Happy slice of mcp pizzaMCP.pizza
serena

serena

MCP.Pizza Chef: oraios

Most assistants read code by scrolling through whole files. Serena instead looks up the exact function or class you mean, finds everywhere it is used, and edits it in place — the way a code editor's jump-to-definition works. It plugs into Claude Desktop, Cursor, VS Code, Cline, Roo Code, Windsurf, and Goose. Python, Java, and TypeScript work out of the box, with other languages supported less thoroughly. It is free and open source.

Coding

Use This MCP server To

Find every place a function is used before changing it Rename something across a large project safely Ask what a big unfamiliar codebase actually does Refactor a class without pasting whole files into chat Let the assistant run tests and fix what breaks

README

  • 🚀 Serena is a powerful coding agent toolkit capable of turning an LLM into a fully-featured agent that works directly on your codebase.
  • 🔧 Serena provides essential semantic code retrieval and editing tools that are akin to an IDE's capabilities, extracting code entities at the symbol level and exploiting relational structure.
  • 🆓 Serena is free & open-source, enhancing the capabilities of LLMs you already have access to free of charge.

Demonstration

Here is a demonstration of Serena implementing a small feature for itself (a better log GUI) with Claude Desktop. Note how Serena's tools enable Claude to find and edit the right symbols.

Serena-Add-Logo_x264.mp4

LLM Integration

Serena provides the necessary tools for coding workflows, but an LLM is required to do the actual work, orchestrating tool use.

Serena can be integrated with an LLM in several ways:

  • by using the model context protocol (MCP).
    Serena provides an MCP server which integrates with
    • Claude Desktop,
    • IDEs like VSCode, Cursor or IntelliJ,
    • Extensions like Cline or Roo Code
    • Goose (for a nice CLI experience)
    • and many others, including the ChatGPT app soon
  • by using Agno – the model-agnostic agent framework.
    Serena's Agno-based agent allows you to turn virtually any LLM into a coding agent, whether it's provided by Google, OpenAI or Anthropic (with a paid API key) or a free model provided by Ollama, Together or Anyscale.
  • by incorporating Serena's tools into an agent framework of your choice.
    Serena's tool implementation is decoupled from the framework-specific code and can thus easily be adapted to any agent framework.

Programming Language Support & Semantic Analysis Capabilities

serena FAQ

Which apps does this work in?
Claude Desktop, Cursor, VS Code, Cline, Roo Code, Windsurf, and Goose, among others.
Do I need to pay for anything?
No — Serena is free and open source, and works with the model subscription you already have.
Which programming languages are supported?
Python, Java, and TypeScript are supported directly. Ruby, Go, C#, Rust, Kotlin, Dart, and C/C++ are available but largely untested.
Can I use this to understand a project I just inherited?
Yes — it can walk the code, explain how the pieces fit together, and keep notes it remembers for later.
How hard is setup?
You add a short snippet to your assistant's settings file, and running it needs a Python package tool such as uv installed.
Does it change my files?
Yes, it can edit code directly, so keep your work under version control before you start.