DataForSEO

dataforseo/mcp-server-typescript

The DataForSEO MCP server provides AI assistants with direct access to DataForSEO's SEO and marketing analytics APIs. Built with TypeScript, it exposes tools across four main modules: SERP for search engine results, Keywords Data for keyword research, OnPage for content analysis, and DataForSEO Labs for competitive research and market analysis. The server handles authentication with the DataForSEO API, implements field filtering for focused data retrieval, and follows a modular architecture that makes it easy to extend with additional tools. This implementation is particularly valuable for digital marketers and SEO professionals who need to analyze search rankings, research keywords, evaluate competitors, and optimize content without leaving their AI assistant conversation.

真实 I/O · 已连通 ✓

启动 server · tools/list · 89 个工具 · dataforseo-mcp-server

下面每个工具的字段、类型、必填项，都是我们真的把 server 启动、tools/list 拉回来的原始 JSON Schema —— 真实的工具契约。注意：下方「示例调用」是按 schema 自动生成的演示，不是真实调用的返回。

ai_opt_kw_data_loc_and_lang

Utility tool for 'AI Optimization Keyword Data Locations and Languages' (ai_opt_kw_data_loc_and_lang) to get list of availible locations and languages

Input（真实 schema）

无参数

示例调用

{
  "tool": "ai_opt_kw_data_loc_and_lang",
  "arguments": {}
}

ai_optimization_keyword_data_search_volume

This endpoint provides search volume data for your target keywords, reflecting their estimated usage in AI LLMs

Input（真实 schema）

keywordsarrayrequired

Keywords. The maximum number of keywords you can specify: 1000

location_namestring

full name of the location, example: 'United Kingdom', 'United States'

language_codestringrequired

Search engine language code (e.g., 'en')

示例调用

{
  "tool": "ai_optimization_keyword_data_search_volume",
  "arguments": {
    "keywords": [],
    "language_code": "…"
  }
}

ai_optimization_llm_models

Utility tool for ai_optimization_llm_response to get list of availible locations and languages

Input（真实 schema）

llm_typestringrequired

type of llm. Must be one of: 'claude', 'gemini', 'chat_gpt', 'perplexity'

示例调用

{
  "tool": "ai_optimization_llm_models",
  "arguments": {
    "llm_type": "…"
  }
}

ai_optimization_llm_response

This endpoint allows you to retrieve structured responses from a specific AI model, based on the input parameters

Input（真实 schema）

llm_typestringrequired

type of llm. Must be one of: 'claude', 'gemini', 'chat_gpt', 'perplexity'

user_promptstringrequired

Prompt for the AI model. The question or task you want to send to the AI model. You can specify up to 500 characters in the user_prompt field

model_namestringrequired

name of the AI model. consists of the actual model name and version name. if not sure which model to use, first call the ai_optimization_llm_models tool to get list of available models for the specified llm_type

temperaturenumber

randomness of the AI response optional field higher values make output more diverse; lower values make output more focused;

top_pnumber

diversity of the AI response, optional field, controls diversity of the response by limiting token selection;

web_searchboolean

enable web search for current information. When enabled, the AI model can access and cite current web information;

示例调用

{
  "tool": "ai_optimization_llm_response",
  "arguments": {
    "llm_type": "…",
    "user_prompt": "…",
    "model_name": "…"
  }
}

ai_optimization_llm_mentions_filters

This endpoint provides all the necessary information about filters that can be used with AI Optimization LLM Mentions API endpoints

Input（真实 schema）

无参数

示例调用

{
  "tool": "ai_optimization_llm_mentions_filters",
  "arguments": {}
}

ai_opt_llm_ment_loc_and_lang

Utility tool for 'AI Optimization LLM Mentions Locations and Languages' (ai_opt_llm_ment_loc_and_lang) to get list of available locations and languages

Input（真实 schema）

无参数

示例调用

{
  "tool": "ai_opt_llm_ment_loc_and_lang",
  "arguments": {}
}

ai_opt_llm_ment_search

This endpoint provides aggregated LLM mentions metrics grouped by the most frequently mentioned pages for the specified target

Input（真实 schema）

targetarrayrequired

Array of target objects to search for LLM mentions. Each object must contain either 'domain' or 'keyword'. Maximum number of targets: 1000

location_namestring

full name of the location, example: 'United Kingdom', 'United States'

language_codestring

Search engine language code (e.g., 'en')

platformstring

Platform to search for LLM mentions

filtersarray

Array-based filter expression. A single condition is a 3-element array: [field, operator, value]. Combine conditions with ["and"|"or"] between them: [condition, "and", condition]. Max 8 filters. Operators: regex, not_regex, <, <=, >, >=, =,

order_byarray

resuresults sorting rules optional field you can use the same values as in the filters array to sort the results possible sorting types: asc – results will be sorted in the ascending order desc – results will be sorted in the descending ord

limitnumber

Number of results to return. Default is 10, maximum is 1000.

示例调用

{
  "tool": "ai_opt_llm_ment_search",
  "arguments": {
    "target": []
  }
}

ai_opt_llm_ment_agg_metrics

This endpoint provides aggregated metrics for mentions of the keywords or domains specified in the target array of the request.

Input（真实 schema）

targetarrayrequired

Array of target objects to search for LLM mentions. Each object must contain either 'domain' or 'keyword'. Maximum number of targets: 1000

location_namestring

full name of the location, example: 'United Kingdom', 'United States'

language_codestring

Search engine language code (e.g., 'en')

platformstring

Platform to search for LLM mentions

filtersarray

internal_list_limitnumber

Internal parameter to limit the number of items processed. Not exposed to end-users.

示例调用

{
  "tool": "ai_opt_llm_ment_agg_metrics",
  "arguments": {
    "target": []
  }
}

ai_opt_llm_ment_cross_agg_metrics

This endpoint provides aggregated metrics grouped by custom keys for mentions of the keywords or domains specified in the target array of the request

Input（真实 schema）

targetsarrayrequired

array of objects containing target entities with aggregation keys. you can specify up to 10, but not less than 2

location_namestring

full name of the location, example: 'United Kingdom', 'United States'

language_codestring

Search engine language code (e.g., 'en')

platformstring

Platform to search for LLM mentions

filtersarray

internal_list_limitnumber

Internal parameter to limit the number of items processed. Not exposed to end-users.

示例调用

{
  "tool": "ai_opt_llm_ment_cross_agg_metrics",
  "arguments": {
    "targets": []
  }
}

ai_opt_llm_ment_top_domains

This endpoint provides aggregated LLM mentions metrics grouped by the most frequently mentioned domains for the specified target

Input（真实 schema）

targetarrayrequired

Array of target objects to search for LLM mentions. Each object must contain either 'domain' or 'keyword'. Maximum number of targets: 1000

location_namestring

full name of the location, example: 'United Kingdom', 'United States'

language_codestring

Search engine language code (e.g., 'en')

platformstring

Platform to search for LLM mentions

links_scopestring

specifies which links will be used to extract domains and aggregation

initial_dataset_filtersarray

items_list_limitnumber

maximum number of results in the items array, min value is 1, max value is 10

internal_list_limitnumber

maximum number of elements within internal arrays, min value is 1, max value is 10

示例调用

{
  "tool": "ai_opt_llm_ment_top_domains",
  "arguments": {
    "target": []
  }
}

ai_opt_llm_ment_top_pages

This endpoint provides aggregated LLM mentions metrics grouped by the most frequently mentioned pages for the specified target

Input（真实 schema）

targetarrayrequired

Array of target objects to search for LLM mentions. Each object must contain either 'domain' or 'keyword'. Maximum number of targets: 1000

location_namestring

full name of the location, example: 'United Kingdom', 'United States'

language_codestring

Search engine language code (e.g., 'en')

platformstring

Platform to search for LLM mentions

links_scopestring

specifies which links will be used to extract domains and aggregation

initial_dataset_filtersarray

items_list_limitnumber

maximum number of results in the items array, min value is 1, max value is 10

internal_list_limitnumber

maximum number of elements within internal arrays, min value is 1, max value is 10

示例调用

{
  "tool": "ai_opt_llm_ment_top_pages",
  "arguments": {
    "target": []
  }
}

ai_optimization_chat_gpt_scraper

This endpoint provides results from ChatGPT searches

Input（真实 schema）

keywordstringrequired

keyword required field you can specify up to 2000 characters in the keyword field all %## will be decoded (plus character ‘+’ will be decoded to a space character) if you need to use the “%” character for your keyword, please specify it as

location_namestring

full name of the location, example: 'United Kingdom', 'United States'

language_codestringrequired

Search engine language code (e.g., 'en')

force_web_searchboolean

force AI agent to use web search

示例调用

{
  "tool": "ai_optimization_chat_gpt_scraper",
  "arguments": {
    "keyword": "…",
    "language_code": "…"
  }
}

ai_optimization_chat_gpt_scraper_locations

Utility tool for ai_optimization_chat_gpt_scraper to get list of available locations

Input（真实 schema）

country_iso_codestring

ISO 3166-1 alpha-2 country code, for example: US, GB, MT

location_namestring

Name of location or it`s part.

示例调用

{
  "tool": "ai_optimization_chat_gpt_scraper_locations",
  "arguments": {
    "country_iso_code": "…",
    "location_name": "…"
  }
}

serp_organic_live_advanced

Get organic search results for a keyword in specified search engine

Input（真实 schema）

search_enginestring

search engine name, one of: google, yahoo, bing.

location_namestring

full name of the location required field Location format - hierarchical, comma-separated (from most specific to least) Can be one of: 1. Country only: "United States" 2. Region,Country: "California,United States" 3. City,Region,Country:

depthnumber

parsing depth optional field number of results in SERP

language_codestringrequired

search engine language code (e.g., 'en')

keywordstringrequired

Search keyword

max_crawl_pagesnumber

page crawl limit optional field number of search results pages to crawl max value: 100 Note: the max_crawl_pages and depth parameters complement each other

devicestring

device type optional field can take the values:desktop, mobile default value: desktop

people_also_ask_click_depthnumber

clicks on the corresponding element specify the click depth on the people_also_ask element to get additional people_also_ask_element items;

示例调用

{
  "tool": "serp_organic_live_advanced",
  "arguments": {
    "language_code": "…",
    "keyword": "…"
  }
}

serp_locations

Utility tool for serp_organic_live_advanced to get list of availible locations.

Input（真实 schema）

search_enginestring

search engine name, one of: google, yahoo, bing.

country_iso_codestringrequired

ISO 3166-1 alpha-2 country code, for example: US, GB, MT

location_typestring

Type of location. Possible variants: 'TV Region','Postal Code','Neighborhood','Governorate','National Park','Quarter','Canton','Airport','Okrug','Prefecture','City','Country','Province','Barrio','Sub-District','Congressional District','Muni

location_namestring

Name of location or it`s part.

示例调用

{
  "tool": "serp_locations",
  "arguments": {
    "country_iso_code": "…"
  }
}

serp_youtube_locations

Utility tool to get list of available locations for: serp_youtube_organic_live_advanced, serp_youtube_video_info_live_advanced, serp_youtube_video_comments_live_advanced, serp_youtube_video_subtitles_live_advanced.

Input（真实 schema）

country_iso_codestringrequired

ISO 3166-1 alpha-2 country code, for example: US, GB, MT

location_typestring

location_namestring

Name of location or it`s part.

示例调用

{
  "tool": "serp_youtube_locations",
  "arguments": {
    "country_iso_code": "…"
  }
}

serp_youtube_organic_live_advanced

provides top 20 blocks of youtube search engine results for a keyword

Input（真实 schema）

keywordstringrequired

Search keyword

location_namestringrequired

language_codestringrequired

search engine language code (e.g., 'en')

devicestring

device type optional field can take the values:desktop, mobile default value: desktop

osstring

device operating system optional field if you specify desktop in the device field, choose from the following values: windows, macos default value: windows if you specify mobile in the device field, choose from the following values: android,

block_depthnumber

parsing depth optional field number of blocks of results in SERP max value: 700

示例调用

{
  "tool": "serp_youtube_organic_live_advanced",
  "arguments": {
    "keyword": "…",
    "location_name": "…",
    "language_code": "…"
  }
}

serp_youtube_video_info_live_advanced

provides data on the video you specify

Input（真实 schema）

video_idstringrequired

ID of the video

location_namestringrequired

language_codestringrequired

search engine language code (e.g., 'en')

devicestring

device type optional field can take the values:desktop, mobile default value: desktop

osstring

示例调用

{
  "tool": "serp_youtube_video_info_live_advanced",
  "arguments": {
    "video_id": "…",
    "location_name": "…",
    "language_code": "…"
  }
}

serp_youtube_video_comments_live_advanced

provides data on the video comments you specify

Input（真实 schema）

video_idstringrequired

ID of the video

location_namestringrequired

language_codestringrequired

search engine language code (e.g., 'en')

devicestring

device type optional field can take the values:desktop, mobile default value: desktop

osstring

depthnumber

parsing depth, number of results in SERP, max value: 700

示例调用

{
  "tool": "serp_youtube_video_comments_live_advanced",
  "arguments": {
    "video_id": "…",
    "location_name": "…",
    "language_code": "…"
  }
}

serp_youtube_video_subtitles_live_advanced

provides data on the video subtitles you specify

Input（真实 schema）

video_idstringrequired

ID of the video

location_namestringrequired

language_codestringrequired

search engine language code (e.g., 'en')

subtitles_languagestring

language code of original text (e.g., 'en')

subtitles_translate_languagestring

language code of translated text (e.g., 'en')

devicestring

device type optional field can take the values:desktop, mobile default value: desktop

osstring

示例调用

{
  "tool": "serp_youtube_video_subtitles_live_advanced",
  "arguments": {
    "video_id": "…",
    "location_name": "…",
    "language_code": "…"
  }
}

共 89 个工具，此处展示前 20 个。

综合分

Canlah Score69

归属岗位Apollo · 搜索运营专员

岗位分值×1.30

★ Stars223

↓ 下载量27k

工具数（实测）89

npm 包dataforseo-mcp-server

✓ 已连通：字段来自真实的 tools/list（工具清单）。工具本身尚未真实调用。

效果测评卡

进行中 · 待运行

任务成功率

输出质量 (LLM 评审)

延迟

成本 / token

稳定性

真实 I/O 已解决「输入输出是什么」；下一步接 agent 真跑，量化「效果好不好」。

取用 / 安装

npx -y dataforseo-mcp-server

源码仓库 ↗

同岗位其他 skill

Lighthouse

danielsogl/lighthouse-mcp-server

✓ I/O · 12

This MCP server integrates Google Lighthouse web performance auditing capabilities, built by Daniel Sogl to provide automated website performance, accessibility, SEO, and best practices analysis through the Lighthouse testing framework. The implementation enables programmatic execution of Lighthouse audits against web pages, returning detailed performance metrics, optimization recommendations, and compliance scores that can be used for continuous monitoring, automated testing pipelines, or bulk website analysis workflows.

Apollo★ 62↓ 2.8k

AI SEO

automatelab-tech/ai-seo-mcp

✓ I/O · 20

AI SEO is a free, open-source MCP server by AutomateLab that audits web pages across 13 dimensions for AI citation eligibility. It evaluates schema validation, robots.txt compliance, llms.txt standards, entity density, and technical metadata to score how likely AI assistants such as ChatGPT, Perplexity, and Claude are to cite a given page. The server requires no API keys or registration and runs fully locally.

Apollo★ 2↓ 1.6k

AutomateLab SEO Performance

automatelab-tech/seo-performance-mcp

✓ I/O · 9

AutomateLab SEO Performance unifies data from Google Search Console, GA4, Matomo, Microsoft Clarity, and AI citation tracking to assess post-publish content performance. Eight tools grouped across posts, cohort, and GSC categories emit per-URL verdicts—refresh, expand, merge, kill, double_down, or hold—with reason codes and confidence scores. The server runs locally via stdio with credentials provided as environment variables and is available as the npm package @automatelab/seo-performance-mcp.

Apollo★ 1↓ 1.3k