AIBase
EN
Explore
Docdex
D

Docdex

Docdex is a lightweight local document indexing and search daemon that builds an index of Markdown/text files on the local disk for each project and provides search fragments via HTTP API or CLI without external services or uploads.
Search toolsDeveloper tools#Document Search#Local Indexing#MCP Tool#Code Assistant.Rust
2.5 points
7.2K
Open Site

Overview

Installation

Content Details

Alternatives

What is Docdex?

Docdex is a local document search engine designed specifically for code projects. It can automatically scan document files (such as Markdown and text files) in a project, build a local index, and then allow you to quickly find relevant document content through a simple search. All data is stored locally, without the need to connect to the Internet or any external services.

How to use Docdex?

Using Docdex is very simple: first install it, then run the indexing command in your project directory, and finally start the service. You can search for documents through the HTTP API or command-line tools, and the search results will be returned in a structured manner, which is very suitable for integration into the development workflow.

Use cases

Docdex is particularly suitable for the following scenarios: 1. There are a large number of documents in a large project that need to be quickly searched. 2. A unified document search entry is needed for team collaboration. 3. It can be integrated into AI programming assistants (such as GitHub Copilot, Cursor, etc.) to provide context. 4. The local development environment needs to quickly access project documents. 5. Scenarios where sensitive document content needs to be protected from leakage.

Main Features

Local Indexing
All document indexes are stored on the local disk, without the need for a network connection or external services, ensuring data privacy and security.
Real-time File Monitoring
The service automatically monitors changes to document files during operation and updates the index in real-time to ensure that search results are always up-to-date.
Multi-interface Support
It provides two access methods, HTTP API and command line, for easy integration into various development tools and workflows.
AI Assistant Friendly
It is specifically optimized for AI programming assistants, providing a concise API and an output format suitable for prompt engineering.
Security Features
It has multiple built-in security mechanisms, including authentication tokens, IP whitelists, rate limits, and TLS support, to protect document access security.
MCP Protocol Support
It supports the Model Context Protocol (MCP) and can be seamlessly integrated with AI development tools that support MCP (such as Cursor, Claude Desktop, etc.).
Advantages
It runs completely locally, and data never leaves your machine, protecting privacy and security.
It has a lightweight design, consumes few resources, and starts quickly.
It supports real-time file monitoring, and the index is automatically updated.
It provides multiple security options and is suitable for use in enterprise environments.
It is highly compatible with mainstream AI development tools.
It is an open-source project, allowing for customization and feature expansion.
Limitations
It only supports text and Markdown format documents and does not support binary formats such as PDF and Word.
It requires manual configuration and service startup, which is not suitable for users who are completely unfamiliar with the command line.
Indexing large projects may take some time and disk space.
Advanced security features require additional configuration.

How to Use

Install Docdex
Install Docdex globally via npm or run it temporarily using npx. Make sure your system has Node.js 18 or a higher version installed.
Create a Document Index
Run the indexing command in your project directory, and Docdex will automatically scan all document files and create a local index.
Start the Search Service
Start the HTTP service so that you can search for documents through the API. By default, it listens on the local port 46137.
Search for Documents
Now you can search for documents through the HTTP API or the command line.

Usage Examples

Provide Project Document Search for New Team Members
When new members join a project, they can quickly search for project documents through Docdex to understand the code structure, API design, and development specifications, without having to manually browse a large number of files.
AI Programming Assistant Integration
Integrate Docdex into AI programming tools such as Cursor or Claude Desktop. When the AI assistant needs to understand project documents, it can automatically search for relevant documents as context.
Document Check Before Code Review
Before submitting code for review, developers can search for relevant documents to ensure that the code implementation complies with the specifications and best practices in the project documents.

Frequently Asked Questions

What document formats does Docdex support?
How much disk space does the index take up?
How can I protect sensitive documents from being indexed?
Can Docdex be shared and used within a team?
How can I integrate Docdex with my IDE or editor?
Does Docdex support Chinese search?

Related Resources

GitHub Repository
The source code and latest version of Docdex
npm Package Page
Information about the Docdex npm package and installation instructions
Model Context Protocol Documentation
The official documentation for the MCP protocol, learn how to integrate with AI tools
Issue Feedback and Discussion
Report issues, request features, or participate in discussions

Installation

Copy the following command to your Client for configuration
{
    "mcpServers": {
      "docdex": {
        "command": "docdexd",
        "args": ["mcp", "--repo", ".", "--log", "warn", "--max-results", "8"],
        "env": {}
      }
    }
  }
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

A
Airweave
Airweave is an open - source context retrieval layer for AI agents and RAG systems. It connects and synchronizes data from various applications, tools, and databases, and provides relevant, real - time, multi - source contextual information to AI agents through a unified search interface.
Python
15.1K
5 points
V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
10.4K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
10.0K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
14.7K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
6.7K
4 points
P
Paperbanana
Python
8.9K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
10.7K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
9.9K
5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
39.0K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
23.7K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
81.2K
4.3 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
27.2K
4.3 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
69.4K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
37.3K
5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
24.9K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
56.2K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
English简体中文繁體中文にほんご
© 2026AIBase