Skip to main content
Glama
WillianPaiva

Copilot MCP Server

by WillianPaiva
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

Copilot MCP Server

A Model Context Protocol (MCP) server that integrates with GitHub Copilot to provide AI-powered code assistance directly to Claude Code and other MCP-compatible tools.

Features

  • Chat with Copilot: Get general programming assistance using GitHub Copilot's AI models

  • Code Explanation: Detailed explanations of code snippets

  • Code Suggestions: Generate code based on natural language descriptions

  • Code Review: Get feedback and improvement suggestions for your code

  • Multiple AI Models: Support for GPT-4o, Claude 3.5 Sonnet, and Gemini 2.0 Flash

  • Rate Limiting: Built-in rate limiting to respect API limits

  • Automatic Authentication: Works with your existing GitHub Copilot CLI setup

Related MCP server: copilot-mcp-server

Installation

Option 1: Using npx (Recommended)

npx @willianpaiva/copilot-mcp-server

Option 2: Manual Installation

  1. Clone this repository:

git clone https://github.com/WillianPaiva/copilot-mcp.git
cd copilot-mcp

  1. Install dependencies:

npm install

  1. Build the project:

npm run build

Configuration

No Configuration Needed!

The server works out of the box with your existing GitHub Copilot authentication.

Optional Configuration

Only needed for special use cases. Create a .env file:

cp .env.example .env

Optional settings:

# Only if you want to override the detected organization
GITHUB_ORG=your_organization_name

# Optional debugging
LOG_LEVEL=info
DEBUG=false
MAX_REQUESTS_PER_MINUTE=60

Setup Requirements

Prerequisites:

  1. GitHub Copilot Subscription: You need an active GitHub Copilot subscription

  2. GitHub Copilot CLI Installed: Install and authenticate GitHub Copilot CLI:

    # Install GitHub CLI first
brew install gh  # or your preferred method

# Install GitHub Copilot CLI extension
gh extension install github/gh-copilot

# Authenticate (this will save tokens to ~/.config/github-copilot/)
gh auth login

Authentication

Automatic Authentication (Recommended)

The MCP server automatically detects your GitHub Copilot authentication from:

  1. ~/.config/github-copilot/hosts.json

  2. ~/.config/github-copilot/apps.json

No manual configuration needed if you have GitHub Copilot CLI installed and authenticated!

Troubleshooting Authentication

If automatic detection fails, ensure you have GitHub Copilot CLI properly installed and authenticated:

gh extension install github/gh-copilot
gh auth login

Usage

With Claude Code

Add the following to your Claude Code MCP configuration:

Option 1: Using npx (Recommended)

{
  "mcpServers": {
    "copilot": {
      "command": "npx",
      "args": ["-y", "@willianpaiva/copilot-mcp-server"]
    }
  }
}

Option 2: Manual Installation

{
  "mcpServers": {
    "copilot": {
      "command": "node",
      "args": ["/path/to/your/copilot-mcp/build/index.js"]
    }
  }
}

That's it! No tokens or environment variables needed - the server automatically uses your existing GitHub Copilot authentication.

Available Tools

copilot_chat

General programming assistance and questions.

// Example usage in Claude Code
copilot_chat({
  message: "How do I implement a binary search algorithm?",
  model: "gpt-4o",
  context: "I'm working on a JavaScript project"
})

copilot_explain

Get detailed explanations of code.

copilot_explain({
  code: "function fibonacci(n) { return n <= 1 ? n : fibonacci(n-1) + fibonacci(n-2); }",
  language: "javascript"
})

copilot_suggest

Generate code from natural language descriptions.

copilot_suggest({
  prompt: "Create a React component for a user profile card",
  language: "javascript",
  maxSuggestions: 3
})

copilot_review

Get code review and improvement suggestions.

copilot_review({
  code: "your code here",
  language: "python",
  reviewType: "security"
})

Available Resources

copilot://models

List of available AI models and their capabilities.

copilot://usage

Current usage statistics and rate limiting information.

Development

Run in Development Mode

npm run dev

Build

npm run build

Lint

npm run lint

Test

npm test

Rate Limiting

The server implements rate limiting to respect GitHub's API limits:

  • Default: 60 requests per minute

  • Configurable via MAX_REQUESTS_PER_MINUTE environment variable

  • Automatic reset every minute

Error Handling

The server includes comprehensive error handling for:

  • Authentication failures

  • Rate limit exceeded

  • Network issues

  • Invalid requests

  • API unavailability

Troubleshooting

Common Issues

  1. Authentication Failed

    • Ensure GitHub Copilot CLI is installed: gh extension install github/gh-copilot

    • Make sure you're authenticated: gh auth login

    • Verify you have access to GitHub Copilot

  2. Rate Limit Exceeded

    • Wait for the rate limit to reset (1 minute)

    • Consider reducing the frequency of requests

  3. API Not Available

    • Verify you have access to GitHub Copilot

    • Check GitHub's status page for outages

Debug Mode

Enable debug mode for verbose logging:

DEBUG=true
LOG_LEVEL=debug

Contributing

  1. Fork the repository

  2. Create a feature branch

  3. Make your changes

  4. Add tests if applicable

  5. Submit a pull request

License

MIT License - see LICENSE file for details.

Security

  • The server uses your existing GitHub Copilot authentication

  • No tokens are stored or transmitted by this application

  • Authentication files are read-only from GitHub CLI's standard locations

  • Follow GitHub's security best practices for your main GitHub authentication

Support

For issues and questions:

  1. Check the troubleshooting section

  2. Search existing GitHub issues

  3. Create a new issue with detailed information

Available Tools

4 tools
copilot_chatC

Chat with GitHub Copilot AI models for general programming assistance

ParametersJSON Schema
NameRequiredDescriptionDefault
messageYesYour message or question for Copilot
contextNoOptional context to provide (e.g., current code, file contents)
modelNoAI model to use (optional)
temperatureNoResponse creativity (0=focused, 2=creative)

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 carries the full burden of behavioral disclosure. It states the tool 'Chats with GitHub Copilot AI models' but doesn't mention any behavioral traits such as rate limits, authentication requirements, response formats, or potential side effects (e.g., whether it's read-only or can modify data). This is a significant gap for a tool with no annotation coverage.

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?

The description is a single, efficient sentence that front-loads the core purpose ('Chat with GitHub Copilot AI models') and adds a clarifying phrase ('for general programming assistance'). There is no wasted wording, making it highly concise and well-structured.

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 complexity of an AI chat tool with 4 parameters, no annotations, and no output schema, the description is incomplete. It lacks details on behavioral traits (e.g., how responses are formatted, any limitations), doesn't differentiate from siblings, and provides minimal context beyond the basic purpose, leaving gaps for effective tool selection and invocation.

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?

Schema description coverage is 100%, so the schema fully documents all parameters (message, context, model, temperature). The description adds no parameter-specific information beyond what's in the schema, such as examples or usage tips. The baseline score of 3 reflects adequate coverage by the schema alone.

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 verb ('Chat with') and resource ('GitHub Copilot AI models'), specifying it's for 'general programming assistance'. However, it doesn't distinguish this from sibling tools like copilot_explain, copilot_review, or copilot_suggest, which likely serve more specific programming assistance purposes.

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 its siblings (copilot_explain, copilot_review, copilot_suggest). It mentions 'general programming assistance' but doesn't clarify what constitutes 'general' versus the more specialized purposes implied by the sibling names, leaving the agent to guess about appropriate contexts.

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

copilot_explainC

Get detailed explanations of code from GitHub Copilot

ParametersJSON Schema
NameRequiredDescriptionDefault
codeYesCode to explain
languageNoProgramming language (auto-detected if not provided)
contextNoAdditional context about the code

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool 'gets' explanations, implying a read-only operation, but doesn't cover aspects like rate limits, authentication needs, response format, or potential errors. This leaves significant gaps in understanding how the tool behaves in practice.

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?

The description is a single, clear sentence with zero waste—it directly states the tool's purpose without unnecessary elaboration. It's appropriately sized and front-loaded, making it easy for an agent to parse quickly.

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 complexity of explaining code and the lack of annotations and output schema, the description is insufficient. It doesn't address what the explanations include, how they're formatted, or any limitations, leaving the agent with incomplete context for effective tool invocation.

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 schema description coverage is 100%, meaning all parameters are documented in the schema. The description adds no additional meaning beyond what's in the schema (e.g., it doesn't clarify what 'detailed explanations' entail or how context influences results). Baseline 3 is appropriate as the schema handles parameter documentation adequately.

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 action ('Get detailed explanations') and the resource ('code from GitHub Copilot'), making the purpose evident. However, it doesn't explicitly differentiate from sibling tools like copilot_chat or copilot_review, which might also involve explanations or discussions about code.

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 like copilot_chat or copilot_review. It lacks any mention of specific contexts, prerequisites, or exclusions, leaving the agent to infer usage based on tool names alone.

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

copilot_reviewC

Get code review and improvement suggestions from GitHub Copilot

ParametersJSON Schema
NameRequiredDescriptionDefault
codeYesCode to review
languageNoProgramming language
reviewTypeNoType of review to perform

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 carries the full burden of behavioral disclosure. It states the tool 'Get[s] code review and improvement suggestions,' which implies a read-only operation, but doesn't clarify if it modifies data, requires authentication, has rate limits, or what the output format is. For a tool with no annotations, this leaves significant behavioral gaps.

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?

The description is a single, clear sentence: 'Get code review and improvement suggestions from GitHub Copilot.' It's front-loaded with the core purpose, has zero waste, and is appropriately sized for the tool's complexity. Every word earns its place.

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 no annotations and no output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., structured feedback, suggestions list), potential errors, or behavioral traits like response format. For a tool with 3 parameters and no structured output, more context is needed to guide effective use.

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?

Schema description coverage is 100%, so the schema already documents all parameters (code, language, reviewType) with descriptions and constraints. The description adds no additional parameter semantics beyond what's in the schema, such as examples or usage tips. Baseline 3 is appropriate as the schema handles the heavy lifting.

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: 'Get code review and improvement suggestions from GitHub Copilot.' It specifies the verb ('Get') and resource ('code review and improvement suggestions'), and distinguishes it from siblings by focusing on review rather than chat, explanation, or suggestion. However, it doesn't explicitly differentiate from siblings like 'copilot_suggest' which might overlap in providing suggestions.

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 doesn't mention sibling tools (copilot_chat, copilot_explain, copilot_suggest) or specify scenarios where this review tool is preferred over others, such as for security checks versus general coding help. Usage is implied but not explicitly defined.

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

copilot_suggestC

Get code suggestions and completions from GitHub Copilot

ParametersJSON Schema
NameRequiredDescriptionDefault
promptYesDescription of what code you want to generate
languageNoTarget programming language
contextNoExisting code context or constraints
maxSuggestionsNoMaximum number of suggestions to return

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'suggestions and completions' but fails to detail critical aspects such as rate limits, authentication requirements, response format, or potential side effects. This is a significant gap for a tool interacting with an external AI service.

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?

The description is a single, efficient sentence that directly states the tool's function without unnecessary words. It is front-loaded and wastes no space, making it easy for an agent to parse quickly.

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 complexity of interacting with GitHub Copilot, no annotations, and no output schema, the description is insufficient. It lacks details on behavioral traits, error handling, and return values, leaving the agent with incomplete information for reliable tool invocation.

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 input schema has 100% description coverage, clearly documenting all four parameters. The description adds no additional meaning beyond the schema, such as examples or usage tips. However, since the schema is comprehensive, a baseline score of 3 is appropriate as the description doesn't need to compensate for gaps.

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 as 'Get code suggestions and completions from GitHub Copilot', specifying the action ('Get') and resource ('code suggestions and completions'). It distinguishes from sibling tools like copilot_chat, copilot_explain, and copilot_review by focusing on generation rather than conversation, explanation, or review, though it doesn't explicitly contrast them.

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 like copilot_chat or copilot_explain. It lacks context about specific scenarios, prerequisites, or exclusions, leaving the agent to infer usage based on the name and purpose alone.

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

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3/5.0
Disambiguation2/5

The tools have significant overlap in purpose, as all involve interacting with GitHub Copilot for code-related assistance. While the descriptions differentiate them slightly (e.g., 'chat' vs. 'suggest'), an agent could easily confuse them, especially since 'copilot_suggest' and 'copilot_chat' might both provide code suggestions. The boundaries are unclear, leading to potential misselection.

Naming Consistency5/5

All tool names follow a consistent 'copilot_' prefix with a descriptive suffix (chat, explain, review, suggest). This verb_noun-like pattern is predictable and readable, making it easy for agents to understand the naming convention without confusion or deviation.

Tool Count3/5

With 4 tools, the count is borderline for a server focused on GitHub Copilot interactions. It feels slightly thin, as it might lack coverage for other potential Copilot functionalities (e.g., debugging or documentation generation), but it's reasonable for basic assistance. However, the overlap in tools reduces the effective utility of having four distinct tools.

Completeness3/5

The tool surface covers key aspects of GitHub Copilot (chat, explanation, review, suggestions), but there are notable gaps. For example, it lacks tools for more advanced operations like code refactoring, debugging assistance, or integration with specific programming languages. While agents can work around this, the surface is not fully comprehensive for a general programming assistance domain.

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

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/WillianPaiva/copilot-mcp'

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