Skip to main content
Glama
GitHub Models Helper

GitHub Models Helper

by bvm-arjun108

MCP TypeScript GitHub Models Helper

TypeScript MCP server that integrates with GitHub Models to list available models and compare responses across models for the same prompt. This README includes full requirements, project description, build steps, and testing flow.

Project requirements

  • Node.js 18+

  • GitHub account with access to GitHub Models

  • GitHub Personal Access Token (PAT) with GitHub Models access

  • MCP Inspector (runs via npx)

Related MCP server: Model Hub MCP

Project description

This server exposes three MCP primitives:

  • Resource: models://available (lists available models)

  • Tool: compare_models (compares model responses to the same prompt)

  • Prompt: compare_models_prompt (builds a reusable comparison prompt)

Project structure

mcp-typescript-github-models-helper/
  src/
    githubModels.ts
    index.ts
  .env.template
  .gitignore
  package.json
  tsconfig.json

Step-by-step setup

  1. Install dependencies

npm install
  1. Create .env from the template

cp .env.template .env
  1. Add your GitHub Models token

GITHUB_TOKEN=your_github_token_here

Optional: override the API base URL in .env:

GITHUB_MODELS_API_BASE=https://models.inference.ai.azure.com

Step-by-step implementation (what the code does)

  1. src/githubModels.ts

    • Fetches available models with GET /models

    • Compares models with POST /chat/completions

    • Uses GITHUB_TOKEN from .env

  2. src/index.ts

    • Creates the MCP server

    • Registers the models://available resource

    • Registers the compare_models tool

    • Registers the compare_models_prompt prompt

    • Connects to STDIO transport

Run (development)

npm run dev

Build and run (production-style)

npm run build
npm start

Step-by-step testing with MCP Inspector

  1. Build the server

npm run build
  1. Start the Inspector

npx @modelcontextprotocol/inspector node dist/index.js
  1. Open the URL printed by the Inspector and click Connect

  2. Test resources

    • Resources tab -> models://available

  3. Test tools

    • Tools tab -> compare_models

  4. Test prompts

    • Prompts tab -> compare_models_prompt

Claude Desktop configuration

Add this to your claude_desktop_config.json and update the paths:

{
  "mcpServers": {
    "GitHub Models Comparison": {
      "command": "node",
      "args": [
        "/absolute/path/to/mcp-typescript-github-models-helper/dist/index.js"
      ],
      "env": {
        "GITHUB_TOKEN": "your_github_personal_access_token"
      }
    }
  }
}

Note: This is not secure for production. Use proper secrets management and authentication when publishing MCP servers.

Troubleshooting

  • Cannot find name 'process': run npm install --save-dev @types/node.

  • 401/403 from GitHub Models: verify the PAT has GitHub Models access.

  • Inspector connection errors: rebuild and re-run npx @modelcontextprotocol/inspector node dist/index.js.

Available Tools

1 tool
compare_modelsB

Compare responses from different models for the same prompt

Inputs: prompt (required), models.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 1 tool

    Disambiguation5/5

    With only one tool, there is no ambiguity or overlap with other tools. The purpose of comparing models is clearly described.

    Naming Consistency5/5

    The tool name follows a standard verb_noun pattern ('compare_models'). With a single tool, there is no inconsistency to evaluate.

    Tool Count2/5

    A single tool feels too few for a server named 'GitHub Models Helper', which implies a broader set of utilities. The scope appears overly narrow.

    Completeness2/5

    The server only provides a model comparison tool, leaving obvious gaps such as listing available models or retrieving model details. This significantly limits helper functionality.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      An MCP server that allows agents to test and compare LLM prompts across OpenAI and Anthropic models, supporting single tests, side-by-side comparisons, and multi-turn conversations.
      MIT
    • A
      license
      B
      quality
      D
      maintenance
      An MCP server that retrieves and provides AI model information from OpenAI, Anthropic, and Google through a unified interface.
      3
      60 npm
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      An MCP server that enables users to query, compare, and synthesize responses from multiple local and cloud LLMs simultaneously using existing subscriptions. It provides tools for parallel model evaluation, consensus polling with an LLM-as-judge, and response synthesis across different model providers.
      8
      33 npm
      15
      MIT
    • F
      license
      A
      quality
      D
      maintenance
      An MCP server for discovering and querying over 300 AI models available on OpenRouter. It enables users to list, search, filter, compare, and get detailed information about models with pricing, context limits, and capabilities.
      5
      1
      -