Home › Development › SocratiCode

SocratiCode

MCP server for enterprise local codebase indexing, semantic search, and code dependency graphs.

TypeScript

★ 3,370 stars Last pushed 2026-11-05 License: AGPL-3.0

View repository →

Connect

Review any command before running it. Package names and URLs come from the server's own registry entry.

Package (npm 1.16.2)

npx -y [email protected]

Or add to your MCP client config:

{
  "mcpServers": {
    "socraticode": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "OPENAI_API_KEY": "<YOUR_VALUE>",
        "GOOGLE_API_KEY": "<YOUR_VALUE>",
        "OLLAMA_API_KEY": "<YOUR_VALUE>",
        "LMSTUDIO_API_KEY": "<YOUR_VALUE>",
        "LITELLM_API_KEY": "<YOUR_VALUE>",
        "QDRANT_API_KEY": "<YOUR_VALUE>"
      }
    }
  }
}

EMBEDDING_PROVIDER — Embedding provider to use: ollama (default), openai, google, lmstudio, or litellm
OPENAI_API_KEY secret — API key for OpenAI embeddings (required only when EMBEDDING_PROVIDER=openai)
GOOGLE_API_KEY secret — API key for Google embeddings (required only when EMBEDDING_PROVIDER=google)
OLLAMA_URL — URL of the Ollama server (default: auto-detected; Docker-managed or http://localhost:11434)
EMBEDDING_MODEL — Embedding model name (defaults per provider; required for lmstudio and litellm)
EMBEDDING_DIMENSIONS — Embedding vector dimensions (defaults per provider; required for lmstudio and litellm)
OLLAMA_MODE — Ollama mode: auto (default), docker, or external
OLLAMA_API_KEY secret — Optional API key for authenticated Ollama proxies. Remote endpoints require HTTPS; loopback HTTP is supported.
LMSTUDIO_URL — LM Studio OpenAI-compatible base URL (default: http://localhost:1234/v1)
LMSTUDIO_API_KEY secret — Optional API key when LM Studio authentication is enabled
LMSTUDIO_ALLOW_MISSING_MODEL_LISTING — Allow compatible embedding servers without a models endpoint to be probed directly
LITELLM_URL — LiteLLM OpenAI-compatible base URL (default: http://localhost:4000/v1)
LITELLM_API_KEY secret — LiteLLM master or virtual API key (required when EMBEDDING_PROVIDER=litellm)
LITELLM_SEND_DIMENSIONS — Forward the dimensions parameter through LiteLLM when explicitly enabled
QDRANT_MODE — Qdrant mode: managed (default, Docker-managed) or external (user-provided instance)
QDRANT_URL — Full URL for remote/cloud Qdrant (e.g. https://xyz.cloud.qdrant.io:6333). Only needed when QDRANT_MODE=external
QDRANT_API_KEY secret — API key for remote Qdrant instance. Only needed when QDRANT_MODE=external