RAG Code Search Agent
by pratishank05
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_HOST | No | Host for SSE transport | 127.0.0.1 |
| MCP_PORT | No | Port for SSE transport | 8080 |
| CHUNK_SIZE | No | Maximum tokens per code chunk | 500 |
| CLAUDE_MODEL | No | Claude model for answer generation | claude-sonnet-4-20250514 |
| RERANK_TOP_K | No | Number of top documents after re-ranking | 10 |
| CHUNK_OVERLAP | No | Overlap lines between adjacent chunks | 50 |
| MCP_TRANSPORT | No | MCP server transport: stdio or sse | stdio |
| CHROMA_DB_PATH | No | Path to ChromaDB persistent storage | data/chroma_db |
| OPENAI_API_KEY | No | API key for OpenAI embeddings (when provider is openai) | |
| RERANKER_MODEL | No | Cross-encoder model for re-ranking | cross-encoder/ms-marco-MiniLM-L-6-v2 |
| EMBEDDING_MODEL | No | Local embedding model name | sentence-transformers/all-MiniLM-L6-v2 |
| RETRIEVAL_TOP_K | No | Number of documents to retrieve from ChromaDB | 20 |
| ANTHROPIC_API_KEY | No | API key for Claude (query rewriting, context compression, answer generation) | |
| CLAUDE_HAIKU_MODEL | No | Claude model for query rewriting and context compression | claude-haiku-4-20250414 |
| EMBEDDING_PROVIDER | No | Embedding provider: local or openai | local |
| CONTEXT_TOKEN_LIMIT | No | Maximum tokens for compressed context | 4000 |
| SIMILARITY_THRESHOLD | No | Minimum cosine similarity for retrieval results | 0.5 |
| OPENAI_EMBEDDING_MODEL | No | OpenAI embedding model name | text-embedding-3-small |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/pratishank05/rag-code-search'
If you have feedback or need assistance with the MCP directory API, please join our Discord server