Codebase Context MCP
An MCP server for cross-platform codebase indexing and searching, using WASM technology to replace native dependencies, capable of running seamlessly on ARM64 and x86_64 architectures, providing code parsing, symbol search, and project analysis functions.
rating : 2 points
downloads : 3.7K
What is codebase-context-mcp?
codebase-context-mcp is a Model Context Protocol server that provides intelligent indexing and searching functions specifically for codebases. It can parse your project code, extract symbol information such as functions, classes, and variables, and provide fast and accurate code search functions. Different from traditional code search tools, it is completely built on WebAssembly technology and does not require the installation of any native C++ dependencies, so it can run on any platform, including devices with ARM64 architecture.How to use codebase-context-mcp?
You can use this server through Claude Code or by directly configuring MCP settings. After installation, it will automatically index your codebase, and then you can search for code, view the file structure, and obtain project overviews and other information through natural language queries. The entire process is fully automated, without the need for manual configuration of complex search services.Applicable scenarios
• Quickly find the definitions of specific functions or classes in a large codebase • Understand the structure and technology stack of a newly taken-over project • Conduct code analysis and search on ARM devices such as Raspberry Pi • Quickly understand the project architecture during team collaboration • Quickly locate relevant code during code reviewMain features
Full-platform compatibility
Using pure WASM technology, without native dependencies, supporting x86_64 and ARM64 architectures, including devices such as Raspberry Pi, Apple Silicon Mac, and AWS Graviton.
Intelligent code indexing
Automatically parse the codebase, extract symbol information (functions, classes, types, etc.), and build a searchable index.
Fast code search
Provides two search methods: symbol search (search by name) and full-text search (BM25 algorithm), supporting fuzzy matching.
File structure analysis
Generate a detailed outline of the file, including functions, classes, import and export statements, and their line numbers.
Project overview
Automatically analyze the project's technology stack, file type distribution, and directory structure to help quickly understand the project.
Incremental indexing
Only re-index the files that have changed, significantly improving the efficiency of repeated indexing.
Advantages
True cross-platform support: No need to compile native dependencies on ARM64 devices
Zero-configuration installation: Just use 'npm install' and no complex environment configuration is required
Lightweight: Using pure JavaScript and WASM, with low resource consumption
Seamless integration with Claude: Directly communicate with Claude through the MCP protocol
Intelligent ignoring: Automatically ignore irrelevant directories such as node_modules and.git
Support for mainstream languages: TypeScript, JavaScript, Python, C#, etc.
Limitations
Performance limitation: The WASM parsing speed may be slightly slower than the native implementation
File size limitation: Supports a maximum single file size of 512KB
Project scale limitation: Supports a maximum of 20,000 files
Limited language support: Currently supports 7 programming languages and does not support all languages
Requires manual triggering of indexing: Does not automatically monitor file changes
How to use
Install the server
Add the MCP server through the Claude Code command-line tool
Or manually configure
Add server settings to the MCP configuration file
Index the codebase
When using it for the first time, you need to index the codebase first
Start searching
After the indexing is completed, you can use various search tools to query the code
Usage examples
Find a specific function
When you need to find a function named 'calculateTotal' but are not sure which file it is in
Understand a new project
When you first take over a new project and need to quickly understand the project's technology stack and overall structure
Code review assistance
When conducting a code review, you need to view the complete structure of a file
Cross-file search
You need to find all code that uses a specific API or pattern
Frequently Asked Questions
Why can this tool work on Raspberry Pi while other similar tools cannot?
How much disk space will the index occupy?
Which programming languages are supported?
How to update the index?
Can certain files or directories be ignored?
What is the performance like? How large a project can it handle?
Related resources
GitHub repository
Project source code and latest updates
Model Context Protocol documentation
Official specification of the MCP protocol
Claude Code documentation
Claude Code usage guide
web-tree-sitter project
The WASM parser technology used

Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
20.4K
4.5 points

Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
34.3K
5 points

Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
25.4K
4.3 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
72.7K
4.3 points

Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
31.1K
5 points

Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
65.4K
4.5 points

Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
21.0K
4.5 points

Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
98.2K
4.7 points



