How do I install Code Index?

Pick a client above and copy the generated config. Cursor and VS Code also have a deep link when the server can run locally or remotely.

Is Code Index official?

No. Registry-listed is not the same as vendor-official. Read the methodology for the difference.

How is the trust score calculated?

This listing scores 45 (Fair). The formula is published on the methodology page.

MCPpedia

Code Index MCP Server | MCPpedia

Code Index MCP Server

Name: Code Index MCP Server
Author: achreftlili

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

Tools Versions Alternatives

Registryachreftlili

45Fair

Install

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "achreftlili-code-index": {
      "command": "uvx",
      "args": [
        "mcp-code-index"
      ],
      "env": {
        "CODE_INDEX_EMBEDDER": "",
        "CODE_INDEX_EMBED_MODEL": "",
        "CODE_INDEX_EMBED_DIM": "",
        "CODE_INDEX_DB": "",
        "CODE_INDEX_EMBED_BATCH": "",
        "CODE_INDEX_EMBED_DEVICE": ""
      }
    }
  }
}

Install guide

Related servers

SuperLocalMemory

78Good

Local-first memory for AI agents: recall with sources, answer checks, documents, mesh, governance.

Registryqualixar249 stars1.3K/wk

Codebase Memory

77Good

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

Environment

Name	Required	Notes
CODE_INDEX_EMBEDDER	No	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	No	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	No	Embedding dimension. Defaults to 768 (matches jina-embeddings-v2-base-code). Must match the model's output dim.
CODE_INDEX_DB	No	Path to the SQLite index database. Defaults to .claude/index.db relative to the working directory.
CODE_INDEX_EMBED_BATCH	No	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	No	Torch device override: 'cpu', 'mps', or 'cuda'. Unset = auto-detect. Set 'cpu' to avoid Apple-Silicon MPS out-of-memory errors.

Code Index MCP Server

Install

Related servers

SuperLocalMemory

Codebase Memory

Environment

Tools

About

FAQ

Reviews

Firecrawl MCP Server

Zotero MCP

haiku.rag

openInvest