G

Glyph

glyph is a code symbol extraction tool based on Tree-sitter. It extracts symbol outlines from the codebase through a declarative query language, provides structured context for LLM programming agents, supports multiple languages, and has configurable levels of detail.
2 points
1

What is glyph?

glyph is a server based on the Model Context Protocol (MCP) that can extract symbol outlines from your codebase. Using the Tree-sitter query language, it can accurately obtain information about code structures such as functions, classes, and variables, helping AI coding assistants better understand your code.

How to use glyph?

You can use glyph directly through the command line or integrate it into AI coding tools (such as Claude Code or Cursor). Simply specify the code file path and the level of extraction details to quickly generate code structure information.

Applicable scenarios

Suitable for scenarios where AI coding assistants need to understand complex code structures, such as code completion, documentation generation, and error detection. Particularly suitable for large projects or multi-language development environments.

Main Features

Accurate symbol extractionUse the Tree-sitter query language to accurately extract symbol information such as functions, classes, and variables from the code.
Multi-language supportSupports multiple programming languages such as Go, Java, JavaScript/TypeScript, and Python, and is easy to extend to new languages.
Multiple levels of detailProvides three levels of detail: minimal, standard, and full to meet the needs of different scenarios.
High-performance processingOptimized Tree-sitter queries enable fast parsing and support processing of large-scale codebases.
MCP protocol compatibilityDesigned for seamless integration with AI coding assistants and supports the Model Context Protocol (MCP).

Advantages and Limitations

Advantages
Improve the AI coding assistant's understanding of the code
Support multiple programming languages and can be flexibly extended
Provide detailed symbol information for code analysis
Efficient and lightweight parsing performance
Limitations
Requires some configuration to发挥 its maximum potential
Need to add query patterns for unsupported languages
May require learning the Tree-sitter query syntax for first-time use

How to Use

Install glyph
Install Go on macOS using Homebrew, and then install glyph via Go.
Run the MCP server
Start glyph as an MCP server for use by AI coding assistants.
Use the CLI mode
Extract symbol information for specific files directly through the command line.

Usage Examples

AI code completionAfter integrating glyph into an AI coding assistant, the assistant can more accurately understand the code structure and provide more relevant code completion suggestions.
Code documentation generationUse the symbol information extracted by glyph to automatically generate code documentation or API references.

Frequently Asked Questions

Which programming languages does glyph support?
How to improve the understanding ability of AI coding assistants?
Does glyph require complex configuration?
What is the performance of glyph?

Related Resources

Official GitHub repository
Source code and development documentation for glyph
Tree-sitter query language documentation
Learn how to write Tree-sitter query statements
MCP protocol specification
Detailed specification of the Model Context Protocol (MCP)
Installation
Copy the following command to your Client for configuration
{
  "mcpServers": {
    "glyph": {
      "command": "/usr/local/bin/glyph",
      "args": ["mcp"]
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.
Z
Zen MCP Server
Zen MCP is a multi-model AI collaborative development server that provides enhanced workflow tools and cross-model context management for AI coding assistants such as Claude and Gemini CLI. It supports seamless collaboration of multiple AI models to complete development tasks such as code review, debugging, and refactoring, and can maintain the continuation of conversation context between different workflows.
Python
18
5 points
O
Opendia
OpenDia is an open - source browser extension tool that allows AI models to directly control the user's browser, perform automated operations using existing login status, bookmarks and other data, support multiple browsers and AI models, and focus on privacy protection.
JavaScript
15
5 points
C
Container Use
Container Use is an open-source tool that provides a containerized isolated environment for coding agents, supporting parallel development of multiple agents without interference.
Go
12
5 points
N
Notte Browser
Certified
Notte is an open-source full-stack network AI agent framework that provides browser sessions, automated LLM-driven agents, web page observation and operation, credential management, etc. It aims to transform the Internet into an agent-friendly environment and reduce the cognitive burden of LLMs by describing website structures in natural language.
701
4.5 points
S
Search1api
The Search1API MCP Server is a server based on the Model Context Protocol (MCP), providing search and crawling functions, and supporting multiple search services and tools.
TypeScript
376
4 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
892
4.3 points
B
Bing Search MCP
An MCP server for integrating Microsoft Bing Search API, supporting web page, news, and image search functions, providing network search capabilities for AI assistants.
Python
262
4 points
M
MCP Alchemy
Certified
MCP Alchemy is a tool that connects Claude Desktop to multiple databases, supporting SQL queries, database structure analysis, and data report generation.
Python
361
4.2 points
Featured MCP Services
M
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
1.8K
5 points
G
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
154
4.3 points
N
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
201
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
892
4.3 points
F
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
6.7K
4.5 points
U
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#
616
5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
797
4.8 points
G
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
335
4.5 points
AIbase
Zhiqi Future, Your AI Solution Think Tank
© 2025AIbase