A Model Context Protocol (MCP) server for providing code context from git repositories
What is fkesheh code context mcp
Code Context MCP Server
A Model Context Protocol (MCP) server for providing code context from local git repositories. This server allows you to:
- Clone git repositories locally
- Process branches and files
- Generate embeddings for code chunks
- Perform semantic search over code
Features
- Uses local git repositories instead of GitHub API
- Stores data in SQLite database
- Splits code into semantic chunks
- Generates embeddings for code chunks using Ollama
- Provides semantic search over code
Prerequisites
- Node.js (v16+)
- Git
- Ollama with an embedding model
Installation
# Clone the repository
git clone <repository-url>
cd code-context-mcp
# Install dependencies
npm install
# Build the project
npm run build
Configuration
Set the following environment variables:
DATA_DIR
: Directory for SQLite database (default: '~/.codeContextMcp/data')REPO_CACHE_DIR
: Directory for cloned repositories (default: '~/.codeContextMcp/repos')
Using Ollama
For faster and more powerful embeddings, you can use Ollama:
# Install Ollama from https://ollama.ai/
# Pull an embedding model (unclemusclez/jina-embeddings-v2-base-code is recommended)
ollama pull unclemusclez/jina-embeddings-v2-base-code
Usage
Using with Claude Desktop
Add the following configuration to your Claude Desktop configuration file (claude_desktop_config.json
):
{
"mcpServers": {
"code-context-mcp": {
```json
"command": "/path/to/your/node"
```,
"args": ["/path/to/claude-code-context-mcp/dist/index.js"]
}
}
}
Tools
The server provides the following tool:
queryRepo
Clones a repository, processes code, and performs semantic search:
{
"repoUrl": "https://github.com/username/repo.git",
"branch": "main", // Optional - defaults to repository's default branch
"query": "Your search query",
"keywords": ["keyword1", "keyword2"], // Optional - filter results by keywords
"filePatterns": ["**/*.ts", "src/*.js"], // Optional - filter files by glob patterns
"excludePatterns": ["**`/node_modules/**"],` // Optional - exclude files by glob patterns
"limit": 10 // Optional - number of results to return, default: 10
}
The branch
parameter is optional. If not provided, the tool will automatically use the repository's default branch.
The keywords
parameter is optional. If provided, the results will be filtered to only include chunks that contain at least one of the specified keywords (case-insensitive matching).
The filePatterns
and excludePatterns
parameters are optional. They allow you to filter which files are processed and searched using glob patterns (e.g., **/*.ts
for all TypeScript files).
Database Schema
The server uses SQLite with the following schema:
repository
: Stores information about repositoriesbranch
: Stores information about branchesfile
: Stores information about filesbranch_file_association
: Associates files with branchesfile_chunk
: Stores code chunks and their embeddings
Debugging
MAC Mx Series - ARM Architecture Issues
When installing better-sqlite3 on Mac M-series chips (ARM architecture), if you encounter errors like "mach-o file, but is an incompatible architecture (have 'x86_64', need 'arm64e' or 'arm64')", you need to ensure the binary matches your architecture. Here's how to resolve this issue:
# Check your Node.js architecture
node -p "process.arch"
# If it shows 'arm64', but you're still having issues, try:
npm rebuild better-sqlite3 --build-from-source
# Or for a clean install:
npm uninstall better-sqlite3
export npm_config_arch=arm64
export npm_config_target_arch=arm64
npm install better-sqlite3 --build-from-source
If you're using Rosetta, make sure your entire environment is consistent. Your error shows x86_64 binaries being built but your system needs arm64. For persistent configuration, add to your .zshrc or .bashrc:
export npm_config_arch=arm64
export npm_config_target_arch=arm64
Testing Ollama Embeddings
curl http://localhost:11434/api/embed -d '{"model":"unclemusclez/jina-embeddings-v2-base-code","input":"Llamas are members of the camelid family"}' curl http://127.0.01:11434/api/embed -d '{"model":"unclemusclez/jina-embeddings-v2-base-code","input":"Llamas are members of the camelid family"}' curl http://[::1]:11434/api/embed -d '{"model":"unclemusclez/jina-embeddings-v2-base-code","input":"Llamas are members of the camelid family"}'
License
MIT
Leave a Comment
Frequently Asked Questions
What is MCP?
MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications, providing a standardized way to connect AI models to different data sources and tools.
What are MCP Servers?
MCP Servers are lightweight programs that expose specific capabilities through the standardized Model Context Protocol. They act as bridges between LLMs like Claude and various data sources or services, allowing secure access to files, databases, APIs, and other resources.
How do MCP Servers work?
MCP Servers follow a client-server architecture where a host application (like Claude Desktop) connects to multiple servers. Each server provides specific functionality through standardized endpoints and protocols, enabling Claude to access data and perform actions through the standardized protocol.
Are MCP Servers secure?
Yes, MCP Servers are designed with security in mind. They run locally with explicit configuration and permissions, require user approval for actions, and include built-in security features to prevent unauthorized access and ensure data privacy.
Related MCP Servers
chrisdoc hevy mcp
sylphlab pdf reader mcp
An MCP server built with Node.js/TypeScript that allows AI agents to securely read PDF files (local or URL) and extract text, metadata, or page counts. Uses pdf-parse.
aashari mcp server atlassian bitbucket
Node.js/TypeScript MCP server for Atlassian Bitbucket. Enables AI systems (LLMs) to interact with workspaces, repositories, and pull requests via tools (list, get, comment, search). Connects AI directly to version control workflows through the standard MCP interface.
aashari mcp server atlassian confluence
Node.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get spaces & pages (content formatted as Markdown) and search via CQL. Connects AI seamlessly to Confluence knowledge bases using the standard MCP interface.
prisma prisma
Next-generation ORM for Node.js & TypeScript | PostgreSQL, MySQL, MariaDB, SQL Server, SQLite, MongoDB and CockroachDB
Zzzccs123 mcp sentry
mcp sentry for typescript sdk
zhuzhoulin dify mcp server
zhongmingyuan mcp my mac
zhixiaoqiang desktop image manager mcp
MCP 服务器,用于管理桌面图片、查看详情、压缩、移动等(完全让Trae实现)
zhixiaoqiang antd components mcp
An MCP service for Ant Design components query | 一个减少 Ant Design 组件代码生成幻觉的 MCP 服务,包含系统提示词、组件文档、API 文档、代码示例和更新日志查询
Submit Your MCP Server
Share your MCP server with the community
Submit Now