MCPgee
MCPgee
MCPgeeMCPgee

Argyph

v1.0.0•Developer Tools•stable

Local-first MCP server giving AI coding agents fast, structured, and semantic context over any codebase. Zero config, zero cloud, full context.

claudeclaude-codecode-intelligencecode-searchembeddings
Share:
16
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Argyph?

Argyph is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to local-first mcp server giving ai coding agents fast, structured, and semantic context over any codebase. zero config, zero cloud, full context.

Local-first MCP server giving AI coding agents fast, structured, and semantic context over any codebase. Zero config, zero cloud, full context.

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

Features

  • Local-first MCP server giving AI coding agents fast, structu

Use Cases

Get fast semantic code search across any codebase without cloud.
Provide AI agents with structured codebase context instantly.
Enable zero-config code intelligence for LLM-assisted development.
ezzy1630

Maintainer

LicenseApache-2.0
Languagerust
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx argyph

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 Argyph

Argyph is a local-first, zero-config MCP server written in Rust that gives AI coding agents fast, structured, and semantic context over any codebase without sending code to the cloud. It exposes 19 tools organized across four tiers — from immediate file inventory and regex search to structural analysis like call graphs and symbol references, and background semantic search using a hybrid BM25 and vector retrieval system over AST-aware chunks. Developers using Claude Code, Claude Desktop, or other MCP clients can point Argyph at any repository and immediately get precise, token-efficient codebase context that avoids dumping entire files into the LLM context window.

Prerequisites

  • Node.js 18+ for npx-based installation (or Rust toolchain for source builds)
  • Homebrew (optional, for macOS installation)
  • An MCP client such as Claude Code or Claude Desktop
  • Optional: OPENAI_API_KEY or similar for semantic (vector) embedding features
1

Add Argyph to Claude Code

The recommended installation for Claude Code users is a single command that registers the server via npx.

claude mcp add argyph -- npx argyph@latest
2

Alternative: Install via Homebrew (macOS)

macOS users can also install the Argyph binary directly via Homebrew for a persistent installation.

brew install Ezzy1630/argyph/argyph
3

Initialize the index in your project

Navigate to your code repository and run argyph init to build the initial file inventory and structural index. Semantic indexing runs in the background.

cd ~/code/your-repo
argyph init
4

Configure Claude Desktop (optional)

If using Claude Desktop rather than Claude Code, add Argyph to your config file manually.

{
  "mcpServers": {
    "argyph": {
      "command": "npx",
      "args": ["argyph@latest"]
    }
  }
}
5

Configure embedding provider (optional)

To enable the Tier 2 semantic search features, set your embedding provider via environment variable. The default is local embeddings requiring no API key.

# For local embeddings (default, no API key needed):
export ARGYPH_EMBED_PROVIDER=local

# For OpenAI embeddings:
export ARGYPH_EMBED_PROVIDER=openai
export OPENAI_API_KEY=sk-...

Argyph Examples

Client configuration

Claude Desktop configuration to launch Argyph via npx for zero-config codebase indexing.

{
  "mcpServers": {
    "argyph": {
      "command": "npx",
      "args": ["argyph@latest"],
      "env": {
        "ARGYPH_EMBED_PROVIDER": "local"
      }
    }
  }
}

Prompts to try

Example prompts leveraging Argyph's multi-tier code retrieval tools.

- "What does this codebase do, and where is session expiration controlled?"
- "Find all callers of the authenticate() function in this repo"
- "Show me the imports and symbol definitions in the auth module"
- "Search for code related to rate limiting in the API layer"

Troubleshooting Argyph

npx argyph fails on Intel Mac with binary not found

Prebuilt binaries are not available for Intel Mac architecture. Build from source using Cargo: 'cargo install argyph --locked'. This requires the Rust toolchain to be installed.

Semantic search returns no results or errors about embeddings

Semantic indexing runs in the background after argyph init. Wait a few minutes for it to complete. If using openai embeddings, ensure OPENAI_API_KEY is set and the argyph binary was built with --features smart.

Frequently Asked Questions about Argyph

What is Argyph?

Argyph is a Model Context Protocol (MCP) server that local-first mcp server giving ai coding agents fast, structured, and semantic context over any codebase. zero config, zero cloud, full context. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Argyph?

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

Which AI clients work with Argyph?

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

Is Argyph free to use?

Yes, Argyph is open source and available under the Apache-2.0 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

Argyph Alternatives — Similar Developer Tools Servers

Looking for alternatives to Argyph? 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 ToolsCoding AgentsBrowse All Servers

Quick Config Preview

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

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

Read the full setup guide →

Ready to use Argyph?

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 ServersRead Our Guides