Go to the "..." (usually Data or Load Sample Data) tab.

Click "Load Sample Dataset" and select sample_mflix. This will automatically import the necessary data.

If you're using a local MongoDB instance: You can download the sample_mflix dataset from MongoDB's official resources (e.g., as part of the MongoDB University course materials or directly from their sample data repositories) and import it using mongoimport.

Installation

Clone the repository:

git clone https://github.com/patw/movie-mcp.git
cd movie-mcp

Install dependencies:

pip install -r requirements.txt

Usage

The script expects the MongoDB connection URI as a command-line argument.

Run the script:

python movie_tools.py "mongodb://localhost:27017/"

Or, if using a MongoDB Atlas connection string:

python movie_tools.py "mongodb+srv://user:pass@clusterdomain/?retryWrites=true&w=majority"

Replace user, pass and clusterdomain with your actual MongoDB Atlas credentials and cluster details.

FastMCP Server: Once running, the script will start a fastmcp server. This server exposes the defined tools (e.g., find_movies, count_movies) over a local HTTP endpoint (by default http://127.0.0.1:8000/tools). You can then interact with these tools programmatically, typically from an LLM agent or another Python script.

Example of how an LLM or another program might call these tools (conceptually):

# This is pseudo-code representing how an LLM agent might interact
# In a real scenario, you'd use a client library for fastmcp or direct HTTP requests.

# Example: Find movies by Bill Murray
tool_call = {
"tool_name": "find_movies",
"args": {
"actors": ["Bill Murray"],
"limit": 5,
"projection_fields": ["title", "year", "imdb.rating"]
}
}
# result = make_tool_call(tool_call)
# print(result)

# Example: Count romantic comedies from the 90s
tool_call = {
"tool_name": "count_movies",
"args": {
"genres": ["Comedy", "Romance"],
"start_year": 1990,
"end_year": 1999
}
}
# result = make_tool_call(tool_call)
# print(result)

FastMCP Tools

This section details the functions exposed as tools by fastmcp.

`find_movies`

Finds movies based on a variety of criteria, with options for sorting and limiting results.

def find_movies(
title: Optional[str] = None,
genres: Optional[Union[List[str], str]] = None,
actors: Optional[Union[List[str], str]] = None,
directors: Optional[Union[List[str], str]] = None,
writers: Optional[Union[List[str], str]] = None,
year: Optional[int] = None,
start_year: Optional[int] = None,
end_year: Optional[int] = None,
min_imdb_rating: Optional[float] = None,
min_metacritic_rating: Optional[int] = None,
min_tomatoes_viewer_rating: Optional[float] = None,
min_tomatoes_critic_rating: Optional[float] = None,
rated_mpaa: Optional[str] = None,
sort_by: Optional[str] = "imdb.rating",
sort_order_asc: bool = False,
limit: int = 10,
projection_fields: Optional[List[str]] = None
) -> List[Dict[str, Any]]:

Args:

title (str, optional): Movie title (case-insensitive partial match).
genres (List[str] or str, optional): List of genres; movie must ma

Categories

Current Category: mongodb-atlas

movie-mcp-simple

movie-mcp