kodit
Verified Safeby helixml
Overview
Indexes code repositories to generate various AI-driven enrichments (snippets, summaries, architecture docs, API docs, commit descriptions, database schemas, cookbooks) and enables semantic search for better AI code generation.
Installation
python -m kodit serve --host 0.0.0.0 --port 8080Environment Variables
- KODIT_DATABASE_URL
- KODIT_API_KEYS
- KODIT_DEFAULT_SEARCH_PROVIDER
- KODIT_EMBEDDING_ENDPOINT_MODEL
- KODIT_EMBEDDING_ENDPOINT_API_KEY
- KODIT_ENRICHMENT_ENDPOINT_MODEL
- KODIT_ENRICHMENT_ENDPOINT_API_KEY
Security Notes
The system handles API keys and other secrets primarily through environment variables, which is a good practice. Network communication for external LLM/embedding providers is handled by LiteLLM and `httpx`, supporting SSL verification and retries. File system operations related to cloning and scanning Git repositories are performed within a designated `clone_dir`, which is sanitized and managed to prevent path traversal. Database interactions use SQLAlchemy, mitigating common SQL injection risks. The use of local LLM/embedding models implies local resource usage, which can be a performance concern but not directly a security vulnerability. The system appears robust against common web vulnerabilities.
Similar Servers
wcgw
An MCP server that empowers AI chat applications to execute shell commands, edit code, and manage project context on a local machine for development tasks.
cclsp
MCP server to integrate LLM-based coding agents with Language Server Protocol (LSP) servers for robust symbol resolution and code navigation.
In-Memoria
Provides persistent intelligence infrastructure (semantic concepts, patterns, architecture) for AI agents to understand and interact with codebases.
codex-mcp-server
Provides a Model Context Protocol (MCP) server to integrate OpenAI Codex CLI with AI clients like Claude, offering session management, model selection, and native resume capabilities for coding assistance.