J

Jinni

Jinni is an efficient tool for providing project context to large language models. It overcomes the limitations of reading files one by one by integrating relevant files and their metadata.
3.5 points
247

What is Jinni?

Jinni is an intelligent project context extraction tool designed specifically for AI programming assistants. It can automatically scan your code project, extract all relevant file contents, and provide them to large language models (LLMs) in a structured manner, enabling AI to have a deeper understanding of the overall picture of your project.

How to use Jinni?

Simply configure your AI development environment (such as Cursor/Roo/Claude, etc.), and Jinni will work in the background. When the AI needs to understand the project, it will automatically obtain the complete code context.

Applicable scenarios

It is particularly suitable for scenarios such as the maintenance of complex code libraries, new members quickly getting familiar with the project, and cross - file code refactoring. It allows the AI assistant to understand your project like a senior developer.

Main features

Intelligent context extractionAutomatically identify and extract source code files in the project, excluding irrelevant content such as binaries/logs
Seamless MCP integrationDeeply integrate with mainstream AI development tools through the Model Context Protocol
Custom filtering rulesSupport.gitignore - style rules to precisely control which files should be included or excluded
Complete metadataProvide metadata such as file path, size, and modification time to help understand file relationships
Seamless WSL supportAutomatically handle Windows/WSL path conversion, ensuring worry - free cross - platform development

Advantages and limitations

Advantages
Get a complete project view with one click without manually viewing each file
The intelligent filtering mechanism ensures that only relevant code files are included
Ready - to - use with mainstream AI programming tools
Support large - scale projects and automatically handle path and encoding issues
Limitations
For extremely large projects, you may need to adjust the inclusion rules to avoid overly long context
Simple development environment settings are required for the first - time configuration
Binary/non - text files are not included by default (can be modified through configuration)

How to use

Install Jinni
Install the Jinni package via pip or uv
Configure the MCP client
Add Jinni server settings to the configuration file of your AI development tool
Specify the project root directory (optional)
For security reasons, you can restrict Jinni to access only specific directories
Start using
Restart your development environment, and now the AI can request to read the project context

Usage examples

New members getting familiar with the projectNewly joined developers use AI to quickly understand the project structure and main modules
Cross - file refactoringEnsure consistency when refactoring code that affects multiple files
Dependency analysisSort out the module dependencies in a complex project

Frequently Asked Questions

Why can't the AI sometimes see some of my files?
How to limit the directory scope that Jinni can access?
How to handle Windows/WSL paths?
What should I do if the project is too large and the context exceeds the limit?

Related resources

Official GitHub repository
Get the latest version and source code
MCP protocol documentation
Understand the technical details of the Model Context Protocol
Cursor integration guide
How to configure Jinni in Cursor
Installation
Copy the following command to your Client for configuration
{
    "mcpServers": {
        "jinni": {
            "command": "uvx",
            "args": ["jinni-server"]
        }
    }
}

{
      "mcpServers": {
        "jinni": {
          "command": "uvx",
          "args": ["jinni-server"]
        }
      }
    }

{
      "mcpServers": {
        "jinni": {
          // Adjust python path if needed, or ensure the correct environment is active
          "command": "python -m jinni.server"
          // Optionally constrain the server to only read within a tree (recommended for security):
          // "command": "python -m jinni.server --root /absolute/path/to/repo"
        }
      }
    }
Note: Your key is sensitive information, do not share it with anyone.
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.
652
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
336
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
823
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
221
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
317
4.2 points
P
Postgresql MCP
A PostgreSQL database MCP service based on the FastMCP library, providing CRUD operations, schema inspection, and custom SQL query functions for specified tables.
Python
105
4 points
M
MCP Scan
MCP-Scan is a security scanning tool for MCP servers, used to detect common security vulnerabilities such as prompt injection, tool poisoning, and cross-domain escalation.
Python
609
5 points
A
Agentic Radar
Agentic Radar is a security scanning tool for analyzing and assessing agentic systems, helping developers, researchers, and security experts understand the workflows of agentic systems and identify potential vulnerabilities.
Python
548
5 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
1.7K
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
823
4.3 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
79
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
130
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#
554
5 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
6.6K
4.5 points
C
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
5.2K
4.7 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
745
4.8 points
AIbase
Zhiqi Future, Your AI Solution Think Tank
© 2025AIbase