Skip to main content
Glama
limithacker

百度图片搜索 MCP Server

by limithacker
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote

百度图片搜索 MCP Server

基于百度图片搜索 API 的 MCP (Model Context Protocol) 服务器。支持图片搜索、下载和格式转换一体化。

功能特性

  • 🔍 图片搜索：搜索百度图片，返回图片标题、URL、尺寸、格式等信息

  • 📥 一键下载：搜索同时可直接下载图片到本地

  • 🔄 格式转换：支持 JPEG、PNG、WebP 三种格式互转（基于 sharp）

  • 🖼️ 双源选择：可选择缩略图（thumburl，百度 CDN 稳定快速）或原图（objurl，可能有防盗链）

  • 📄 分页支持：支持自定义每页数量和页码

Related MCP server: mcp_search_images

安装

# 克隆仓库
git clone <repo-url>
cd mcp_image_bd_tools

# 安装依赖
npm install

# 构建
npm run build

配置 MCP

在 MCP 客户端配置中添加：

{
  "mcpServers": {
    "image-baidu": {
      "command": "node",
      "args": ["path/to/mcp_image_bd_tools/dist/index.js"]
    }
  }
}

使用

工具：search_images

参数说明

参数

类型

必填

默认值

说明

keyword

string

✅

-

搜索关键字

page

number

❌

1

页码，从 1 开始

perPage

number

❌

30

每页数量，最大 60

downloadPath

string

❌

-

下载目录路径。设置后自动下载图片

format

string

❌

-

输出格式：jpeg / png / webp（仅下载模式有效）

urlType

string

❌

thumb

图片源：thumb（缩略图）/ original（原图）

使用示例

仅搜索：

{
  "keyword": "维多利亚港",
  "page": 1,
  "perPage": 10
}

搜索并下载缩略图：

{
  "keyword": "故宫",
  "downloadPath": "./downloads",
  "perPage": 5
}

搜索并下载原图 + 转换为 JPEG：

{
  "keyword": "黄山",
  "downloadPath": "./downloads",
  "format": "jpeg",
  "urlType": "original",
  "perPage": 3
}

返回结果结构

{
  "keyword": "维多利亚港",
  "totalNum": 44880,
  "hasMore": true,
  "page": 1,
  "images": [
    {
      "index": 1,
      "thumbUrl": "https://img0.baidu.com/it/u=...",
      "originalUrl": "https://...",
      "sourceUrl": "http://...",
      "title": "图片标题",
      "width": 1920,
      "height": 1080,
      "format": "jpg",
      "isGif": false,
      "isCopyright": false,
      "detailUrl": "https://image.baidu.com/search/detail?...",
      "downloaded": true,
      "localPath": "downloads/1_图片标题_a1b2c3d4.jpg",
      "convertedFrom": "webp→jpeg"
    }
  ],
  "error": "有 1 张图片下载失败（如：...）"
}

技术架构

src/
├── index.ts          # MCP Server 入口，注册 search_images 工具
├── baidu-image.ts    # 百度图片搜索 API 封装（acjson 接口）
├── downloader.ts     # 图片下载 + sharp 格式转换模块
├── types.ts          # TypeScript 类型定义
└── utils.ts          # 工具函数（URL 构建、格式检测、随机 UA 等）

依赖

  • @modelcontextprotocol/sdk: MCP 协议 SDK

  • axios: HTTP 客户端

  • sharp: 高性能图片格式转换（JPEG/PNG/WebP）

技术实现细节

搜索 API

使用百度图片搜索的 acjson 接口：

GET https://image.baidu.com/search/acjson
  ?tn=resultjson_com
  &word={关键字}
  &pn={偏移量}
  &rn={每页数量}
  &gsm={pn的十六进制}
  &newReq=1

  • 已验证：无需 Cookie 即可调用，直接请求即可返回完整结果

  • 分页通过 pn（偏移量，步长为 rn）和 gsm（pn 的十六进制值）控制

  • 响应中包含 totalNum（总结果数）和 hasMore（是否有更多）

图片格式检测

下载图片时自动检测格式，优先级：

  1. 响应头 Content-Type

  2. 文件魔数（Magic Bytes）

如果设置了 format 参数且与实际格式不一致，自动使用 sharp 转换。

反爬策略

  • 随机 User-Agent（从多个真实浏览器 UA 中随机选择）

  • 正确的 Referer 头

  • 请求间添加 300-700ms 随机延迟

  • 并发下载数限制为 3

License

MIT

Available Tools

1 tool
search_imagesA

搜索百度图片，支持搜索、下载和格式转换一体化。

功能说明：

  1. 仅搜索模式：不指定 downloadPath，只返回图片信息（URL、尺寸、标题等）

  2. 搜索+下载模式：指定 downloadPath，自动下载图片到本地目录

  3. 格式转换：指定 format 参数，自动将图片转换为目标格式（仅下载模式有效）

使用示例：

  • 搜索图片：{ "keyword": "维多利亚港" }

  • 搜索第2页：{ "keyword": "长城", "page": 2 }

  • 下载缩略图：{ "keyword": "故宫", "downloadPath": "./downloads" }

  • 下载原图并转JPEG：{ "keyword": "黄山", "downloadPath": "./downloads", "format": "jpeg", "urlType": "original" }

ParametersJSON Schema
NameRequiredDescriptionDefault
pageNo页码，从 1 开始，默认 1
formatNo可选，指定输出图片格式。当下载的图片格式与指定格式不一致时自动转换。仅在设置 downloadPath 时有效
keywordYes搜索关键字（必填）
perPageNo每页数量，默认 30，最大 60
urlTypeNo选择下载使用的图片源。thumb=缩略图（默认，百度 CDN，稳定快速），original=原图（来源站点，可能有防盗链）。默认 thumbthumb
downloadPathNo可选，指定下载目录。设置后会将图片下载到该目录，否则只返回图片 URL 列表。例如：./downloads 或 /absolute/path
downloadFilenameNo可选，自定义下载文件名（不含扩展名，扩展名由 format 或图片原始格式决定）。多张图时自动追加索引后缀，例如指定 mypic 则保存为 mypic_1.jpg、mypic_2.jpg。仅在设置 downloadPath 时有效

TDQS

A4.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Without annotations, the description discloses important behaviors: search-only returns metadata (URLs, sizes, titles), download mode saves files, format conversion applies only to downloads, and urlType notes anti-leech risks on original images. It could add error handling or return format details, but core behavioral traits are well covered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise yet structured with numbered modes and short examples. It front-loads the summary and avoids redundancy with the schema, making every sentence functional.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has no output schema, but the description indicates what search-only mode returns. It doesn't specify download mode's return value or error cases, but overall it is quite complete for the tool's complexity, especially given the detailed input schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage, the schema already explains parameters, but the description enriches understanding by showing mode-dependent parameter interactions (e.g., format and downloadFilename only effective with downloadPath) and provides concrete examples that clarify parameter usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the tool searches Baidu images and supports search, download, and format conversion. It clearly differentiates the three operational modes (search-only, download, format conversion) with specific verbs and resources.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit instructions for when to use each mode: omit downloadPath for search-only, specify it for download, and only use format with download. Concrete examples illustrate typical usage scenarios, making it easy to select the correct configuration.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 1 tool updatev1.0.0
    • First observedsearch_images
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.6/5.0
Disambiguation5/5

Only one tool exists, so there is zero risk of confusion between tools. The tool's internal modes (search, download, convert) are clearly described and mutually exclusive.

Naming Consistency5/5

With a single tool named 'search_images', the naming is clean and follows a conventional verb_noun pattern. There are no inconsistent conventions to penalize.

Tool Count3/5

Having only one tool is borderline for a typical MCP server, but the tool bundles search, download, and format conversion into one interface, which fits the server's stated purpose of Baidu image search. Still, it feels slightly thin compared to servers with dedicated tools for each operation.

Completeness5/5

The single tool covers the core lifecycle of image searching: querying with pagination, downloading thumbnails or originals, and converting formats. There are no obvious missing operations for a search-focused server.

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/limithacker/mcp_image_bd_tools'

If you have feedback or need assistance with the MCP directory API, please join our Discord server