Codeix MCP Server

AI coding agents spend most of their token budget *finding* code before they can *work on* it. They grep, read files, grep again, backtrack. On a

Local serverstdioPython

What is the Codeix MCP server?

Most file and storage access work still happens through a UI a human drives. Codeix MCP server moves it into the conversation instead. AI coding agents spend most of their token budget finding code before they can work on it. They grep, read files, grep again, backtrack. On a large codebase the agent might burn thousands of tokens just locating the right function — or.

The tools it exposes

The server publishes 8 tools. What each one is for:

  • Problem — What happens today
  • explore — Explore project structure: metadata, subprojects, files grouped by directory
  • search — Unified full-text search across symbols, files, and texts (FTS5, BM25-ranked) with scope/kind/path/project filters
  • get_file_symbols — List all symbols in a file
  • get_children — Get children of a class/module
  • get_callers — Find all places that call or reference a symbol
  • get_callees — Find all symbols that a function/method calls
  • flush_index — Flush pending index changes to disk

Getting it running

Installation goes through your MCP client rather than a global install: point it at codeix on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

How it compares

Among the file and storage access options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Codeix's toolset — Problem, explore, search and 5 more — is a fair guide to whether it matches your workflow. It is maintained by montanetech; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Codeix's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
ProblemWhat happens today
exploreExplore project structure: metadata, subprojects, files grouped by directory
searchUnified full-text search across symbols, files, and texts (FTS5, BM25-ranked) with scope/kind/path/project filters
get_file_symbolsList all symbols in a file
get_childrenGet children of a class/module
get_callersFind all places that call or reference a symbol
get_calleesFind all symbols that a function/method calls
flush_indexFlush pending index changes to disk

How to install the Codeix MCP server

{
  "mcpServers": {
    "codeix": {
      "command": "npx",
      "args": ["-y", "codeix"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Codeix to Problem.
  • Use Codeix to explore.
  • Use Codeix to search.

Frequently asked questions

It connects Codeix to MCP-compatible AI assistants such as Claude and Cursor, exposing 8 tools (Problem, explore, search, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Codeix directly.