codebase-rag-mcp
by AyushShanu
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DATA_DIR | No | Where cloned corpora are staged (default ./data) | ./data |
| INDEX_DIR | No | Where FAISS/BM25 artifacts persist. Defaults to a per-repo directory under an OS-appropriate user-data path. Must be absolute if set. | |
| LOG_LEVEL | No | Log level: DEBUG, INFO, WARNING, ERROR (default INFO) | INFO |
| AUTO_INDEX | No | Set 'false' to require a prebuilt index (default 'true') | true |
| REPO_SOURCE | No | Default repo (URL or local path) to zero-config auto-index | |
| GROQ_API_KEY | No | Groq Cloud API key | |
| GEMINI_API_KEY | No | Google Gemini API key (optional) | |
| NVIDIA_API_KEY | No | NVIDIA NIM / build API key | |
| LOCAL_MODEL_NAME | No | Model name to use against the local server | |
| OPENROUTER_API_KEY | No | OpenRouter (multi-provider proxy) API key | |
| LOCAL_MODEL_API_KEY | No | Optional bearer token for the local server | |
| LOCAL_MODEL_BASE_URL | No | Base URL for an OpenAI-compatible local server (Ollama, vLLM, LM Studio, etc.) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
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 | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues