Typesense MCP Server

Instructions

Retrieves the schema and metadata for a specific collection.

Args:
    ctx (Context): The MCP context.
    collection_name (str): The name of the collection to describe.

Returns:
    dict | str: The collection schema dictionary or an error message string.

Implementation Reference

• main.py:142-167 (handler)

  This is the handler function for the 'describe_collection' tool. It is decorated with @mcp.tool() for registration and implements the logic to retrieve the schema and metadata of a Typesense collection by name, handling various errors.

  @mcp.tool()
  async def describe_collection(ctx: Context, collection_name: str) -> dict | str:
      """
      Retrieves the schema and metadata for a specific collection.
  
      Args:
          ctx (Context): The MCP context.
          collection_name (str): The name of the collection to describe.
  
      Returns:
          dict | str: The collection schema dictionary or an error message string.
      """
      if not collection_name:
          return "Error: collection_name parameter is required."
      try:
          client: typesense.Client = ctx.request_context.lifespan_context.client
          collection_info = client.collections[collection_name].retrieve()
          return collection_info
      except typesense.exceptions.ObjectNotFound:
          return f"Error: Collection '{collection_name}' not found."
      except typesense.exceptions.TypesenseClientError as e:
          print(f"Error describing collection '{collection_name}': {e}")
          return f"Error describing collection '{collection_name}': {e}"
      except Exception as e:
          print(f"An unexpected error occurred while describing collection '{collection_name}': {e}")
          return f"An unexpected error occurred: {e}"