Python Codebase Analysis RAG System

Python Codebase Analysis RAG System

Public
shervinemp/CodebaseMCP

Analyzes Python codebases using AST to extract and vectorize code elements, enabling advanced querying, semantic search, visualization, and natural language Q&A via a Model Context Protocol (MCP) server integrated with LLM-powered embeddings and background refinement.

python
0 tools
May 30, 2025
Updated Jun 4, 2025

Supercharge Your AI with Python Codebase Analysis RAG System

MCP Server

Unlock the full potential of Python Codebase Analysis RAG System through LangDB's AI Gateway. Get enterprise-grade security, analytics, and seamless integration with zero configuration.

Unified API Access
Complete Tracing
Instant Setup
Get Started Now

Free tier available • No credit card required

Instant Setup
99.9% Uptime
10,000+Monthly Requests
Configuration Requirements
API Key
Configure authentication and required variables to access this MCP server
Required Environment Variables
GENERATE_LLM_DESCRIPTIONS
Optional
string

Set to true to enable background LLM description generation and refinement

Default: true
GENERATION_MODEL_NAME
Optional
string

Gemini model for text generation

Default: models/gemini-pro
LLM_CONCURRENCY
Optional
string

Max concurrent background LLM tasks (embeddings/descriptions/refinements)

Default: 5
WEAVIATE_GRPC_PORT
Optional
string

Weaviate gRPC port

Default: 50051
WEAVIATE_PORT
Optional
string

Weaviate HTTP port

Default: 8080
WEAVIATE_BATCH_SIZE
Optional
string

Batch size for Weaviate operations

Default: 100
SEMANTIC_SEARCH_LIMIT
Optional
string

Limit for semantic search results

Default: 5
SEMANTIC_SEARCH_DISTANCE
Optional
string

Distance threshold for semantic search

Default: 0.7
WEAVIATE_HOST
Optional
string

Weaviate host address

Default: localhost
WATCHER_POLLING_INTERVAL
Optional
string

File watcher polling interval in seconds

Default: 5
GEMINI_API_KEY
Optional
string

Your Gemini API key

EMBEDDING_MODEL_NAME
Optional
string

Gemini model for embeddings

Default: models/embedding-001

Security Notice

Your environment variables and credentials are securely stored and encrypted. LangDB never shares these configuration values with third parties.

Related MCPs5
  • YouTube MCP

    Model Context Protocol server enabling YouTube video analysis with transcript extraction, AI-powered summarization, natural language querying, video search, and comment analysis using Gemini AI.

    Added May 30, 2025
  • Image Toolkit MCP Server

    Powerful Model Context Protocol server enabling advanced image generation, modification, background removal, and hosting through natural language text commands using Google Gemini and integrated APIs.

    Added May 30, 2025
  • MCP-JIRA-Python Server

    Python-based MCP (Model Context Protocol) server enabling secure, local JIRA integration with tools for issue management, user lookup, issue linking, commenting, and advanced JQL search.

    Added May 30, 2025
  • Needle MCP Server

    Manage and search documents efficiently using a Model Context Protocol server integrated with Claude’s large language model and Needle’s ecosystem for advanced natural language retrieval and organization.

    7 tools
    Added May 30, 2025
  • MCP Qdrant Server with OpenAI Embeddings

    Provides semantic vector search and collection management using Qdrant database integrated with OpenAI embeddings for enhanced natural language query capabilities within the Model Context Protocol framework.

    Added May 29, 2025