# Argo (MCP server)

> Argo is an MCP server that adds search and knowledge tools to AI assistants such as Claude Desktop, Claude Code and Cursor. 专门为 agent 打造的开源 agent 搜索工具，具备 200+的搜索源及多语言搜索能力，覆盖中文/英文/学术/代码/购物/金融/新闻/百科。. It has 207 GitHub stars, is released under the Apache-2.0 license and runs locally with npx -y argo-search.

这是踏雪寻仙 DeepSeek Harness 插件系列的一员（dsh-files 39★ · dsh-models 模型选择 + 子代理路由 + 推理层级）。同作者完整技能系列：session-digger 29★ · taxue-invest 21★ · taxueskills 23★ · taxue-creative-style 12★

## Key facts

| Fact | Value |
|---|---|
| Repository | https://github.com/taxueseek/argo |
| GitHub stars | 207 |
| License | Apache-2.0 |
| Language | Python |
| Transport | stdio |
| Packages | npm: argo-search |
| Remote URL | none |
| Needs API key | no |
| Official | no |
| Works with | Claude Desktop, Claude Code, Cursor, VS Code |
| Category | AI & search |
| Latest release | v2.9.9 (Oct 25, 2026) |
| Last commit | Oct 25, 2026 |

## Install

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "argo": {
      "command": "npx",
      "args": [
        "-y",
        "argo-search"
      ]
    }
  }
}
```

Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards.

### Claude Code

```sh
claude mcp add --transport stdio argo -- npx -y argo-search
```

### Cursor (.cursor/mcp.json)

```json
{
  "mcpServers": {
    "argo": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "argo-search"
      ]
    }
  }
}
```

Project file; use ~/.cursor/mcp.json to enable it in every project.

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "argo": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "argo-search"
      ]
    }
  }
}
```

Config formats checked against the official docs on 2026-10-07.

## Similar MCP servers

- [ClawMem](https://appsgit.com/mcp-servers/clawmem): On-device memory layer for AI agents. Claude Code, OpenClaw and Hermes. (212 stars, MIT)
- [Mengram](https://appsgit.com/mcp-servers/mengram): Long-term memory for AI agents: semantic facts, episodic events, and procedural workflows. (204 stars, Apache-2.0, needs API key)
- [Kokon](https://appsgit.com/mcp-servers/kokon): Generate and edit images offline with Qwen-Image 2.1 on your GPU. (220 stars, AGPL-3.0)
- [MCP Image](https://appsgit.com/mcp-servers/mcp-image): AI image generation and editing with prompt optimization and quality presets. (183 stars, MIT, needs API key)
- [SuperCMO](https://appsgit.com/mcp-servers/supercmo): Marketing media generation — image, video, voice — for AI agents. (221 stars, Apache-2.0, needs API key)
- [SerpApi](https://appsgit.com/mcp-servers/serpapi): Official SerpApi MCP server for Google, Bing, and other search engines. (182 stars, MIT, official, needs API key)

---

Canonical page: https://appsgit.com/mcp-servers/argo
Source: appsgit (https://appsgit.com), the app store for github. Data from the GitHub API, refreshed daily.
Machine access: JSON API https://appsgit.com/api/v1/apps (OpenAPI: https://appsgit.com/openapi.json), MCP server https://mcp.appsgit.com/mcp, full index https://appsgit.com/llms-full.txt.