How do I install Indxr MCP Server?

Follow the setup instructions on the Indxr GitHub repository, then add the server configuration to your AI client.

What category is Indxr MCP Server?

Indxr is categorized under Developer Tools. Browse more servers in these categories on MCPgee.

Indxr

Name: Indxr MCP Server
Author: bahdotsh

v1.0.0•Developer Tools•stable

A fast codebase indexer and knowledge wiki for AI agents.

aiai-agentsclaude-codemcp-serveropenai

Stars

Downloads

Weekly

0/5

View on GitHub

What is Indxr?

Indxr is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to fast codebase indexer and knowledge wiki for ai agents.

A fast codebase indexer and knowledge wiki for AI agents.

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

A fast codebase indexer and knowledge wiki for AI agents.

Use Cases

Fast codebase indexing for AI agents

Knowledge wiki and token-efficient code search

bahdotsh

Maintainer

LicenseMIT

Languagerust

Versionv1.0.0

UpdatedMay 20, 2026

Statushealthy

Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

View Source Browse All Servers

Installation

Manual Installation

npx indxr

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms

ThroughputMedium

Resource Usage

Memory UsageLow

CPU UsageLow

How to Set Up and Use Indxr

Indxr is a fast, Rust-powered codebase indexer and knowledge wiki for AI agents that gives them deep, token-efficient access to large codebases without flooding context windows. It parses 27 programming languages using Tree-sitter and regex, exposes 27 MCP tools covering symbol lookup, caller tracing, dependency graph generation, cyclomatic complexity analysis, type flow tracking, and git structural diffing, and maintains a self-updating wiki that stays in sync with code changes. Developers use it so AI agents can navigate and reason about large codebases accurately without reading every file from scratch.

Prerequisites

Rust toolchain (cargo) installed for building from source, OR a pre-built binary from the releases page
An Anthropic API key (ANTHROPIC_API_KEY) or OpenAI API key (OPENAI_API_KEY) for the auto-updating wiki feature
An MCP-compatible client such as Claude Desktop, Cursor, or Windsurf
Git initialised in the codebase you want to index (required for structural diffing features)

Install indxr via cargo

Build and install indxr with the wiki and optional HTTP features enabled.

cargo install indxr --features wiki,http

Set your LLM API key

Export your Anthropic or OpenAI API key so indxr can auto-update the wiki when code changes.

export ANTHROPIC_API_KEY=your_key_here
# or
export OPENAI_API_KEY=your_key_here

Generate the initial wiki for your codebase

Run indxr wiki generate from your project root to build the knowledge wiki. This may take a few minutes for large codebases.

cd /path/to/your/project
indxr wiki generate

Start the indxr MCP server

Start the server in watch mode so the wiki auto-updates on file changes.

indxr serve . --watch --wiki-auto-update

Initialise client configuration

Run indxr init to automatically write MCP configuration files for Claude, Cursor, and Windsurf in your project.

indxr init

Restart your MCP client

Fully restart your MCP client (Claude Desktop, Cursor, etc.) to pick up the new configuration written by indxr init.

Indxr Examples

Client configuration

Manual MCP configuration for Claude Desktop pointing to the indxr server process.

{
  "mcpServers": {
    "indxr": {
      "command": "indxr",
      "args": ["serve", ".", "--watch", "--wiki-auto-update"]
    }
  }
}

Prompts to try

Prompts that leverage indxr's deep code analysis tools.

- "Find all callers of the authenticate() function in this codebase."
- "What are the top 10 most complex functions by cyclomatic complexity?"
- "Show me the dependency graph for the payments module."
- "What changed structurally between this branch and main?"
- "Search the wiki for how the caching layer works."
- "Estimate how many tokens it would take to read the entire auth module."

Troubleshooting Indxr

cargo install fails because Rust is not installed.

Install Rust via rustup: curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh — then restart your terminal and retry the install.

Wiki generation fails or produces empty results.

Ensure you are running 'indxr wiki generate' from the root of a git repository. Confirm ANTHROPIC_API_KEY or OPENAI_API_KEY is set correctly. For large repos, generation can take several minutes — let it complete.

indxr init does not write config for my client.

Use the --global flag to write configuration to user-level locations: 'indxr init --global'. Then check ~/.claude.json or ~/.cursor/mcp.json depending on your client.

Frequently Asked Questions about Indxr

What is Indxr?

Indxr is a Model Context Protocol (MCP) server that fast codebase indexer and knowledge wiki for ai agents. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Indxr?

Follow the installation instructions on the Indxr GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Indxr?

Indxr works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Indxr free to use?

Yes, Indxr is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Indxr Alternatives — Similar Developer Tools Servers

Looking for alternatives to Indxr? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.

Ecc

★ 188.2k

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Javaguide

★ 155.8k

Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发

Gemini CLI

★ 104.5k

A secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in

Awesome MCP Servers

★ 87.3k

⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.

MCP Servers

★ 86.0k

Model Context Protocol Servers

CC Switch

★ 77.5k

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Developer Tools Browse All Servers

Set Up Indxr in Your Editor

Choose your AI client for step-by-step setup instructions.

🖥️

Claude Desktop

macOS & Windows app

⌨️

Claude Code

CLI & terminal

📝

Cursor

AI-first code editor

💻

VS Code

GitHub Copilot MCP

🏄

Windsurf

Codeium AI editor

🔌

Cline

VS Code extension

Quick Config Preview

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

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Indxr?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides

Explore All Servers Read Our Guides