Skip to main content
Glama
deenesjakoruzh
yokingma

OneSearch MCP Server

by yokingma
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

🚀 OneSearch MCP 服务器：网页搜索、爬取、抓取与内容预处理

一个模型上下文协议 (MCP) 服务器实现，集成了多个搜索提供商，用于网页搜索、本地浏览器搜索，并利用 agent-browser 提供抓取功能。

功能特性

  • 网页搜索、抓取、爬取并预处理来自网站的内容。

  • 支持多种搜索引擎和网页抓取工具：SearXNG、Tavily、DuckDuckGo、Bing、Google、Zhipu (智谱)、Exa、Bocha (博查) 等。

  • 本地网页搜索（浏览器搜索），支持多种搜索引擎：Bing、Google、Baidu、Sogou 等。

    • 使用 agent-browser 进行浏览器自动化。

    • 免费，无需 API 密钥。

  • 已启用工具： one_search、one_scrape、one_map、one_extract

Related MCP server: Firecrawl MCP Server

从 v1.1.0 及更早版本迁移

v1.1.0 中的重大变更：

  • 移除 Firecrawl：Firecrawl 集成已被移除，转而使用 agent-browser，它提供了类似的功能且无需外部 API 服务。

  • 新的浏览器要求：必须安装 Chromium 浏览器（请参阅“先决条件”部分）。

  • 环境变量：不再使用 FIRECRAWL_API_URL 和 FIRECRAWL_API_KEY。

变更内容：

  • one_scrape 和 one_map 现在使用 agent-browser 而非 Firecrawl

  • one_extract 现在预处理多 URL 页面内容以供下游分析，而不是执行内置的 LLM 提取

  • 所有基于浏览器的操作现在都在本地处理，提供更好的隐私保护且无 API 成本

迁移步骤：

  1. 安装 Chromium 浏览器（请参阅“先决条件”）

  2. 从环境变量中移除 FIRECRAWL_API_URL 和 FIRECRAWL_API_KEY

  3. 更新至最新版本：npm install -g one-search-mcp@latest

先决条件

浏览器要求：此服务器使用 agent-browser 进行网页抓取和本地搜索，需要基于 Chromium 的浏览器。

好消息：服务器将自动检测并使用您系统中已安装的浏览器：

  • ✅ Google Chrome

  • ✅ Microsoft Edge

  • ✅ Chromium

  • ✅ Google Chrome Canary

如果您没有安装上述任何浏览器，您可以：

# Option 1: Install Google Chrome (Recommended)
# Download from: https://www.google.com/chrome/

# Option 2: Install Microsoft Edge
# Download from: https://www.microsoft.com/edge

# Option 3: Install Chromium via agent-browser
npx agent-browser install

# Option 4: Install Chromium directly
# Download from: https://www.chromium.org/getting-involved/download-chromium/

安装

使用 Claude Code CLI（推荐）

# Add to Claude Code with default settings (local search)
claude mcp add one-search-mcp -- npx -y one-search-mcp

# Add with custom search provider (e.g., SearXNG)
claude mcp add one-search-mcp -e SEARCH_PROVIDER=searxng -e SEARCH_API_URL=http://127.0.0.1:8080 -- npx -y one-search-mcp

# Add with Tavily API
claude mcp add one-search-mcp -e SEARCH_PROVIDER=tavily -e SEARCH_API_KEY=your_api_key -- npx -y one-search-mcp

手动安装

# Install globally (Optional)
npm install -g one-search-mcp

# Or run directly with npx
npx -y one-search-mcp

使用 Docker

Docker 镜像已预装所有依赖项（Chromium 浏览器），无需额外设置。

拉取镜像：

# From GitHub Container Registry
docker pull ghcr.io/yokingma/one-search-mcp:latest

# Or from Docker Hub
docker pull zacma/one-search-mcp:latest

配置 Claude Desktop：

{
  "mcpServers": {
    "one-search-mcp": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "ghcr.io/yokingma/one-search-mcp:latest"],
      "env": {
        "SEARCH_PROVIDER": "local"
      }
    }
  }
}

使用自定义搜索提供商：

{
  "mcpServers": {
    "one-search-mcp": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "SEARCH_PROVIDER=tavily",
        "-e", "SEARCH_API_KEY=your_api_key",
        "ghcr.io/yokingma/one-search-mcp:latest"
      ]
    }
  }
}

环境变量

搜索引擎：

  • SEARCH_PROVIDER（可选）：要使用的搜索提供商，支持 searxng、duckduckgo、bing、tavily、google、zhipu、exa、bocha、local，默认为 local。

  • SEARCH_API_URL（可选）：SearxNG API 的 URL，或 google 的 Google 自定义搜索引擎 ID。

  • SEARCH_API_KEY（可选）：搜索提供商的 API 密钥，tavily、bing、google、zhipu、exa、bocha 需要此项。

// supported search providers
export type SearchProvider = 'searxng' | 'duckduckgo' | 'bing' | 'tavily' | 'google' | 'zhipu' | 'exa' | 'bocha' | 'local';

搜索提供商配置

提供商

是否需要 API 密钥

是否需要 API URL

备注

local

否

否

免费，使用浏览器自动化

duckduckgo

否

否

免费，无需 API 密钥

searxng

可选

是

自托管元搜索引擎

bing

是

否

Bing 搜索 API

tavily

是

否

Tavily API

google

是

是（搜索引擎 ID）

Google 自定义搜索

zhipu

是

否

智谱 AI

exa

是

否

Exa AI

bocha

是

否

博查 AI

其他 MCP 客户端的配置

Claude Desktop

添加到您的 Claude Desktop 配置文件中：

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "one-search-mcp": {
      "command": "npx",
      "args": ["-y", "one-search-mcp"],
      "env": {
        "SEARCH_PROVIDER": "local"
      }
    }
  }
}

Cursor

添加到您的 mcp.json 文件中：

{
  "mcpServers": {
    "one-search-mcp": {
      "command": "npx",
      "args": ["-y", "one-search-mcp"],
      "env": {
        "SEARCH_PROVIDER": "local"
      }
    }
  }
}

Windsurf

添加到您的 ./codeium/windsurf/model_config.json 文件中：

{
  "mcpServers": {
    "one-search-mcp": {
      "command": "npx",
      "args": ["-y", "one-search-mcp"],
      "env": {
        "SEARCH_PROVIDER": "local"
      }
    }
  }
}

自托管 SearXNG（可选）

如果您想使用 SearXNG 作为搜索提供商，可以通过 Docker 在本地部署：

先决条件：

  • 已安装并运行 Docker（版本 20.10.0 或更高）

  • 至少 4GB 可用内存

快速开始：

# Clone SearXNG Docker repository
git clone https://github.com/searxng/searxng-docker.git
cd searxng-docker

# Start SearXNG
docker compose up -d

部署后，SearXNG 默认将在 http://127.0.0.1:8080 可用。

配置 OneSearch 使用 SearXNG：

# Set environment variables
export SEARCH_PROVIDER=searxng
export SEARCH_API_URL=http://127.0.0.1:8080

有关更多详细信息，请参阅 官方 SearXNG Docker 文档。

故障排除

找不到浏览器错误

如果您看到类似“Browser not found”的错误，说明服务器无法检测到任何已安装的基于 Chromium 的浏览器。请安装以下其中之一：

或者通过 agent-browser 安装：

npx agent-browser install

许可证

MIT 许可证 - 详情请参阅 LICENSE 文件。

Available Tools

4 tools
one_extractA

Fetch and preprocess page content from one or more URLs. Returns cleaned text blocks that can be passed to downstream tools or models.

ParametersJSON Schema
NameRequiredDescriptionDefault
urlsYesList of URLs to extract information from

TDQS

A3.5/5.0
Behavior2/5

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

No annotations provided, so description carries full burden. 'Returns cleaned text blocks' hints at preprocessing but does not detail cleaning steps, error handling, or auth needs.

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?

Two concise sentences, front-loaded with action, then output. No wasted words.

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

Completeness3/5

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

For a simple tool (1 param, no output schema), description adequately covers purpose and output. Lacks details on cleaning specifics, error handling, or limits.

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?

Schema covers parameter with 100% coverage. Description adds value by specifying preprocessing and output type ('cleaned text blocks'), going beyond schema's 'extract information'.

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?

Description clearly states the verb 'fetch and preprocess' and the resource 'page content from URLs'. Differentiates from siblings: one_map, one_scrape, one_search.

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

Usage Guidelines2/5

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

No explicit when-to-use or when-not-to-use guidance. Mentions downstream use but lacks context for choosing over siblings.

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

one_mapA

Discover URLs from a starting point by loading a page in the browser and extracting links from its HTML.

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesStarting URL for URL discovery
limitNoMaximum number of URLs to return
searchNoOptional search term to filter URLs
includeSubdomainsNoInclude URLs from subdomains in results

TDQS

A3.9/5.0
Behavior3/5

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

With no annotations, the description carries the full burden of behavioral disclosure. It does disclose the core mechanism—loading a page in the browser and extracting links from its HTML—but it omits important details such as whether the crawl is recursive, whether subdomains are included by default, or any performance/rate implications.

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 a single, front-loaded sentence that immediately conveys the main action and mechanism. It contains no filler, repetition, or unnecessary detail.

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

Completeness3/5

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

The description is minimal but sufficient for a simple one-page link extractor. However, with no output schema, it leaves ambiguity about return format and whether discovery is recursive or limited to the initial page, which is important for a mapping tool with four parameters.

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

Parameters3/5

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

Schema coverage is 100%, so the description does not need to add much parameter detail. It simply reinforces 'starting point' for the url parameter and adds no new meaning beyond what the schema already provides.

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 states a specific action: discover URLs from a starting point by loading a page in the browser and extracting HTML links. This clearly distinguishes it from sibling tools like one_extract, one_search, and one_scrape, which focus on other tasks.

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

Usage Guidelines4/5

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

The description gives clear context that this tool is for mapping/discovering URLs from a starting page, which implies when it should be selected. However, it does not explicitly mention alternatives or state when not to use it, so it falls short of a 5.

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

one_scrapeA

Scrape a single webpage and return markdown, HTML, links, or a screenshot. Supports navigation timeout, TLS verification control, full-page screenshots, bounded pre-scrape actions, and advanced executeJavascript only when allowExecuteJavascript is true.

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesThe URL to scrape
actionsNoList of pre-scrape actions to run before content capture. Standard actions are bounded; executeJavascript requires allowExecuteJavascript: true.
formatsNoContent formats to extract (default: ['markdown'])
timeoutNoMaximum time in milliseconds to wait for the page to load
waitForNoTime in milliseconds to wait for dynamic content to load
skipTlsVerificationNoSkip TLS certificate verification
allowExecuteJavascriptNoMust be true when actions contain executeJavascript. Use only for advanced page-side scripting.

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It notably discloses support for navigation timeout, TLS verification control, full-page screenshots, bounded pre-scrape actions, and the gating of executeJavascript. It does not mention error behavior or return structure, but these are less critical for a scraping tool.

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 at two sentences, front-loaded with the core purpose, and every clause adds value (outputs, timeout, TLS, screenshots, actions). There is no fluff or redundancy.

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

Completeness3/5

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

Given the tool's complexity (7 parameters, no output schema, no annotations), the description provides a good overview of capabilities but lacks details on return value structure, error handling, or pagination/navigation behavior. It is adequate but has clear gaps, especially regarding what the returned data looks like for each format.

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

Parameters3/5

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

Since schema description coverage is 100%, the baseline is 3. The description adds some context by mentioning 'bounded pre-scrape actions' and the executeJavascript requirement, which aligns with the actions and allowExecuteJavascript parameters. However, it does not add significant syntax or format details beyond what the schema already provides.

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

Purpose4/5

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

The description clearly identifies the tool's action ('Scrape a single webpage') and its outputs ('markdown, HTML, links, or a screenshot'), which distinguishes it from the sibling tools by focusing on single-page scraping. It is a specific verb+resource statement, though it does not explicitly contrast with siblings like 'one_extract'.

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

Usage Guidelines3/5

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

The description implies usage for scraping a single webpage and mentions the prerequisite for executeJavascript ('only when allowExecuteJavascript is true'). However, it does not explicitly state when to choose this tool over alternatives such as one_extract, one_search, or one_map, nor does it provide exclusion criteria.

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.

  1. 2 tool updatesv1.2.4
    • Changedone_map2 fields changed
      • removedInput schema / properties / ignoreSitemap
        Removed value: -{
-  "description": "Skip sitemap.xml discovery and only use HTML links",
-  "type": "boolean"
-}
      • removedInput schema / properties / sitemapOnly
        Removed value: -{
-  "description": "Only use sitemap.xml for discovery, ignore HTML links",
-  "type": "boolean"
-}
    • Changedone_scrape11 fields changed
      • changedInput schema / properties / actions / description
        Previous value: -"List of actions to perform before scraping"New value: +"List of pre-scrape actions to run before content capture. Standard actions are bounded; executeJavascript requires allowExecuteJavascript: true."
      • changedInput schema / properties / actions / items / anyOf
        Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "milliseconds": {
-        "description": "Time to wait in milliseconds",
-        "type": "number"
-      },
-      "type": {
-        "const": "wait",
-        "type": "string"
-      }
-    },
-    "required": [
-      "type",
-      "milliseconds"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "selector": {
-        "description": "CSS selector for the target element",
-        "type": "string"
-      },
-      "type": {
-        "const": "click",
-        "type": "string"
-      }
-    },
-    "required": [
-      "type",
-      "selector"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "fullPage": {
-        "description": "Take full page screenshot",
-        "type": "boolean"
-      },
-      "type": {
-        "const": "screenshot",
-        "type": "string"
-      }
-    },
-    "required": [
-      "type"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "selector": {
-        "description": "CSS selector for the target element",
-        "type": "string"
-      },
-      "text": {
-        "description": "Text to write",
-        "type": "string"
-      },
-      "type": {
-        "const": "write",
-        "type": "string"
-      }
-    },
-    "required": [
-      "type",
-      "selector",
-      "text"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "key": {
-        "description": "Key to press",
-        "type": "string"
-      },
-      "type": {
-        "const": "press",
-        "type": "string"
-      }
-    },
-    "required": [
-      "type",
-      "key"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "direction": {
-        "description": "Scroll direction",
-        "enum": [
-          "up",
-          "down"
-        ],
-        "type": "string"
-      },
-      "type": {
-        "const": "scroll",
-        "type": "string"
-      }
-    },
-    "required": [
-      "type",
-      "direction"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "type": {
-        "const": "scrape",
-        "type": "string"
-      }
-    },
-    "required": [
-      "type"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "script": {
-        "description": "JavaScript code to execute",
-        "type": "string"
-      },
-      "type": {
-        "const": "executeJavascript",
-        "type": "string"
-      }
-    },
-    "required": [
-      "type",
-      "script"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "milliseconds": {
+        "description": "Time to wait in milliseconds",
+        "type": "number"
+      },
+      "type": {
+        "const": "wait",
+        "type": "string"
+      }
+    },
+    "required": [
+      "type",
+      "milliseconds"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "selector": {
+        "description": "CSS selector for the target element",
+        "type": "string"
+      },
+      "type": {
+        "const": "click",
+        "type": "string"
+      }
+    },
+    "required": [
+      "type",
+      "selector"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "selector": {
+        "description": "CSS selector for the target element",
+        "type": "string"
+      },
+      "text": {
+        "description": "Text to write",
+        "type": "string"
+      },
+      "type": {
+        "const": "write",
+        "type": "string"
+      }
+    },
+    "required": [
+      "type",
+      "selector",
+      "text"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "key": {
+        "description": "Key to press",
+        "type": "string"
+      },
+      "type": {
+        "const": "press",
+        "type": "string"
+      }
+    },
+    "required": [
+      "type",
+      "key"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "direction": {
+        "description": "Scroll direction",
+        "enum": [
+          "up",
+          "down"
+        ],
+        "type": "string"
+      },
+      "type": {
+        "const": "scroll",
+        "type": "string"
+      }
+    },
+    "required": [
+      "type",
+      "direction"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "script": {
+        "description": "JavaScript code to execute",
+        "type": "string"
+      },
+      "type": {
+        "const": "executeJavascript",
+        "type": "string"
+      }
+    },
+    "required": [
+      "type",
+      "script"
+    ],
+    "type": "object"
+  }
+]
      • addedInput schema / properties / allowExecuteJavascript
        Added value: +{
+  "description": "Must be true when actions contain executeJavascript. Use only for advanced page-side scripting.",
+  "type": "boolean"
+}
      • removedInput schema / properties / excludeTags
        Removed value: -{
-  "description": "HTML tags to exclude from extraction",
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}
      • removedInput schema / properties / extract
        Removed value: -{
-  "additionalProperties": false,
-  "description": "Configuration for structured data extraction",
-  "properties": {
-    "prompt": {
-      "description": "User prompt for LLM extraction",
-      "type": "string"
-    },
-    "schema": {
-      "additionalProperties": {},
-      "description": "Schema for structured data extraction",
-      "type": "object"
-    },
-    "systemPrompt": {
-      "description": "System prompt for LLM extraction",
-      "type": "string"
-    }
-  },
-  "type": "object"
-}
      • changedInput schema / properties / formats / items / enum
        Previous value: -[
-  "markdown",
-  "html",
-  "rawHtml",
-  "screenshot",
-  "links",
-  "screenshot@fullPage",
-  "extract"
-]New value: +[
+  "markdown",
+  "html",
+  "rawHtml",
+  "screenshot",
+  "links",
+  "screenshot@fullPage"
+]
      • removedInput schema / properties / includeTags
        Removed value: -{
-  "description": "HTML tags to specifically include in extraction",
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}
      • removedInput schema / properties / location
        Removed value: -{
-  "additionalProperties": false,
-  "description": "Location settings for scraping",
-  "properties": {
-    "country": {
-      "description": "Country code for geolocation",
-      "type": "string"
-    },
-    "languages": {
-      "description": "Language codes for content",
-      "items": {
-        "type": "string"
-      },
-      "type": "array"
-    }
-  },
-  "type": "object"
-}
      • removedInput schema / properties / mobile
        Removed value: -{
-  "description": "Use mobile viewport",
-  "type": "boolean"
-}
      • removedInput schema / properties / onlyMainContent
        Removed value: -{
-  "description": "Extract only the main content, filtering out navigation, footers, etc.",
-  "type": "boolean"
-}
      • removedInput schema / properties / removeBase64Images
        Removed value: -{
-  "description": "Remove base64 encoded images from output",
-  "type": "boolean"
-}
  2. 4 tool updatesv1.2.1
    • Changedone_extract8 fields changed
      • addedInput schema / $schema
        Added value: +"http://json-schema.org/draft-07/schema#"
      • addedInput schema / additionalProperties
        Added value: +false
      • removedInput schema / properties / allowExternalLinks
        Removed value: -{
-  "description": "Allow extraction from external links",
-  "type": "boolean"
-}
      • removedInput schema / properties / enableWebSearch
        Removed value: -{
-  "description": "Enable web search for additional context",
-  "type": "boolean"
-}
      • removedInput schema / properties / includeSubdomains
        Removed value: -{
-  "description": "Include subdomains in extraction",
-  "type": "boolean"
-}
      • removedInput schema / properties / prompt
        Removed value: -{
-  "description": "Prompt for the LLM extraction",
-  "type": "string"
-}
      • removedInput schema / properties / schema
        Removed value: -{
-  "description": "JSON schema for structured data extraction",
-  "type": "object"
-}
      • removedInput schema / properties / systemPrompt
        Removed value: -{
-  "description": "System prompt for LLM extraction",
-  "type": "string"
-}
    • Changedone_map2 fields changed
      • addedInput schema / $schema
        Added value: +"http://json-schema.org/draft-07/schema#"
      • addedInput schema / additionalProperties
        Added value: +false
    • Changedone_scrape9 fields changed
      • addedInput schema / $schema
        Added value: +"http://json-schema.org/draft-07/schema#"
      • addedInput schema / additionalProperties
        Added value: +false
      • addedInput schema / properties / actions / items / anyOf
        Added value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "milliseconds": {
+        "description": "Time to wait in milliseconds",
+        "type": "number"
+      },
+      "type": {
+        "const": "wait",
+        "type": "string"
+      }
+    },
+    "required": [
+      "type",
+      "milliseconds"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "selector": {
+        "description": "CSS selector for the target element",
+        "type": "string"
+      },
+      "type": {
+        "const": "click",
+        "type": "string"
+      }
+    },
+    "required": [
+      "type",
+      "selector"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "fullPage": {
+        "description": "Take full page screenshot",
+        "type": "boolean"
+      },
+      "type": {
+        "const": "screenshot",
+        "type": "string"
+      }
+    },
+    "required": [
+      "type"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "selector": {
+        "description": "CSS selector for the target element",
+        "type": "string"
+      },
+      "text": {
+        "description": "Text to write",
+        "type": "string"
+      },
+      "type": {
+        "const": "write",
+        "type": "string"
+      }
+    },
+    "required": [
+      "type",
+      "selector",
+      "text"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "key": {
+        "description": "Key to press",
+        "type": "string"
+      },
+      "type": {
+        "const": "press",
+        "type": "string"
+      }
+    },
+    "required": [
+      "type",
+      "key"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "direction": {
+        "description": "Scroll direction",
+        "enum": [
+          "up",
+          "down"
+        ],
+        "type": "string"
+      },
+      "type": {
+        "const": "scroll",
+        "type": "string"
+      }
+    },
+    "required": [
+      "type",
+      "direction"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "type": {
+        "const": "scrape",
+        "type": "string"
+      }
+    },
+    "required": [
+      "type"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "script": {
+        "description": "JavaScript code to execute",
+        "type": "string"
+      },
+      "type": {
+        "const": "executeJavascript",
+        "type": "string"
+      }
+    },
+    "required": [
+      "type",
+      "script"
+    ],
+    "type": "object"
+  }
+]
      • removedInput schema / properties / actions / items / properties
        Removed value: -{
-  "direction": {
-    "description": "Scroll direction",
-    "enum": [
-      "up",
-      "down"
-    ],
-    "type": "string"
-  },
-  "fullPage": {
-    "description": "Take full page screenshot",
-    "type": "boolean"
-  },
-  "key": {
-    "description": "Key to press (for press action)",
-    "type": "string"
-  },
-  "milliseconds": {
-    "description": "Time to wait in milliseconds (for wait action)",
-    "type": "number"
-  },
-  "script": {
-    "description": "JavaScript code to execute",
-    "type": "string"
-  },
-  "selector": {
-    "description": "CSS selector for the target element",
-    "type": "string"
-  },
-  "text": {
-    "description": "Text to write (for write action)",
-    "type": "string"
-  },
-  "type": {
-    "description": "Type of action to perform",
-    "enum": [
-      "wait",
-      "click",
-      "screenshot",
-      "write",
-      "press",
-      "scroll",
-      "scrape",
-      "executeJavascript"
-    ],
-    "type": "string"
-  }
-}
      • removedInput schema / properties / actions / items / required
        Removed value: -[
-  "type"
-]
      • removedInput schema / properties / actions / items / type
        Removed value: -"object"
      • addedInput schema / properties / extract / additionalProperties
        Added value: +false
      • addedInput schema / properties / extract / properties / schema / additionalProperties
        Added value: +{}
      • addedInput schema / properties / location / additionalProperties
        Added value: +false
    • Changedone_search2 fields changed
      • addedInput schema / $schema
        Added value: +"http://json-schema.org/draft-07/schema#"
      • addedInput schema / additionalProperties
        Added value: +false
  3. 4 tool updates
    • First observedone_extract
    • First observedone_map
    • First observedone_scrape
    • First observedone_search
Deploy Server
Let your AI agent see the webWeb-to-screenshot MCP for Claude, Cursor and Codex. No cookie banners. Free to start.snap-render.comAd

TDQS

A3.7/5.0

Scored across 4 tools

Disambiguation4/5

Each tool has a distinct core function: search returns SERP results, extract preprocesses multiple URLs, scrape handles single-page advanced operations, and map discovers links. There is minor overlap between extract and scrape for fetching page content, but their descriptions make the intended use cases clear.

Naming Consistency5/5

All tool names follow the consistent pattern 'one_' prefix followed by a lowercase action verb (search, extract, scrape, map), with underscores between words. No mixed conventions or camelCase.

Tool Count5/5

Four tools is well within the ideal range for a focused search/scraping server. Each tool covers a distinct aspect of web research, making the set feel appropriately scoped without being bloated.

Completeness4/5

The tool set covers the primary workflows: searching, extracting content, single-page scraping with advanced options, and link discovery. Minor gaps exist, such as no dedicated batch scraping tool, but the combined functionality handles most common use cases.

Maintenance

ActivityStale
ResponsivenessWithin a week

Resources

Related MCP Connectors

Related MCP Servers

  • Firecrawl MCP Server

    ampcome-mcps
    A
    license
    A
    quality
    D
    maintenance
    A Model Context Protocol server that enables web scraping, crawling, and content extraction capabilities through integration with Firecrawl.
    8
    191,569 npm
    2
    MIT

Appeared in Searches