Skip to main content
Glama
musantro

iRacing MCP

by musantro
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

iRacing MCP

iRacing MCP is a Python-based project that integrates iRacing with the Model Context Protocol (MCP). It provides tools and resources to interact with iRacing data and build custom applications.

Features

  • Retrieve iRacing profile statistics.

  • Get iRating chart (for any category)

  • More coming soon

Related MCP server: Formula1 MCP Server

Getting Started

Prerequisites

Usage

Running the Server Standalone

To start the MCP server, run:

IRACING_USERNAME="your username" IRACING_PASSWORD="your-password" uvx iracing-mcp

Running the Server on VSCode

Add this to your settings.json (in mcp.servers):

"iracing": {
    "command": "uvx",
    "args": [
        "iracing-mcp@latest"
    ],
    "env": {
        "IRACING_USERNAME": "your@email.com",
        "IRACING_PASSWORD": "your password"
    }
}

Running the MCP Server on Claude Desktop

Add this to your settings.json:

[
    "mcpServers": {
        "iracing": {
            "command": "uvx",
            "args": [
                "iracing-mcp@latest"
            ],
            "env": {
                "IRACING_USERNAME": "your@email.com",
                "IRACING_PASSWORD": "your-password"
            }
        }
    }
}

Running the Server on other MCP Clients

Currently I am only using VS Code as MCP Client so I don't know how to configure to other MCP Clients. I am happy to receive PRs on how to configure in the different MCP Servers (e.g. Cursor, Claude Desktop, etc.)

Development

  1. Clone the repository:

    git clone https://github.com/musantro/iracing-mcp.git
cd iracing-mcp

  2. Create environment with dependencies:

    uv sync

  3. Set up environment variables for iRacing credentials:

    export IRACING_USERNAME="your_username"
export IRACING_PASSWORD="your_password"

Linting and Formatting

Use the following commands to lint and format the code:

make

Contributing

We welcome contributions! Follow these steps to contribute:

  1. Fork the repository.

  2. Create a new branch for your feature or bugfix.

  3. Push your branch.

  4. Open a pull request.

License

This project is licensed under the MIT License. See the LICENSE file for details.

Available Tools

2 tools
get_iracing_profile_statsA

Get the current iRacing profile statistics.

Retrieves the user's iRacing profile information including license level, iRating, and other career stats.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A3.5/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden. It discloses that the tool retrieves data but not behavioral traits like authentication needs, rate limits, data freshness, or whether it's a read-only operation. This leaves key behavioral information missing.

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

Conciseness5/5

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

Two short sentences, front-loaded with the core action. Every word adds value; no extraneous content.

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

Completeness3/5

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

The tool has no parameters and no output schema, so the description must specify return values. It mentions license, iRating, and career stats but does not list specific fields or structure. For a simple profile retrieval, this is adequate but not fully complete.

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

Parameters4/5

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

The input schema has zero parameters, so the baseline is 4 per rules. The description does not add parameter-level detail because none exist, but it correctly implies no arguments are needed.

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

Purpose5/5

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

The description clearly states the verb 'Get' and the resource 'iRacing profile statistics', and lists the types of data (license level, iRating, career stats). The sibling tool get_irating_chart suggests a different focus (charts), so the distinction is implicit.

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?

No guidance on when to use this tool versus the sibling get_irating_chart or any prerequisites. The description only states what it does without contextual usage advice.

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

get_irating_chartA

Get the iRating data for a specific license category.

Retrieves the user's iRating history data for the specified racing category. This includes historical iRating values that can be used for charting.

1 is oval, 2 is road, 3 is dirt oval, 4 is dirt road, 5 is sports car, and 6 is formula car.

ParametersJSON Schema
NameRequiredDescriptionDefault
categoryYes

TDQS

A3.8/5.0
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 only states it retrieves iRating history data but does not mention whether it is read-only, any rate limits, data range, or what happens if the category is invalid. This lack of transparency for a simple retrieval tool is a notable gap.

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 four sentences: the first two state the purpose, the third adds charting context, and the fourth lists the category mapping. It is front-loaded and each sentence provides useful information without redundancy. Slightly verbose due to repetition between sentence 1 and 2, but still concise overall.

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

Completeness3/5

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

Given the simplicity of the tool (one parameter, no output schema), the description is adequately complete for basic usage. It explains what the tool does and what the parameter means. However, it does not describe the format or structure of the returned data, which would be helpful for charting without an output schema. A bit more detail on the return type (e.g., array of {date, irating} objects) would increase completeness.

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

Parameters4/5

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

The input schema has 0% description coverage, so the description must compensate. It does so by explicitly mapping integer values to category names (e.g., '1 is oval'), which adds significant meaning beyond the schema's bare type 'integer'. This allows the agent to correctly select the category. However, it could also mention that the parameter is required and that it corresponds to a license category.

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

Purpose5/5

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

The description clearly states 'Get the iRating data for a specific license category' and 'Retrieves the user's iRating history data', specifying both the verb and the resource. It distinguishes itself from the sibling tool 'get_iracing_profile_stats' by focusing on historical data for charting, implying a different use case (history vs. profile stats).

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

Usage Guidelines4/5

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

The description explains the tool is for retrieving historical iRating values 'for charting', which gives a clear use context. It also provides the mapping of category IDs (1-6), which serves as a usage guideline. However, it does not explicitly state when not to use this tool or compare it directly with the sibling, though the context is strong enough.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updatesv0.1.0
    • First observedget_iracing_profile_stats
    • First observedget_irating_chart
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.5/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: one retrieves general profile statistics, the other provides historical iRating data for a specific category. There is no ambiguity between them.

Naming Consistency5/5

Both tools follow a consistent verb_noun pattern using snake_case and the 'get_iracing_' prefix, making them predictable and easy to understand.

Tool Count2/5

With only 2 tools, the server is severely under-scoped for the iRacing domain, which typically requires many more tools for operations like searching races, managing subscriptions, or accessing car/track data.

Completeness1/5

The tool surface is extremely limited, covering only profile stats and iRating history. Critical operations like race listing, car/track data, league management, and session results are entirely missing, making it incomplete for practical use.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Formula One MCP Server

    rakeshgangwar
    A
    license
    B
    quality
    D
    maintenance
    Provides Formula One data and statistics through a Model Context Protocol interface, allowing users to access race calendars, session results, driver statistics, telemetry data, and championship standings.
    8
    11
    MIT

  • Formula1 MCP Server

    Panth1823
    A
    license
    Not graded
    quality
    D
    maintenance
    Provides real-time and historical Formula 1 racing data through the Model Context Protocol, offering access to timing data, driver stats, race results, telemetry, and more.
    15
    MIT

  • Formula One MCP Server

    notsedano
    A
    license
    A
    quality
    D
    maintenance
    A Model Context Protocol server that provides comprehensive Formula One racing data, enabling access to event schedules, driver information, telemetry data, race results, and performance analytics through natural language queries.
    8
    1
    MIT