
Serena MCP: the IDE for your agent
MCP toolkit giving coding agents symbol-level code retrieval and editing
- Pricing
- Open source
- Platforms
- CLI, self-hosted, vscode
- Runs
- Locally
- GitHub stars
- 31.5K
- Last commit
- 2 days ago
- Language
- Python
About Serena MCP: the IDE for your agent
Serena MCP: the IDE for your agent is an open-source MCP server for developer tools. It runs locally on your machine and is started by your AI client.
Serena gives a coding agent IDE-like tools: semantic code retrieval, editing, refactoring and debugging that work at the symbol level rather than with line numbers or plain text search.
It connects to any client or model through MCP, including terminal clients, IDE plugins and desktop apps. You either give the client a launch command or run Serena in HTTP mode and supply the URL. A language model is still needed to orchestrate the tools.
It is aimed at developers working in larger or multi-language codebases with AI agents.
Install
Run in a terminal
claude mcp add serena -- uvx serena-agentAdd to claude_desktop_config.json
{
"mcpServers": {
"serena": {
"command": "uvx",
"args": [
"serena-agent"
]
}
}
}Add to ~/.cursor/mcp.json
{
"mcpServers": {
"serena": {
"command": "uvx",
"args": [
"serena-agent"
]
}
}
}Add to .vscode/mcp.json
{
"servers": {
"serena": {
"type": "stdio",
"command": "uvx",
"args": [
"serena-agent"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"serena": {
"command": "uvx",
"args": [
"serena-agent"
]
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"serena": {
"command": "uvx",
"args": [
"serena-agent"
]
}
}
}What it does
- Symbol-level tools
- Retrieval and editing based on code structure.
- Refactoring support
- Cross-file renames and moves in single calls.
- Client-agnostic
- Works with any MCP-capable client or LLM.
- Two connection modes
- Launch command or HTTP mode.
- Language support
- Covers many languages through semantic analysis.
Good for
- Rename symbols across files
- Navigate references in a monorepo
- Refactor large codebases with an agent
- Add semantic tools to an existing client
Pricing
Open source
Open source; license not stated in the content
Prices change. Check oraios.github.io before you buy.
Serena MCP: the IDE for your agent FAQ
How do I connect it?
Give your client a launch command or start Serena in HTTP mode and provide the URL.
Which clients work?
Terminal clients, IDE plugins and desktop or web clients that support MCP.
Does it include a model?
No, an LLM is needed to orchestrate the tools.
Is Serena MCP: the IDE for your agent free?
Yes. Serena MCP: the IDE for your agent is open source, so you can use and self-host it for free.
How do I add Serena MCP: the IDE for your agent to Claude Code?
Run this command in your terminal: claude mcp add serena -- uvx serena-agent
What are the best alternatives to Serena MCP: the IDE for your agent?
The closest alternatives to Serena MCP: the IDE for your agent are REA, Codebase Memory, GitHub, XERJ and Ouroboros.
Alternatives to Serena MCP: the IDE for your agent

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
Not checked yet- Remote
- Open source
- 34.5K GitHub stars
- Developer tools

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Ouroboros
MCP serverSpec-first layer that pins requirements and verifies results of AI coding agent work
Runs locally- Open source
- 6.4K GitHub stars
- Developer tools

Claude Code Ultimate Guide
MCP serverMCP server for searching the Claude Code Ultimate Guide from any MCP client
Runs locally- Open source
- 6.5K GitHub stars
- AI models and LLM tooling