Skip to main content
Glama
mchow01

Horse Racing News

by mchow01

Overview

MCP server to get content from thoroughbreddailynews.com's RSS feed

Requirements

Getting Started

Part 1: Running MCP Server

  1. Clone this repository

  2. cd horseracingnews

  3. Run uv run horse_racing_news_mcp_server.py and keep running.

Related MCP server: MyNews MCP Server

Part 2: Update Claude Desktop Configuration (assuming macOS)

  1. Run cd ~/Library/Application\ Support/Claude

  2. Use your favorite editor and open up claude_desktop_config.json (e.g., vim claude_desktop_config.json)

  3. Assuming you never added an MCP server to the configuration file before, add:

{
  "mcpServers": {
    "horseracing": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/horseracingnews",
        "run",
        "horse_racing_news_mcp_server.py"
      ]
    }
  }
}

Make sure to restart Claude Desktop

Source

Prompts Used

I was informed of Thoroughbred Daily News yesterday. They provide an RSS feed at https://www.thoroughbreddailynews.com/feed/.  Can you write a Python program that:

Loads the feed
Parse the XML
For each story, show the title, content, and link

Excellent, thanks so much! Now, can you turn it into an MCP server using FastMCP? Expose one method for @mcp.tool() named get_horse_racing_news.

Available Tools

1 tool
get_horse_racing_newsC

Fetch the latest horse racing news from Thoroughbred Daily News.

Args: limit: Maximum number of stories to return (default: 10, max: 50)

Returns: Dictionary containing feed information and list of news stories

ParametersJSON Schema
NameRequiredDescriptionDefault
limitNo

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must fully disclose behavioral traits. It states the tool fetches news, implying a read-only operation, but does not specify if it requires authentication, has rate limits, or details about the fetch mechanism (e.g., real-time vs. cached). The description adds minimal behavioral context beyond the basic action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized and front-loaded, starting with the core purpose. The Args and Returns sections are structured clearly, though the 'Returns' section is vague ('Dictionary containing feed information and list of news stories'). Overall, it avoids unnecessary verbosity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of annotations and output schema, the description is incomplete. It does not explain the structure of the returned dictionary, error handling, or any side effects. For a tool with no structured data support, more detail on behavior and outputs is needed to be fully informative.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds meaning for the single parameter 'limit' by explaining it controls the 'maximum number of stories to return' and provides default and max values. However, with 0% schema description coverage, the schema lacks descriptions, so the description compensates partially but does not fully detail parameter behavior or constraints beyond what's implied.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Fetch the latest horse racing news from Thoroughbred Daily News.' It specifies the verb ('fetch') and resource ('horse racing news'), and identifies the source. However, with no sibling tools, it cannot demonstrate differentiation from alternatives, preventing a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It does not mention any prerequisites, context for usage, or exclusions. The lack of sibling tools means no explicit comparisons are needed, but general usage context is still missing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

TDQS

B3.1/5.0
Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined and singular.

Naming Consistency5/5

Since there is only one tool, naming consistency is inherently perfect. The tool name follows a clear verb_noun pattern (get_horse_racing_news).

Tool Count2/5

A single tool is too few for a news server, as it only supports fetching news without any filtering, searching, or categorization capabilities. This limits functionality and feels thin for the domain.

Completeness2/5

The server is severely incomplete for a news domain. It lacks essential operations such as searching news by keyword, filtering by date or category, or accessing specific articles, which are common in news APIs.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to fetch categorized news headlines and full article text from a multi-topic RSS aggregator, with no API keys required.
    13
    ISC
  • A
    license
    Not graded
    quality
    C
    maintenance
    Provides curated international news feeds with tools to list, read, and fetch RSS/Atom/RDF feeds. Enables AI agents to access and filter world news data through natural language.
    16
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/mchow01/horseracingnews'

If you have feedback or need assistance with the MCP directory API, please join our Discord server