# 自動安裝 MCP

> 自動安裝 MCP 需要將 Cherry Studio 升級到 v1.1.18 或更高版本。

## 功能簡介

除咗手動安裝之外，Cherry Studio 仲內置咗 `@mcpmarket/mcp-auto-install` 工具，呢個係一個更方便嘅 MCP 伺服器安裝方式。你只需要喺支援 MCP 服務嘅大模型對話入面輸入相應指令就得。

{% hint style="warning" %}
**測試階段提醒：**

* `@mcpmarket/mcp-auto-install` 目前仍處於測試階段
* 效果取決於大模型嘅「智商」，有啲會自動添加，有啲仲係**需要喺 MCP 設定入面再手動更改某啲參數**
* 目前搜索源係由 @modelcontextprotocol 入面進行搜索，可以自行配置（下方說明）
  {% endhint %}

## 使用說明

例如，你可以輸入：

```
幫我安裝一個 filesystem mcp server
```

<figure><img src="/files/8c3666488e10e3f91d90a6140303506ec72753a6" alt=""><figcaption><p>輸入指令安裝 MCP 伺服器</p></figcaption></figure>

<figure><img src="/files/629dab91c21f05a1bf1a12f6f750095c351e3fb7" alt=""><figcaption><p>MCP 伺服器配置介面</p></figcaption></figure>

系統會自動識別你嘅需求，並透過 `@mcpmarket/mcp-auto-install` 完成安裝。呢個工具支援多種類型嘅 MCP 伺服器，包括但不限於：

* filesystem（檔案系統）
* fetch（網絡請求）
* sqlite（資料庫）
* 等等...

> MCP\_PACKAGE\_SCOPES 變量可以自訂 MCP 服務搜索源，預設值為：`@modelcontextprotocol`，可以自訂配置。

## `@mcpmarket/mcp-auto-install` 庫嘅介紹

{% hint style="info" %}
**預設配置參考：**

```json
// `axun-uUpaWEdMEMU8C61K` 為服務 id，自訂即可
"axun-uUpaWEdMEMU8C61K": {
  "name": "mcp-auto-install",
  "description": "Automatically install MCP services (Beta version)",
  "isActive": false,
  "registryUrl": "https://registry.npmmirror.com",
  "command": "npx",
  "args": [
    "-y",
    "@mcpmarket/mcp-auto-install",
    "connect",
    "--json"
  ],
  "env": {
    "MCP_REGISTRY_PATH": "詳情見https://www.npmjs.com/package/@mcpmarket/mcp-auto-install"
  },
  "disabledTools": []
}
```

`@mcpmarket/mcp-auto-install` 係一個開源嘅 npm 包，你可以喺 [npm 官方倉庫](https://www.npmjs.com/package/@mcpmarket/mcp-auto-install) 睇返佢嘅詳細資訊同使用文件。`@mcpmarket` 係 Cherry Studi 官方 MCP 服務集合。
{% endhint %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.cherry-ai.com/docs/zhong-wen-fan-ti/advanced-basic/mcp/auto-install.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.