serena
by oraios
Overview
Provides a multi-language Code Analysis and Interaction server for AI Agents using the Language Server Protocol (LSP), enabling agents to understand, navigate, and modify codebases.
Installation
uv run --directory <path-to-serena-repo> serena-mcp-server <path-to-your-project/.serena/project.yml>Environment Variables
- OPENAI_API_KEY
- ANTHROPIC_API_KEY
- GITHUB_TOKEN
- MIX_ENV
- MIX_TARGET
- TERRAFORM_CLI_PATH
Security Notes
The system is designed to interact with various external language servers and execute shell commands (`ExecuteShellCommandTool`). While this functionality is core to its operation, it inherently introduces risks. An AI agent using this server could potentially execute arbitrary commands on the host system if not properly constrained or monitored. There are no obvious hardcoded credentials or hidden malicious patterns in the truncated source code, and process management is handled with common utilities like `subprocess` and `psutil`.
Similar Servers
mcp-language-server
Proxies a Language Server Protocol (LSP) server to provide semantic code intelligence tools to Model Context Protocol (MCP) clients, enabling LLMs to interact with codebases.
sentry-mcp
The Sentry Model Context Protocol (MCP) server is designed as middleware to the Sentry API, optimized for human-in-the-loop coding agents and AI assistants (like Cursor, Claude Code) to facilitate developer workflows and debugging use cases.
chunkhound
Transforms codebases into searchable knowledge bases for AI assistants using semantic search and regex search, with deep research capabilities for code and files.
cclsp
MCP server to integrate LLM-based coding agents with Language Server Protocol (LSP) servers for robust symbol resolution and code navigation.