Jinni
Jinni is a tool to efficiently provide Large Language Models the context of your projects. It gives a consolidated view of relevant project files complete with metadata, overcoming the limitations and inefficiencies of reading files one by one. The p
What is Jinni?
Jinni is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to jinni is a tool to efficiently provide large language models the context of your projects. it gives a consolidated view of relevant project files complete with metadata, overcoming the limitations and...
Jinni is a tool to efficiently provide Large Language Models the context of your projects. It gives a consolidated view of relevant project files complete with metadata, overcoming the limitations and inefficiencies of reading files one by one. The p
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Jinni is a tool to efficiently provide Large Language Models
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx jinni-bring-your-project-into-contextConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Jinni
Jinni provides AI assistants with a complete, consolidated view of your software project's source files, overcoming the slow and fragmented experience of reading files one by one. Each file is preceded by a path header so the model can reason about the full structure, and smart defaults automatically exclude binaries, build artifacts, dotfiles, and other irrelevant content. Fine-grained inclusion and exclusion rules can be set via .contextfiles, a gitignore-style format that takes precedence over .gitignore, giving teams precise control over what goes into the AI's context window.
Prerequisites
- Python 3.10 or higher
- uv or pip package manager
- An MCP-compatible client such as Claude Desktop or Claude Code
- A local project directory to load into context
Install Jinni via pip or uv
Install the jinni package, which provides both the CLI utility and the jinni-server MCP entry point used by AI clients.
pip install jinni
# or with uv:
uv pip install jinniConfigure your MCP client
Add jinni-server to your MCP client configuration. Using uvx ensures the server runs in a clean, isolated environment without conflicting with other Python packages.
{
"mcpServers": {
"jinni": {
"command": "uvx",
"args": ["jinni-server"]
}
}
}Create a .contextfiles to control scope (optional)
Add a .contextfiles file to your project root with gitignore-style patterns to precisely control which files are included. Patterns starting with ! are exclusions and override .gitignore rules.
# .contextfiles
src/**
docs/**/*.md
!**/__pycache__/**
!dist/**Try the CLI to test output before using MCP
Run jinni from the command line to preview what the AI will see. The output is also copied to the clipboard so you can paste it directly into any chat interface.
jinni ./my_project/
# List files only (no content):
jinni -l ./my_project/Ask your AI assistant to read project context
With the MCP server running, instruct your AI client to load project context. The read_context tool accepts a project_root path and optional target patterns to narrow scope.
Jinni Examples
Client configuration
Claude Desktop config using uvx to launch jinni-server as an MCP server.
{
"mcpServers": {
"jinni": {
"command": "uvx",
"args": ["jinni-server"]
}
}
}Prompts to try
Prompts to load project context and ask questions about your codebase.
- "Read context for the project at /Users/me/projects/api-service"
- "Load only the src module from /Users/me/projects/myapp and explain the architecture"
- "List all files jinni would include for /Users/me/projects/webapp without reading content"
- "Read context for /Users/me/projects/backend excluding the tests directory"
- "What external dependencies does this project use? Read its context first."Troubleshooting Jinni
Context dump is too large for the model's context window
Use the targets parameter in read_context to specify only the subdirectories or file patterns you need, or set size_limit_mb to cap output size. Use list_only=true first to preview the file list.
Binary or generated files are included unexpectedly
Jinni auto-excludes common binary types but may include unexpected files. Add exclusion rules to .contextfiles with ! prefixes, e.g. !dist/**, !*.wasm, or !**/*.min.js.
uvx not found when the MCP server tries to start
Install uv with: curl -LsSf https://astral.sh/uv/install.sh | sh. Make sure the shell that launches Claude Desktop has uv on its PATH. Alternatively change the command to 'jinni-server' if installed globally via pip.
Frequently Asked Questions about Jinni
What is Jinni?
Jinni is a Model Context Protocol (MCP) server that jinni is a tool to efficiently provide large language models the context of your projects. it gives a consolidated view of relevant project files complete with metadata, overcoming the limitations and inefficiencies of reading files one by one. the p It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Jinni?
Follow the installation instructions on the Jinni GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Jinni?
Jinni works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Jinni free to use?
Yes, Jinni is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.
Jinni Alternatives — Similar Coding Agents Servers
Looking for alternatives to Jinni? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Jinni in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Jinni?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.