Code Context Provider MCP
Provides code context and analysis for AI assistants using WebAssembly Tree-sitter parsers.
Code Context Provider MCP
MCP server that provides code context and analysis for AI assistants. Extracts directory structure and code symbols using WebAssembly Tree-sitter parsers with Zero Native Dependencies.
Features
- Generate directory tree structure
- Analyze JavaScript/TypeScript and Python files
- Extract code symbols (functions, variables, classes, imports, exports)
- Compatible with the MCP protocol for seamless integration with AI assistants
Quick Usage (MCP Setup)
Installing via Smithery
To install Code Context Provider for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @AB498/code-context-provider-mcp --client claude
Windows
{
"mcpServers": {
"code-context-provider-mcp": {
"command": "cmd.exe",
"args": [
"/c",
"npx",
"-y",
"code-context-provider-mcp@latest"
]
}
}
}
MacOS/Linux
{
"mcpServers": {
"code-context-provider-mcp": {
"command": "npx",
"args": [
"-y",
"code-context-provider-mcp@latest"
]
}
}
}
OR install globally with npm:
npm install -g code-context-provider-mcp
Then use it by running:
code-context-provider-mcp # if you're not using @latest, you may want to clear the cache for latest version using `Remove-Item -Path "$env:LOCALAPPDATA\npm-cache\_npx" -Recurse -Force` for windows and `rm -rf ~/.npm/_npx` for linux/macos
Available Tools
get_code_context
Analyzes a directory and returns its structure along with code symbols (optional).
Parameters:
absolutePath(string, required): Absolute path to the directory to analyzeanalyzeJs(boolean, optional): Whether to analyze JavaScript/TypeScript and Python files (default: false)includeSymbols(boolean, optional): Whether to include code symbols in the response (default: false)symbolType(enum, optional): Type of symbols to include if includeSymbols is true (options: 'functions', 'variables', 'classes', 'imports', 'exports', 'all', default: 'all')filePatterns(array of strings, optional): File patterns to analyze (e.g. ['.js', '.py', 'config.*'])maxDepth(number, optional): Maximum directory depth to analyze (default: 5 levels)
Note: Anonymous functions are automatically filtered out of the results.
Example Output Text On Tool Call
Directory structure for: C:\Users\Admin\Desktop\mcp\context-provider-mcp
Code Analysis Summary:
- Files analyzed: 3
- Total functions: 29
- Total variables: 162
- Total classes: 0
Note: Symbol analysis is supported for JavaScript/TypeScript (.js, .jsx, .ts, .tsx) and Python (.py) files only.
Code analysis limited to a maximum depth of 5 directory levels (default).
├── index.js (39 KB)
│ └── [Analyzed: 22 functions, 150 variables, 0 classes]
│ Functions:
│ - initializeTreeSitter [39:0]
│ - getLanguageFromExtension [107:0]
│ - getPosition [138:24]
File Pattern Examples
You can use the filePatterns parameter to specify which files to analyze. This is useful for complex projects with multiple languages or specific files of interest.
Examples:
["*.js", "*.py"]- Analyze all JavaScript and Python files["config.*"]- Analyze all configuration files regardless of extension["package.json", "*.config.js"]- Analyze package.json and any JavaScript config files[".ts", ".tsx", ".py"]- Analyze TypeScript and Python files (using extension format)
The file pattern matching supports:
- Simple glob patterns with wildcards (*)
- Direct file extensions (with or without the dot)
- Exact file names
Handling Large Projects
For very large projects, you can use the maxDepth parameter to limit how deeply the tool will traverse directories:
maxDepth: 2- Only analyze the root directory and one level of subdirectoriesmaxDepth: 3- Analyze the root, and two levels of subdirectoriesmaxDepth: 0- Only analyze files in the root directory
This is particularly useful when:
- Working with large monorepos
- Analyzing projects with many dependencies
- Focusing only on the main source code and not third-party libraries
Supported Languages
Code symbol analysis is supported for:
- JavaScript (.js)
- JSX (.jsx)
- TypeScript (.ts)
- TSX (.tsx)
- Python (.py)
Using the filePatterns parameter allows you to include other file types in the directory structure, though symbolic analysis may be limited.
Development
[Development] Setting up the Development Environment
# Clone the repository
git clone https://github.com/your-username/code-context-provider-mcp.git
cd code-context-provider-mcp
# Install dependencies
npm install
# Set up WASM parsers
npm run setup
[Development] Post-Installation
After installation, the package's prepare script automatically runs to download the WASM parsers. If for some reason the download fails, users can manually run the setup:
npx code-context-provider-mcp-setup
License
MIT
For more information or help
Server Terkait
Alpha Vantage MCP Server
sponsorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
S3 Documentation MCP Server
A lightweight Model Context Protocol (MCP) server that brings RAG (Retrieval-Augmented Generation) capabilities to your LLM over Markdown documentation stored on S3.
Figma MCP Server with Chunking
An MCP server for the Figma API, with chunking and pagination to handle large files.
AiCore Project
A unified framework for integrating various language models and embedding providers to generate text completions and embeddings.
SVG to PNG MCP Server
A server that converts SVG code to PNG images using the cairosvg library.
GhostMCP
Injectable MCP server for AI-driven reverse engineering inside processes
Modexia-mcp
The financial infrastructure for autonomous AI. Equips Claude and other agents with secure, programmable USDC smart accounts (ERC-4337). Tools exposed: get_balance, transfer_usdc, get_history. Features: Abstracted gas fees (Paymasters), native USDC settlement on Base, and strict developer-defined spending limits (Policy-as-Code) to eliminate LLM hallucination liability.
MCP Cat PSQL
An example of a remote, authentication-free MCP server deployable on Cloudflare Workers.
TakeProfit MCP
Provides access to TakeProfit.com's Indie documentation and tooling — a Python-based scripting language for building custom cloud indicators and trading strategies on the TakeProfit platform.
DocsetMCP
A server for accessing Dash-style documentation sets locally. Requires a local Dash installation.
Brain
Adaptive error memory & code intelligence MCP server with Hebbian synapse network, cross-project learning, and auto-error detection