
• Limitations
• Troubleshooting
• License

Overview

This server provides a comprehensive set of tools for accessing IMDb data through the IMDb API. It serves as a bridge between agents and the IMDb database, offering detailed information about movies, TV shows, actors, directors, and more.

Features

• 🎬 Movie and TV show search capabilities
• 📋 Detailed information about movies and TV shows
• 👨‍👩‍👧‍👦 Cast and crew information
• 🏆 Top-rated and popular content lists
• 💰 Box office data
• 🌍 Country-specific movie information (with special focus on Indian cinema)
• 🔜 Upcoming releases
• 🔄 Efficient response caching system

Requirements

• Python: 3.13 or higher
• Package Manager: uv (recommended) or pip
• RapidAPI Account: Required for IMDb API access

Configuration

This server requires an API key from RapidAPI for the IMDb API service:

1. Create an account on RapidAPI

2. Subscribe to the IMDb API on RapidAPI

3. Configure the API key using one of these methods:

   Method 1: Smithery Configuration (for HTTP mode)

   • When installing via Smithery, provide your API key through the Smithery configuration system
   • The key is passed per-request, allowing for multi-user scenarios

   Method 2: Environment Variable (for stdio mode)

   export RAPID_API_KEY_IMDB=your_api_key_here

Tools

Search Tools

Tool	Description	Example
search_imdb	Search for movies and TV shows with various filtering options	search_imdb(primary_title="Inception")

IMDb ID Tools

Tool	Description	Example
get_imdb_details	Retrieve detailed information about a movie or TV show	get_imdb_details(imdb_id="tt1375666")
get_directors	Retrieve the directors of a movie	get_directors(imdb_id="tt1375666")
get_cast	Retrieve the cast of a movie	get_cast(imdb_id="tt1375666")
get_writers	Retrieve the writers of a movie	get_writers(imdb_id="tt1375666")

Configuration Tools

Tool	Description	Example
get_types	Get all available content types	get_types()
get_genres	Get all available genres	get_genres()
get_countries	Get all available countries	get_countries()
get_languages	Get all available languages	get_languages()

Movies Tools

Paginated (5 results per page)

Tool	Description	Example
get_top_250_movies	Get the top 250 movies from IMDb	get_top_250_movies(start=0)
get_top_box_office_us	Get the US box office records	get_top_box_office_us(start=0)
get_most_popular_movies	Get the most popular movies	get_most_popular_movies(start=0)

TV Shows Tools

Paginated (5 results per page)

Tool	Description	Example
get_top_250_tv_shows	Get the top 250 TV shows from IMDb	get_top_250_tv_shows(start=0)
get_most_popular_tv_shows	Get the most popular TV shows	get_most_popular_tv_shows(start=0)

Upcoming Releases Tools

Paginated (5 results per page)

Tool	Description	Example
get_upcoming_releases	Get upcoming movie and TV show releases by country	get_upcoming_releases(country_code="US", type="MOVIE", start=0)
get_country_codes_for_upcoming_releases	Get available country codes for upcoming releases	get_country_codes_for_upcoming_releases()

India Spotlight Tools

Paginated (5 results per page)

Tool	Description	Example
get_top_rated_malayalam_movies	Get top 50 rated Malayalam movies	get_top_rated_malayalam_movies(start=0)
get_upcoming_indian_movies	Get most anticipated upcoming Indian movies	get_upcoming_indian_movies(start=0)
get_trending_tamil_movies	Get trending Tamil movies	get_trending_tamil_movies(start=0)
get_trending_telugu_movies	Get trending Telugu movies	get_trending_telugu_movies(start=0)
get_top_rated_tamil_movies	Get top 50 rated Tamil movies	get_top_rated_tamil_movies(start=0)
get_top_rated_telugu_movies	Get top 50 rated Telugu movies	get_top_rated_telugu_movies(start=0)
get_top_rated_indian_movies	Get top 250 rated Indian movies	get_top_rated_indian_movies(start=0)

Example Prompt and Response

What are the 5 action movies that will be released in the nearest future?

I'll find the upcoming action movies for you.

Called MCP tool get_upcoming_releases

Now I'll look for the action movies from these upcoming releases:

Called MCP tool get_upcoming_releases

Based on the search results, here are the 5 upcoming action movies that will be released in the nearest future:

1. A Minecraft Movie (April 4, 2025)

   • Genres: Action, Adventure, Comedy
   • Description: Four misfits are pulled through a portal into a cubic wonderland and embark on a quest with an expert crafter to get back home.

2. Freaky Tales (April 4, 2025)

   • Genres: Action, Adventure, Comedy
   • Description: Four interconnected stories set in 1987 Oakland, CA about the love of music, movies, people, places and memories.

3. Wake Up (April 4, 2025)

   • Genres: Action, Horror
   • Description: Young activists invade a furniture store to protest environmental issues but find themselves trapped with a hunting-obsessed night guard.

4. Warfare (April 11, 2025)

   • Genres: Action, Drama, War
   • Description: Based on ex-Navy Seal Ray Mendoza's real-life experiences during the Iraq War.

5. The Amateur (April 11, 2025)

   • Genres: Action, Thriller
   • Description: A CIA cryptographer blackmails his agency into training him to pursue terrorists who killed his wife.

Installation

Installing via Smithery (Recommended)

To install IMDb Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @uzaysozen/imdb-mcp-server --client claude

This will automatically configure the server with your RapidAPI key through Smithery's configuration system.

Option 1: Using Docker

1. Clone this repository

git clone https://github.com/uzaysozen/imdb-mcp-server.git
cd imdb-mcp-server

1. Build the Docker image

docker build -t imdb_server .

1. Run the Docker container

docker run -d -p 8081:8081 -e RAPID_API_KEY_IMDB=your_api_key_here --name imdb_server imdb_server

Note: The Docker container runs in HTTP mode by default on port 8081.

Option 2: Direct Python Execution (using uv)

1. Clone this repository

git clone https://github.com/uzaysozen/imdb-mcp-server.git
cd imdb-mcp-server

1. Install uv (if not already installed)

# On macOS and Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# On Windows
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"

1. Install dependencies using uv

uv sync

1. Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "imdb_server": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/imdb-mcp-server",
        "run",
        "imdb-server"
      ],
      "env": {
        "RAPID_API_KEY_IMDB": "your_api_key_here"
      }
    }
  }
}

Starting the Server

Stdio Mode (Default for local development)

# Using uv (recommended)
uv run imdb-server

# Or directly with Python module
python -m imdb_mcp_server

HTTP Mode (Used by Docker and Smithery)

# Using uv
TRANSPORT=http uv run imdb-server

# Or with Python module
TRANSPORT=http python -m imdb_mcp_server

# With custom port
TRANSPORT=http PORT=8081 uv run imdb-server

After adding your chosen configuration, restart Claude Desktop to load the IMDb server. You'll then be able to use all the movie and TV show data tools in your conversations with Claude.

Technical Details

The server is built on:

• Python 3.13+: Modern Python runtime
• FastMCP: Server implementation with HTTP and stdio transport support
• IMDb API via RapidAPI: Primary data source
• Requests: API communication library
• Smithery: Configuration and deployment management
• uv: Fast Python package manager and runner
• Custom in-memory caching system: Optimized response caching with LRU eviction
• Smart pagination: Limits results to 5 items per request, optimizing for AI agent consumption

Transport Modes

The server supports two transport modes:

1. Stdio Mode (Default): Traditional MCP server communication via standard input/output

   • Used for local Claude Desktop installations
   • Configured via environment variables (RAPID_API_KEY_IMDB)

2. HTTP Mode: RESTful HTTP transport with CORS support

   • Used for Docker deployments and Smithery
   • Supports per-request configuration via Smithery config system
   • Runs on port 8081 by default (configurable via PORT environment variable)

Pagination System

All data retrieval tools implement pagination to enhance AI agent performance:

Purpose

• AI-Optimized Responses: Limits each response to 5 items, preventing overwhelm in AI agents that process the data
• Focused Results: Helps agents provide more relevant and concise information to users
• Improved Processing: Reduces the cognitive load on AI agents when analyzing movie and TV show data

Implementation

• Each paginated endpoint accepts a start parameter (default: 0)
• Results include navigation metadata (totalCount, hasMore, nextStart)
• Consistent 5-item page size across all collection endpoints
• Example request with pagination: get_top_250_movies(start=5) returns items 6-10

Benefits

• Better Agent Responses: Prevents AI agents from receiving too much data at once
• Manageable Information: Creates digestible chunks of data that agents can process effectively
• Sequential Access: Allows structured exploration of large datasets through multiple tool calls

Caching System

The server implements an efficient caching system to improve performance and reduce API calls:

Features

• In-memory Cache: Stores API responses in memory for quick retrieval
• Configurable Expiration and Size: Cache entries expire after a customizable time period (default: 10 minutes) and have a default size of 100 cache keys
• Automatic Cache Cleaning: Periodically (default: 5 minutes) removes expired entries to manage memory usage using a background thread
• Cache Keys: Generated based on the URL and query parameters to ensure uniqueness

Benefits

• Reduced API Usage: Helps stay within API rate limits by reusing responses
• Faster Response Times: Eliminates network latency for cached queries
• Cost Efficiency: Minimizes the number of API calls, especially for popular or repeated queries

Configuration

The cache size and expiration time can be adjusted in src/main.py:

# Defaults: 600 seconds (10 minutes) and 100 cache keys
# You can customize by modifying the ResponseCache instantiation:
response_cache = ResponseCache(max_size=100, expiry_seconds=600)

# Example with custom values:
# response_cache = ResponseCache(max_size=50, expiry_seconds=120)

Limitations

• API rate limits apply based on your RapidAPI subscription
• Some detailed information may require additional API calls
• Search results may be limited to a certain number of items per request
• In-memory cache is lost when server restarts
• All paginated responses return a maximum of 5 items per page

Troubleshooting

Problem	Solution
API key not recognized	Stdio mode: Ensure the RAPID_API_KEY_IMDB environment variable is properly set. HTTP mode: Verify the rapidApiKeyImdb is provided in the Smithery configuration
Rate limit exceeded	Check your RapidAPI subscription tier and limits at RapidAPI Dashboard
Timeout errors	The server has a 30-second timeout; for large requests, try limiting parameters or using pagination
Empty results	Try broader search terms or check if the content exists in IMDb's database
High memory usage	If running for extended periods with many unique queries, restart the server occasionally to clear the cache
Port already in use	Change the port using the PORT environment variable (HTTP mode only): PORT=8082 python src/main.py
Import errors	Ensure all dependencies are installed: uv sync or pip install mcp[cli] requests smithery
Connection refused (Docker)	Ensure the container is running: docker ps and check the logs: docker logs imdb_server

License

This MCP server is available under the MIT License.