Google News & Trends MCP

Official16 tools

by AKzar1el · Python

Query Google News RSS feeds and search interest over time via Google Trends.

The io.github.AKzar1el/mcp-trendpulse server is a Python Model Context Protocol (MCP) server for researching current news and search-interest trends. It queries Google News RSS feeds and also supports search interest over time via Google Trends.

🛠️ Key Features

Tooling count: 16
Queries Google News RSS feeds
Retrieves search interest over time via Google Trends

🚀 Use Cases

Research current news topics using Google News RSS feeds
Analyze how search interest changes over time using Google Trends

⚡ Developer Benefits

Built as an MCP server
Python (3.10+)
MIT-licensed

⚠️ Limitations

Description indicates functionality is focused on Google News and Google Trends

Topics

data-scrapinggoogle-newsgoogle-trendsmcp-servermodel-context-protocolnlppythontrends-analysiscontent-strategykeyword-researchmarket-researchseotrend-analysisgemini-cli-extension

Declared in the repository manifest (server.json). Not verified against a live endpoint.

get_news_by_keyword

Find articles by keyword using Google News.

Parameters5

keyword	string	required	Search term to find articles.
period	integer	optional	Number of days to look back for articles.
max_results	integer	optional	Maximum number of results to return.
full_data	boolean	optional	Return full data for each article. If False a summary should be created by setting the summarize flag
summarize	boolean	optional	Generate a summary of the article, will first try LLM Sampling but if unavailable will use nlp

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "keyword": {
      "description": "Search term to find articles.",
      "type": "string"
    },
    "period": {
      "default": 7,
      "description": "Number of days to look back for articles.",
      "minimum": 1,
      "type": "integer"
    },
    "max_results": {
      "default": 10,
      "description": "Maximum number of results to return.",
      "minimum": 1,
      "type": "integer"
    },
    "full_data": {
      "default": false,
      "description": "Return full data for each article. If False a summary should be created by setting the summarize flag",
      "type": "boolean"
    },
    "summarize": {
      "default": true,
      "description": "Generate a summary of the article, will first try LLM Sampling but if unavailable will use nlp",
      "type": "boolean"
    }
  },
  "required": [
    "keyword"
  ],
  "type": "object"
}

get_news_by_location

Find articles by location using Google News.

Parameters5

location	string	required	Name of city/state/country.
period	integer	optional	Number of days to look back for articles.
max_results	integer	optional	Maximum number of results to return.
full_data	boolean	optional	Return full data for each article. If False a summary should be created by setting the summarize flag
summarize	boolean	optional	Generate a summary of the article, will first try LLM Sampling but if unavailable will use nlp

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "location": {
      "description": "Name of city/state/country.",
      "type": "string"
    },
    "period": {
      "default": 7,
      "description": "Number of days to look back for articles.",
      "minimum": 1,
      "type": "integer"
    },
    "max_results": {
      "default": 10,
      "description": "Maximum number of results to return.",
      "minimum": 1,
      "type": "integer"
    },
    "full_data": {
      "default": false,
      "description": "Return full data for each article. If False a summary should be created by setting the summarize flag",
      "type": "boolean"
    },
    "summarize": {
      "default": true,
      "description": "Generate a summary of the article, will first try LLM Sampling but if unavailable will use nlp",
      "type": "boolean"
    }
  },
  "required": [
    "location"
  ],
  "type": "object"
}

get_news_by_topic

Find articles by topic using Google News. topic is one of WORLD, NATION, BUSINESS, TECHNOLOGY, ENTERTAINMENT, SPORTS, SCIENCE, HEALTH, POLITICS, CELEBRITIES, TV, MUSIC, MOVIES, THEATER, SOCCER, CYCLING, MOTOR SPORTS, TENNIS, COMBAT SPORTS, BASKETBALL, BASEBALL, FOOTBALL, SPORTS BETTING, WATER SPORTS, HOCKEY, GOLF, CRICKET, RUGBY, ECONOMY, PERSONAL FINANCE, FINANCE, DIGITAL CURRENCIES, MOBILE, ENERGY, GAMING, INTERNET SECURITY, GADGETS, VIRTUAL REALITY, ROBOTICS, NUTRITION, PUBLIC HEALTH, MENTAL HEALTH, MEDICINE, SPACE, WILDLIFE, ENVIRONMENT, NEUROSCIENCE, PHYSICS, GEOLOGY, PALEONTOLOGY, SOCIAL SCIENCES, EDUCATION, JOBS, ONLINE EDUCATION, HIGHER EDUCATION, VEHICLES, ARTS-DESIGN, BEAUTY, FOOD, TRAVEL, SHOPPING, HOME, OUTDOORS, FASHION.

Parameters5

topic	string	required	Topic to search for articles.
period	integer	optional	Number of days to look back for articles.
max_results	integer	optional	Maximum number of results to return.
full_data	boolean	optional	Return full data for each article. If False a summary should be created by setting the summarize flag
summarize	boolean	optional	Generate a summary of the article, will first try LLM Sampling but if unavailable will use nlp

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "topic": {
      "description": "Topic to search for articles.",
      "type": "string"
    },
    "period": {
      "default": 7,
      "description": "Number of days to look back for articles.",
      "minimum": 1,
      "type": "integer"
    },
    "max_results": {
      "default": 10,
      "description": "Maximum number of results to return.",
      "minimum": 1,
      "type": "integer"
    },
    "full_data": {
      "default": false,
      "description": "Return full data for each article. If False a summary should be created by setting the summarize flag",
      "type": "boolean"
    },
    "summarize": {
      "default": true,
      "description": "Generate a summary of the article, will first try LLM Sampling but if unavailable will use nlp",
      "type": "boolean"
    }
  },
  "required": [
    "topic"
  ],
  "type": "object"
}

get_top_news

Get top news stories from Google News.

Parameters4

period	integer	optional	Number of days to look back for top articles.
max_results	integer	optional	Maximum number of results to return.
full_data	boolean	optional	Return full data for each article. If False a summary should be created by setting the summarize flag
summarize	boolean	optional	Generate a summary of the article, will first try LLM Sampling but if unavailable will use nlp

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "period": {
      "default": 3,
      "description": "Number of days to look back for top articles.",
      "minimum": 1,
      "type": "integer"
    },
    "max_results": {
      "default": 10,
      "description": "Maximum number of results to return.",
      "minimum": 1,
      "type": "integer"
    },
    "full_data": {
      "default": false,
      "description": "Return full data for each article. If False a summary should be created by setting the summarize flag",
      "type": "boolean"
    },
    "summarize": {
      "default": true,
      "description": "Generate a summary of the article, will first try LLM Sampling but if unavailable will use nlp",
      "type": "boolean"
    }
  },
  "type": "object"
}

get_trending_terms

Returns google trends for a specific geo location.

Parameters2

geo	string	optional	Geographic target for trending terms. Supports four levels of granularity: - Worldwide: empty string '' - Country: ISO 3166-1 alpha-2 code, e.g. 'US', 'GB', 'CA' - Subdivision (state/province/region): ISO 3166-2 format 'CC-XX' or 'CC-XXX', e.g. 'US-CA' (California), 'BE-BRU' (Brussels) - US metro area: bare Nielsen DMA code (numeric string), e.g. '807' (San Francisco Bay Area), '501' (New York City)
full_data	boolean	optional	Return full data for each trend including related news stories.

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "geo": {
      "default": "US",
      "description": "Geographic target for trending terms. Supports four levels of granularity:\n- Worldwide: empty string ''\n- Country: ISO 3166-1 alpha-2 code, e.g. 'US', 'GB', 'CA'\n- Subdivision (state/province/region): ISO 3166-2 format 'CC-XX' or 'CC-XXX', e.g. 'US-CA' (California), 'BE-BRU' (Brussels)\n- US metro area: bare Nielsen DMA code (numeric string), e.g. '807' (San Francisco Bay Area), '501' (New York City)",
      "type": "string"
    },
    "full_data": {
      "default": false,
      "description": "Return full data for each trend including related news stories.",
      "type": "boolean"
    }
  },
  "type": "object"
}

get_trends

Pull search interest over time for keywords.

Parameters6

keyword	any	required	Search keyword(s) to analyze; comparison lists support 1-5 keywords.
source	string	optional	Search source: 'google search', 'youtube search', 'news search', 'image search', 'google shopping'.
data_mode	string	optional	Legacy resolution hint used only when timeframe is omitted: 'weekly', 'daily', 'monthly'.
geo	string	optional	Geographic region code (e.g. 'US').
timeframe	any	optional	Explicit TrendsPy range, for example 'today 12-m', 'today 90-d', 'all', or 'YYYY-MM-DD YYYY-MM-DD'. Overrides data_mode when supplied.
cat	integer	optional	Google Trends category ID; use 0 for all categories or a value from get_categories.

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "keyword": {
      "anyOf": [
        {
          "minLength": 1,
          "type": "string"
        },
        {
          "items": {
            "minLength": 1,
            "type": "string"
          },
          "maxItems": 5,
          "minItems": 1,
          "type": "array"
        }
      ],
      "description": "Search keyword(s) to analyze; comparison lists support 1-5 keywords."
    },
    "source": {
      "default": "google search",
      "description": "Search source: 'google search', 'youtube search', 'news search', 'image search', 'google shopping'.",
      "type": "string",
      "enum": [
        "google search",
        "youtube search",
        "news search",
        "image search",
        "google shopping"
      ]
    },
    "data_mode": {
      "default": "weekly",
      "description": "Legacy resolution hint used only when timeframe is omitted: 'weekly', 'daily', 'monthly'.",
      "type": "string",
      "enum": [
        "weekly",
        "daily",
        "monthly"
      ]
    },
    "geo": {
      "default": "US",
      "description": "Geographic region code (e.g. 'US').",
      "type": "string"
    },
    "timeframe": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Explicit TrendsPy range, for example 'today 12-m', 'today 90-d', 'all', or 'YYYY-MM-DD YYYY-MM-DD'. Overrides data_mode when supplied."
    },
    "cat": {
      "default": 0,
      "description": "Google Trends category ID; use 0 for all categories or a value from get_categories.",
      "type": "integer"
    }
  },
  "required": [
    "keyword"
  ],
  "type": "object"
}

get_growth

Measure interest growth over specified windows.

Parameters4

keyword	any	required	Search keyword(s) to analyze; comparison lists support 1-5 keywords.
source	string	optional	Search source: 'google search', 'youtube search', etc.
percent_growth	array	optional	Timeframes to calculate growth (e.g. ['3M', '1Y']).
geo	string	optional	Geographic region code (e.g. 'US').

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "keyword": {
      "anyOf": [
        {
          "minLength": 1,
          "type": "string"
        },
        {
          "items": {
            "minLength": 1,
            "type": "string"
          },
          "maxItems": 5,
          "minItems": 1,
          "type": "array"
        }
      ],
      "description": "Search keyword(s) to analyze; comparison lists support 1-5 keywords."
    },
    "source": {
      "default": "google search",
      "description": "Search source: 'google search', 'youtube search', etc.",
      "type": "string",
      "enum": [
        "google search",
        "youtube search",
        "news search",
        "image search",
        "google shopping"
      ]
    },
    "percent_growth": {
      "default": null,
      "description": "Timeframes to calculate growth (e.g. ['3M', '1Y']).",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "geo": {
      "default": "US",
      "description": "Geographic region code (e.g. 'US').",
      "type": "string"
    }
  },
  "required": [
    "keyword"
  ],
  "type": "object"
}

get_ranked_trends

Get ranked trending keywords on Google Search.

Parameters4

source	string	optional	Search source: 'google search'.
sort	string	optional	Field to sort by: 'wow_pct_change', 'volume'.
limit	integer	optional	Maximum number of trends to return.
geo	string	optional	Geographic region code (e.g. 'US').

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "source": {
      "default": "google search",
      "description": "Search source: 'google search'.",
      "type": "string",
      "enum": [
        "google search"
      ]
    },
    "sort": {
      "default": "wow_pct_change",
      "description": "Field to sort by: 'wow_pct_change', 'volume'.",
      "type": "string",
      "enum": [
        "wow_pct_change",
        "volume"
      ]
    },
    "limit": {
      "default": 20,
      "description": "Maximum number of trends to return.",
      "minimum": 1,
      "type": "integer"
    },
    "geo": {
      "default": "US",
      "description": "Geographic region code (e.g. 'US').",
      "type": "string"
    }
  },
  "type": "object"
}

get_top_trends

Get top trends from Google Trends realtime or 24-hour Trending Now feeds.

Parameters3

type	string	optional	Type of trends: 'Google Trends' (realtime), 'Daily Trends' (daily).
limit	integer	optional	Maximum number of trends to return.
geo	string	optional	Geographic region code (e.g. 'US').

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "type": {
      "default": "Google Trends",
      "description": "Type of trends: 'Google Trends' (realtime), 'Daily Trends' (daily).",
      "type": "string",
      "enum": [
        "Google Trends",
        "Daily Trends"
      ]
    },
    "limit": {
      "default": 20,
      "description": "Maximum number of trends to return.",
      "minimum": 1,
      "type": "integer"
    },
    "geo": {
      "default": "US",
      "description": "Geographic region code (e.g. 'US').",
      "type": "string"
    }
  },
  "type": "object"
}

get_news_by_site

Find articles from a specific publisher site using Google News.

Parameters5

site	string	required	Domain of the news site, e.g. 'cnn.com'.
period	integer	optional	Number of days to look back for articles.
max_results	integer	optional	Maximum number of results to return.
full_data	boolean	optional	Return full data for each article. If False a summary should be created by setting the summarize flag
summarize	boolean	optional	Generate a summary of the article, will first try LLM Sampling but if unavailable will use nlp

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "site": {
      "description": "Domain of the news site, e.g. 'cnn.com'.",
      "type": "string"
    },
    "period": {
      "default": 7,
      "description": "Number of days to look back for articles.",
      "minimum": 1,
      "type": "integer"
    },
    "max_results": {
      "default": 10,
      "description": "Maximum number of results to return.",
      "minimum": 1,
      "type": "integer"
    },
    "full_data": {
      "default": false,
      "description": "Return full data for each article. If False a summary should be created by setting the summarize flag",
      "type": "boolean"
    },
    "summarize": {
      "default": true,
      "description": "Generate a summary of the article, will first try LLM Sampling but if unavailable will use nlp",
      "type": "boolean"
    }
  },
  "required": [
    "site"
  ],
  "type": "object"
}

get_article_content

Download, scrape and parse the content of a specific news article from a given URL.

Parameters3

url	string	required	The URL of the news article to download and parse.
full_data	boolean	optional	Return full data for the article. If False a summary should be created by setting the summarize flag
summarize	boolean	optional	Generate a summary of the article, will first try LLM Sampling but if unavailable will use nlp

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "url": {
      "description": "The URL of the news article to download and parse.",
      "type": "string"
    },
    "full_data": {
      "default": false,
      "description": "Return full data for the article. If False a summary should be created by setting the summarize flag",
      "type": "boolean"
    },
    "summarize": {
      "default": true,
      "description": "Generate a summary of the article, will first try LLM Sampling but if unavailable will use nlp",
      "type": "boolean"
    }
  },
  "required": [
    "url"
  ],
  "type": "object"
}

get_interest_by_region

Retrieves geographical interest data based on keywords and other parameters.

Parameters7

keywords	any	required	Search keyword(s) to analyze.
timeframe	string	optional	Timeframe for search volume analysis (e.g., 'today 12-m').
geo	string	optional	Geographic region code (e.g. 'US' or empty '' for worldwide).
cat	integer	optional	Category ID (default: 0 for all).
gprop	string	optional	Google property filter (e.g., '', 'youtube', 'news', 'images', 'froogle').
resolution	string	optional	Geographic resolution: 'COUNTRY', 'REGION', 'CITY', or 'DMA'.
inc_low_vol	boolean	optional	Include regions with low search volume.

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "keywords": {
      "anyOf": [
        {
          "minLength": 1,
          "type": "string"
        },
        {
          "items": {
            "minLength": 1,
            "type": "string"
          },
          "type": "array",
          "minItems": 1,
          "maxItems": 5
        }
      ],
      "description": "Search keyword(s) to analyze."
    },
    "timeframe": {
      "default": "today 12-m",
      "description": "Timeframe for search volume analysis (e.g., 'today 12-m').",
      "type": "string"
    },
    "geo": {
      "default": "US",
      "description": "Geographic region code (e.g. 'US' or empty '' for worldwide).",
      "type": "string"
    },
    "cat": {
      "default": 0,
      "description": "Category ID (default: 0 for all).",
      "type": "integer"
    },
    "gprop": {
      "default": "",
      "description": "Google property filter (e.g., '', 'youtube', 'news', 'images', 'froogle').",
      "type": "string",
      "enum": [
        "",
        "youtube",
        "news",
        "images",
        "froogle"
      ]
    },
    "resolution": {
      "default": "REGION",
      "description": "Geographic resolution: 'COUNTRY', 'REGION', 'CITY', or 'DMA'.",
      "type": "string",
      "enum": [
        "COUNTRY",
        "REGION",
        "CITY",
        "DMA"
      ]
    },
    "inc_low_vol": {
      "default": false,
      "description": "Include regions with low search volume.",
      "type": "boolean"
    }
  },
  "required": [
    "keywords"
  ],
  "type": "object"
}

get_related_queries

Retrieves related queries for a single search term.

Parameters5

keyword	string	required	Search keyword to analyze.
timeframe	string	optional	Timeframe for search volume analysis (e.g., 'today 12-m').
geo	string	optional	Geographic region code (e.g. 'US').
cat	integer	optional	Category ID (default: 0 for all).
gprop	string	optional	Google property filter (e.g., '', 'youtube', 'news', 'images', 'froogle').

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "keyword": {
      "description": "Search keyword to analyze.",
      "type": "string"
    },
    "timeframe": {
      "default": "today 12-m",
      "description": "Timeframe for search volume analysis (e.g., 'today 12-m').",
      "type": "string"
    },
    "geo": {
      "default": "US",
      "description": "Geographic region code (e.g. 'US').",
      "type": "string"
    },
    "cat": {
      "default": 0,
      "description": "Category ID (default: 0 for all).",
      "type": "integer"
    },
    "gprop": {
      "default": "",
      "description": "Google property filter (e.g., '', 'youtube', 'news', 'images', 'froogle').",
      "type": "string",
      "enum": [
        "",
        "youtube",
        "news",
        "images",
        "froogle"
      ]
    }
  },
  "required": [
    "keyword"
  ],
  "type": "object"
}

get_related_topics

Retrieves related topics for a single search term.

Parameters5

keyword	string	required	Search keyword to analyze.
timeframe	string	optional	Timeframe for search volume analysis (e.g., 'today 12-m').
geo	string	optional	Geographic region code (e.g. 'US').
cat	integer	optional	Category ID (default: 0 for all).
gprop	string	optional	Google property filter (e.g., '', 'youtube', 'news', 'images', 'froogle').

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "keyword": {
      "description": "Search keyword to analyze.",
      "type": "string"
    },
    "timeframe": {
      "default": "today 12-m",
      "description": "Timeframe for search volume analysis (e.g., 'today 12-m').",
      "type": "string"
    },
    "geo": {
      "default": "US",
      "description": "Geographic region code (e.g. 'US').",
      "type": "string"
    },
    "cat": {
      "default": 0,
      "description": "Category ID (default: 0 for all).",
      "type": "integer"
    },
    "gprop": {
      "default": "",
      "description": "Google property filter (e.g., '', 'youtube', 'news', 'images', 'froogle').",
      "type": "string",
      "enum": [
        "",
        "youtube",
        "news",
        "images",
        "froogle"
      ]
    }
  },
  "required": [
    "keyword"
  ],
  "type": "object"
}

get_suggestions

Retrieves autocomplete suggestions for a search term.

Parameters2

keyword	string	required	Query string to autocomplete.
language	any	optional	Language code, e.g. 'en'.

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "keyword": {
      "description": "Query string to autocomplete.",
      "type": "string"
    },
    "language": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Language code, e.g. 'en'."
    }
  },
  "required": [
    "keyword"
  ],
  "type": "object"
}

get_categories

Retrieves category list from Google Trends.

Parameters

No parameters.

Raw schema

{
  "additionalProperties": false,
  "properties": {},
  "type": "object"
}

README.md17 KBView on GitHub

mcp-trendpulse

MCPVault: verified

TrendPulse is a Python Model Context Protocol (MCP) server for researching current news and search-interest trends. It combines Google News discovery and article extraction with Google Trends analysis so MCP clients can inspect what is trending, compare keyword momentum, explore related demand, and add current-news context to research workflows.

The project currently ships as a community/self-hosted MCP server and also contains the implementation for a separate hosted TrendPulse by DigestSEO surface for remote MCP clients such as ChatGPT and Codex. The hosted layer uses a smaller, goal-oriented tool surface while the community server keeps the full low-level research toolkit available to developers.

Project status: the local/community server is usable today. The DigestSEO-hosted MCP and public OpenAI plugin are not released yet and should not be treated as available endpoints.

Engineering context: TrendPulse is part of the DigestSEO MCP ecosystem. It complements mcp-gsc for Google Search Console data, mcp-geo for AI visibility, and mcp-web-validator for technical web validation. The broader architecture is documented in the DigestSEO MCP Suite engineering case study.

TrendPulse Demand Brief

Need a fast evidence check before choosing a topic, keyword, market, product angle, or content bet? Tomi offers a human-produced TrendPulse Demand Brief for EUR 49.

For one decision, the brief covers up to five keywords/phrases and two geographic markets using TrendPulse's open-source research capabilities plus current public sources: search-interest direction, relative momentum, related demand, useful news context, and three concrete implications. Target turnaround is within 24 hours after payment is confirmed and the inputs are supplied.

See the exact scope and request format, read a public sample brief, or email info@tomiseregi.si with the subject TrendPulse Demand Brief [TP-RS1].

The paid brief is optional. The Community MCP remains free and unchanged, and the TP-RS1 marker is only an inbound attribution marker; no hidden telemetry is added to the MCP.

What TrendPulse can do

News research

Search Google News by keyword, location, topic, or publisher domain.
Retrieve top news stories.
Resolve Google News links and extract article content.
Fall back from normal HTTP retrieval to Playwright/Chromium for difficult pages.
Optionally summarize article text with MCP client sampling, with local NLP as a fallback.

Trend research

Retrieve current trending terms for a geographic market.
Pull Google Trends interest-over-time data for one or more keywords.
Calculate keyword growth over custom windows such as 3M or 1Y.
Rank live trends by volume or growth.
Inspect interest by country, region, city, or DMA where supported.
Explore related queries, related topics, suggestions, and category IDs.
Compare Google Search, YouTube Search, News Search, Image Search, and Google Shopping trend properties where supported by the underlying provider.

Community and hosted architecture

TrendPulse is being developed with two deliberate surfaces:

Surface	Purpose	Status
Community MCP	Full Python MCP server for local use, development, self-hosting, and integrations with MCP-compatible clients.	Available in this repository
TrendPulse by DigestSEO	Managed remote MCP for ChatGPT/Codex and a future public OpenAI plugin with a smaller, task-oriented tool surface.	In development

The community server remains useful independently. The hosted edition will reuse the same core trend-research concepts while adding the deployment, reliability, authentication, observability, and product integration needed for a managed service.

The implemented hosted tool surface is intentionally higher level than the community API and centers on goals such as:

discover_trends
analyze_keyword_trend
compare_keyword_trends
discover_related_demand
get_trend_context
find_seo_opportunities

These names describe the hosted ChatGPT Apps/MCP interface; they remain separate from the current Community MCP tool names.

Installation

Run from PyPI with `uvx` (recommended)

TrendPulse is published on PyPI, so the shortest install path is:

bash

uvx mcp-trendpulse

To run the current repository head instead of the published package:

bash

uvx --from git+https://github.com/AKzar1el/mcp-trendpulse.git mcp-trendpulse

Install with pip from a checkout

bash

git clone https://github.com/AKzar1el/mcp-trendpulse.git
cd mcp-trendpulse
python -m pip install .
python -m mcp_trendpulse

Browser fallback

News/article tools can fall back to Playwright when ordinary retrieval cannot extract a usable article. Installing the Python playwright package does not install Chromium automatically.

For local use:

bash

playwright install chromium

For Linux environments that also require browser system dependencies:

bash

playwright install --with-deps chromium

Trend-only operations do not inherently require Chromium.

Client configuration

Claude Desktop and Claude Code

Claude Code plugin packaging is included in .claude-plugin/plugin.json with its MCP definition in .mcp.json. The Community MCP remains local/stdin-based and runs through uvx mcp-trendpulse.

Claude Desktop

Using the published PyPI package with uvx:

json

{
  "mcpServers": {
    "mcp-trendpulse": {
      "command": "uvx",
      "args": ["mcp-trendpulse"]
    }
  }
}

VS Code

Install TrendPulse in VS Code

Requires uv/uvx. The install runs the published Community MCP package from PyPI over local stdio.

For workspace-level configuration, put this in .vscode/mcp.json. The same top-level servers shape is used by the VS Code user-profile mcp.json for a global configuration.

json

{
  "servers": {
    "mcp-trendpulse": {
      "command": "uvx",
      "args": ["mcp-trendpulse"]
    }
  }
}

ChatGPT desktop, Codex CLI, and IDE extension

OpenAI's local ChatGPT desktop and Codex clients support local stdio MCP servers and share the same MCP configuration on a Codex host. Add the published TrendPulse package once with:

bash

codex mcp add mcp-trendpulse -- uvx mcp-trendpulse

The same local server is then available to the ChatGPT desktop app, Codex CLI, and the Codex IDE extension. In ChatGPT desktop, you can also open Settings -> MCP Servers and add an STDIO server with command uvx mcp-trendpulse, then restart the app. This runs the published Community MCP package from PyPI; it does not use the unreleased hosted TrendPulse endpoint. ChatGPT on the web is separate and does not read this local Codex MCP configuration.

Cursor and portable Agent Plugins

This repository includes an Agent Plugins 1.0 manifest at the repository root. Compatible clients such as Cursor and GitHub Copilot can load the same portable plugin.json + mcp.json package.

Cursor also supports global and project MCP configuration. Add the server to the relevant mcp.json configuration:

json

{
  "mcpServers": {
    "mcp-trendpulse": {
      "command": "uvx",
      "args": ["mcp-trendpulse"]
    }
  }
}

Devin CLI and Devin Desktop

Devin CLI plugins can load Claude plugin packages and Agent Plugins 1.0 packages directly from GitHub. TrendPulse already ships both compatible layouts (.claude-plugin/plugin.json + .mcp.json, and root plugin.json + mcp.json). Install it with:

bash

devin plugins install AKzar1el/mcp-trendpulse

Devin requires a signed-in CLI session to manage plugins. The installed TrendPulse plugin starts the published Community MCP locally over stdio with uvx mcp-trendpulse; it does not use the unreleased hosted TrendPulse endpoint. The same plugin is available in Devin Desktop after installation.

Kiro

Requires uv/uvx. The install runs the published Community MCP package from PyPI; it does not use the unreleased hosted surface.

Privacy: TrendPulse Community MCP Privacy Notice · Support: info@tomiseregi.si

LM Studio

Add TrendPulse to LM Studio

Requires uv/uvx. LM Studio runs the published Community MCP package locally over stdio; no hosted TrendPulse service is required.

ChatGPT web and other cloud MCP clients

The repository now includes a dedicated stateless Streamable HTTP ASGI entry point at mcp_trendpulse.asgi:app. This is separate from the Community stdio entry point, which remains unchanged.

For controlled local/private testing you can run the ASGI app with Uvicorn or use the provided container. See deploy/README.md for the hardened container, Host/Origin allowlists, Chromium sandbox requirements, health/readiness endpoints, and reverse-proxy notes.

The DigestSEO-hosted endpoint and public ChatGPT app are still not released. Hosted deployments now support fail-closed Clerk OAuth authentication; do not expose the remote transport publicly unless Clerk issuer/JWKS/audience settings, the public base URL, and the Host/Origin allowlists are configured for that deployment.

Configuration

TrendPulse loads environment variables from the process environment and from a local .env file when present.

Useful variables include:

env

HTTP_PROXY=http://your-proxy-address:port
HTTPS_PROXY=http://your-proxy-address:port
GOOGLE_NEWS_LANGUAGE=en
GOOGLE_NEWS_COUNTRY=US
GOOGLE_TRENDS_DELAY=2.0

GOOGLE_NEWS_LANGUAGE and GOOGLE_NEWS_COUNTRY select the Google News language/edition used by all news-discovery tools; defaults remain en and US. GOOGLE_TRENDS_DELAY controls the request delay used by the current Trends provider. Proxy variables can be useful when the upstream service rate-limits or blocks a particular network.

Remote deployments also support TRENDPULSE_HTTP_PATH, TRENDPULSE_HTTP_ALLOWED_HOSTS, TRENDPULSE_HTTP_ALLOWED_ORIGINS, and TRENDPULSE_BROWSER_SANDBOX. The container enables Chromium sandboxing explicitly; local Community runs retain the Playwright-compatible default unless you opt in.

Do not commit secrets, private proxy credentials, or machine-specific .env files.

MCP tools

The community MCP server currently exposes 16 tools.

News tools

Tool	Purpose
`get_news_by_keyword`	Find recent news articles matching a keyword.
`get_news_by_location`	Find recent news associated with a location.
`get_news_by_topic`	Find recent news for a supported Google News topic.
`get_top_news`	Retrieve top Google News stories.
`get_news_by_site`	Find recent news from a specific publisher domain.
`get_article_content`	Download, validate, extract, and optionally summarize one article URL.

Trend tools

Tool	Purpose
`get_trending_terms`	Retrieve current trending terms for a geographic target.
`get_trends`	Retrieve interest-over-time points for one or more keywords.
`get_growth`	Calculate search-interest growth over requested windows.
`get_ranked_trends`	Rank current trends by growth or volume.
`get_top_trends`	Retrieve a top-trends feed without supplying a keyword.
`get_interest_by_region`	Compare keyword interest across geographic regions.
`get_related_queries`	Retrieve top and rising related search queries.
`get_related_topics`	Retrieve top and rising related Google Trends topics.
`get_suggestions`	Resolve autocomplete/topic suggestions for a query.
`get_categories`	Search or page through Google Trends category IDs and names before using `cat`.

Example: explicit trend window

get_trends accepts an explicit timeframe. Supplying one is preferable when you need reproducible comparisons.

json

{
  "keyword": ["technical SEO audit", "AI SEO audit"],
  "geo": "US",
  "source": "google search",
  "timeframe": "today 12-m",
  "cat": 0
}

Supported provider ranges include standard windows such as today 12-m and today 5-y, relative windows such as today 90-d, all, and exact date ranges such as 2021-01-01 2026-01-01.

Google Trends values are normalized interest scores. Do not interpret a 0-100 interest series as absolute search volume.

CLI

The separate Click CLI exposes a smaller news-oriented command set than the MCP server:

bash

uv run mcp-trendpulse-cli --help

Current CLI commands:

text

brief-pack
keyword
location
top
topic
trending

brief-pack emits the deterministic trend/growth evidence table used for Demand Brief fulfillment. It intentionally leaves the final interpretation and recommendations to the human-produced brief.

The CLI and MCP surfaces are intentionally documented separately because they do not expose the same command set.

Development

Install the project with its development dependencies using your preferred Python environment, then run the unit suite:

bash

python -m pytest

The default pytest configuration excludes live integration tests.

Run live provider tests explicitly with:

bash

python -m pytest tests/integration -m integration

Browser-marked integration tests require Playwright Chromium to be installed.

Run Ruff checks with:

bash

ruff check .

MCP Inspector

Run the published-from-GitHub server through the MCP Inspector:

bash

npx @modelcontextprotocol/inspector uvx --from git+https://github.com/AKzar1el/mcp-trendpulse.git mcp-trendpulse

For a local checkout:

bash

npx @modelcontextprotocol/inspector uv run mcp-trendpulse

Packaging

A GitHub Actions workflow builds and publishes Python distributions through PyPI Trusted Publishing when a GitHub release is published. The current stable package can be run with uvx mcp-trendpulse; use the GitHub uvx --from ... form only when you intentionally want repository-head code.

Security notes

Article retrieval is an outbound network feature and is treated as untrusted input. The implementation validates HTTP(S) targets, rejects private and non-routable destinations, checks redirect targets, enforces response-size limits, and applies browser-route validation when Playwright is used.

If you deploy TrendPulse remotely, retain these controls and add deployment-level rate limiting, request timeouts, observability, and resource limits rather than relying only on application defaults.

For responsible disclosure instructions, see SECURITY.md.

Roadmap

Current production-readiness priorities are:

Keep documentation, packaging metadata, and generated MCP manifests coherent with the live tool surface.
Keep CI, package validation, and dependency/runtime coverage aligned with what users actually install.
Preserve provider boundaries so upstream sources can be changed without rewriting the MCP layer.
Harden and operate the existing stateless Streamable HTTP transport while preserving local stdio operation.
Refine the existing smaller hosted tool surface for ChatGPT/Codex against real deployment and buyer evidence.
Complete provider authorization and integrate the hosted service with the DigestSEO application and operational stack.
Package and test the hosted MCP as an OpenAI plugin only after the managed service is production-ready.

License

MIT. See LICENSE.

Install

Tools (16)

get_news_by_keywordget_news_by_locationget_news_by_topicget_top_newsget_trending_termsget_trendsget_growthget_ranked_trends

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "mcp-trendpulse": {
      "command": "uvx",
      "args": [
        "mcp-trendpulse"
      ]
    }
  }
}

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

get_news_by_keyword

get_news_by_location

get_news_by_topic

get_top_news

get_trending_terms

get_trends

get_growth

get_ranked_trends

get_top_trends

get_news_by_site

get_article_content

get_interest_by_region

get_related_queries

get_related_topics

get_suggestions

get_categories

mcp-trendpulse

TrendPulse Demand Brief

What TrendPulse can do

News research

Trend research

Community and hosted architecture

Installation

Run from PyPI with uvx (recommended)

Install with pip from a checkout

Browser fallback

Client configuration

Claude Desktop and Claude Code

Claude Desktop

VS Code

ChatGPT desktop, Codex CLI, and IDE extension

Cursor and portable Agent Plugins

Devin CLI and Devin Desktop

Kiro

LM Studio

ChatGPT web and other cloud MCP clients

Configuration

MCP tools

News tools

Trend tools

Example: explicit trend window

CLI

Development

MCP Inspector

Packaging

Security notes

Roadmap

License

Install

Related servers

Run from PyPI with `uvx` (recommended)