Code Index MCP Server

by achreftliliio.github.achreftlili/code-indexv1.0.6

SQLite-backed hybrid (vector + FTS) code search index for Claude Code over MCP.

1Pythonstdioofficial registry

context tax

queued

security

queued

cold start

queued

freshness

Slowing5mo ago

Install Code Index MCP server

claude mcp add code-index-achreftlili -- uvx mcp-code-index

{
  "mcpServers": {
    "code-index-achreftlili": {
      "command": "uvx",
      "args": [
        "mcp-code-index"
      ]
    }
  }
}

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).

{
  "mcpServers": {
    "code-index-achreftlili": {
      "command": "uvx",
      "args": [
        "mcp-code-index"
      ]
    }
  }
}

Settings → Developer → Edit Config (claude_desktop_config.json), then restart.

{
  "servers": {
    "code-index-achreftlili": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mcp-code-index"
      ]
    }
  }
}

Add to .vscode/mcp.json in your workspace.

{
  "mcpServers": {
    "code-index-achreftlili": {
      "command": "uvx",
      "args": [
        "mcp-code-index"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json.

Configuration

Variable	Required	Secret	Description
CODE_INDEX_EMBEDDER	—	—	Embedder backend. Only 'jina' (local jina-embeddings-v2-base-code via sentence-transformers) is supported; the variable exists for future expansion.
CODE_INDEX_EMBED_MODEL	—	—	HuggingFace model id. Defaults to 'jinaai/jina-embeddings-v2-base-code'. Override only if you know the model is dim-compatible.
CODE_INDEX_EMBED_DIM	—	—	Embedding dimension. Defaults to 768 (matches jina-embeddings-v2-base-code). Must match the model's output dim.
CODE_INDEX_DB	—	—	Path to the SQLite index database. Defaults to .claude/index.db relative to the working directory.
CODE_INDEX_EMBED_BATCH	—	—	Encode batch size (default 32). Lower (e.g. 8 or 4) to reduce peak memory if the GPU OOMs on large files.
CODE_INDEX_EMBED_DEVICE	—	—	Torch device override: 'cpu', 'mps', or 'cuda'. Unset = auto-detect. Set 'cpu' to avoid Apple-Silicon MPS out-of-memory errors.