
Mistral Codestral MCP Server
Provides code completion, bug fixing, and test generation for multiple programming languages, integrating with the Mistral Codestral API to enhance code development processes.
bsmi021
README
Mistral Codestral MCP Server
An MCP server implementation for the Mistral Codestral API, providing code completion, bug fixing, and test generation capabilities.
Features
- Code completion with Mistral's Codestral model
- Bug detection and fixing
- Automated test generation
- Support for multiple programming languages
- Rate limiting and error handling
- Resource access for code files
- Fill-in-the-Middle (FIM) completion support
- Comprehensive input validation using Zod schemas
Installation
-
Clone this repository
-
Install dependencies:
npm install
-
Copy
.env.example
to.env
and add your Mistral API key:cp .env.example .env
-
Build the project:
npm run build
Usage
Start the server:
npm start
Configuration
Add your Mistral API key to the .env
file:
MISTRAL_API_KEY=your_api_key_here
Available Tools
code_completion
Process code for completion, bug fixing, or test generation:
Parameters:
code
(string, required): The code to processlanguage
(string, optional): Programming languagetask
(string, required): One of:"complete"
: Code completion"fix"
: Bug fixing"test"
: Test generation"fim"
: Fill-in-the-Middle completion
API Details
The server supports two main Mistral models:
codestral-latest
: Default model for code-related taskscodestral-mamba-latest
: Alternative model with Mamba architecture
Features include:
- Automatic rate limiting (100ms minimum between requests)
- 30-second timeout for API calls
- Comprehensive error handling for API responses
- Response validation using Zod schemas
- Automatic extraction of code blocks from responses
- Debug logging for API interactions
Development
Run in development mode with auto-reloading:
npm run dev
Run tests:
npm test
Error Handling
The server implements comprehensive error handling:
- API errors are properly caught and formatted
- Rate limiting is implemented
- Input validation using Zod schemas
- Proper error propagation to clients
- Specific error messages for common issues:
- Authentication failures
- Rate limit exceeded
- Server errors
- Invalid input validation
Resource Access
The server provides access to code files through the file://code
resource URI, allowing integration with workspace files.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
MCP Package Docs Server
Facilitates LLMs to efficiently access and fetch structured documentation for packages in Go, Python, and NPM, enhancing software development with multi-language support and performance optimization.
Claude Code MCP
An implementation of Claude Code as a Model Context Protocol server that enables using Claude's software engineering capabilities (code generation, editing, reviewing, and file operations) through the standardized MCP interface.
@kazuph/mcp-taskmanager
Model Context Protocol server for Task Management. This allows Claude Desktop (or any MCP client) to manage and execute tasks in a queue-based system.
Gitingest-MCP
An MCP server for gitingest. It allows MCP clients like Claude Desktop, Cursor, Cline etc to quickly extract information about Github repositories including repository summaries, project directory structure, file contents, etc
Linear MCP Server
Enables interaction with Linear's API for managing issues, teams, and projects programmatically through the Model Context Protocol.
mermaid-mcp-server
A Model Context Protocol (MCP) server that converts Mermaid diagrams to PNG images.
Jira-Context-MCP
MCP server to provide Jira Tickets information to AI coding agents like Cursor

Linear MCP Server
A Model Context Protocol server that integrates with Linear's issue tracking system, allowing LLMs to create, update, search, and comment on Linear issues through natural language interactions.