What can you do with this server?

This server lets MCP clients search global news, fetch top headlines, and monitor AllNewsAPI usage. * Search news articles (search-news) by keyword, date range, language, country, region, category, publisher, and more * Fetch top headlines (headlines) with optional filters for country, category, language, and AI-based criteria * Check API usage (usage) to view your plan, request limits, and remaining quota * Use AI filters like sentiment (positive, negative, neutral) and named entities (person, organization, location) * Control results with pagination, result count (1–100), and full-content retrieval * Sort or target keywords by relevance or publication date, and by title/description/content (paid plans may apply for advanced filters)

How do I use AllNewsAPI MCP?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@AllNewsAPI MCP get the latest headlines about AI" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

AllNewsAPI MCP

Official

by AllNewsAPI

Overview Schema Source Related Servers Discussions Admin

TypeScript

Remote

AllNewsAPI MCP

npm AllNewsAPI/mcp-server MCP server

AllNewsAPI/mcp-server MCP server

Get access to real-time and historical news data including top headlines from global sources via AllNewsAPI. Supports multiple filter options including keyword search, category, language and more. This Model Context Protocol server lets MCP clients (Claude, Cursor, VS Code, Windsurf, and others) search news articles, fetch top headlines, and check your API usage.

You'll need an API key — get one at allnewsapi.com.

Quick start

Pick one of the two ways to connect.

Hosted (no install)

Point your client at the hosted server and pass your API key in the X-API-Key header:

{
  "mcpServers": {
    "allnewsapi": {
      "type": "remote",
      "url": "https://mcp.allnewsapi.com/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY_HERE"
      }
    }
  }
}

Prefer a URL-only setup? Use https://mcp.allnewsapi.com/mcp?apikey=YOUR_API_KEY_HERE instead of the header.

The key can be supplied three ways, in this order of precedence: the X-API-Key header, the apikey query parameter, or an Authorization: Bearer YOUR_API_KEY_HERE header (a fallback for clients that only support bearer tokens).

Local (npx)

Runs the server on your machine via npx — no clone or build needed:

{
  "mcpServers": {
    "allnewsapi": {
      "command": "npx",
      "args": ["allnewsapi-mcp@latest", "--apikey", "YOUR_API_KEY_HERE"]
    }
  }
}

You can also supply the key as an ALLNEWSAPI_KEY environment variable instead of --apikey.

Client-specific setup

Edit your config (Settings → Developer → Edit Config) and add the local or hosted snippet above. Full guide: modelcontextprotocol.io/quickstart/user.

Cursor Settings → MCP → Add new MCP Server. Name it "AllNewsAPI", choose the command type, and enter:

npx allnewsapi-mcp@latest --apikey YOUR_API_KEY_HERE

code --add-mcp '{"name":"allnewsapi","command":"npx","args":["allnewsapi-mcp@latest","--apikey","YOUR_API_KEY_HERE"]}'

The server is then available to your GitHub Copilot agent. Full guide: VS Code MCP docs.

Add the local or hosted snippet above to your MCP config. Full guide: Windsurf MCP docs.

Add it from the terminal — local:

claude mcp add allnewsapi -- npx allnewsapi-mcp@latest --apikey YOUR_API_KEY_HERE

Or the hosted server:

claude mcp add --transport http allnewsapi https://mcp.allnewsapi.com/mcp --header "X-API-Key: YOUR_API_KEY_HERE"

Cowork runs inside Claude Desktop. Add the hosted server as a custom connector — Customize → Connectors → + — and enter the URL with your key:

https://mcp.allnewsapi.com/mcp?apikey=YOUR_API_KEY_HERE

For a local setup, use the Claude Desktop config shown above.

OpenWork is an open-source Cowork alternative with MCP support. Add AllNewsAPI using either the local command (npx allnewsapi-mcp@latest --apikey YOUR_API_KEY_HERE) or the hosted URL above, following OpenWork's MCP configuration.

Any other MCP client: point it at the hosted URL (https://mcp.allnewsapi.com/mcp) or run the npx allnewsapi-mcp@latest command with your API key.

Related MCP server: mcp-newsdata

Tools

`search-news`

Search articles by keyword, date, and filters.

Parameter	Type	Description
`q`	string	Keywords to search for
`startDate` / `endDate`	string	Date range (`YYYY-MM-DD`)
`content`	boolean	Include full article content (default: false)
`lang`	string	Language code(s), e.g. `en`, `fr`
`country`	string	Country code(s), e.g. `us`, `gb`
`region`	string	Region(s), e.g. `americas`, `europe`
`category`	string	Category/categories, e.g. `business`
`max`	number	Number of articles, 1–100 (default: 5)
`page`	number	Page number (default: 1)
`attributes`	string	Where to match keywords: `title`, `description`, `content`
`sortby`	string	`publishedAt` or `relevance`
`publisher`	string	Filter by publisher(s)
`ai_sentiment`	string	`positive`, `negative`, or `neutral`
`ai_entity_name`	string	Named entity, e.g. `Apple`
`ai_entity_type`	string	Entity type, e.g. `person`, `organization`, `location`

`headlines`

Get top headlines, optionally filtered.

Parameter	Type	Description
`country`	string	Country code(s), e.g. `us`, `gb`
`category`	string	Category, e.g. `technology`
`lang`	string	Language code, e.g. `en`
`max`	number	Number of articles, 1–100 (default: 5)
`ai_sentiment`	string	`positive`, `negative`, or `neutral`
`ai_entity_name`	string	Named entity, e.g. `Apple`
`ai_entity_type`	string	Entity type, e.g. `person`, `organization`, `location`

`usage`

Check your plan, request limits, and remaining quota. No parameters.

Plan note: Advanced filters — country, region, category, publisher, lang, attributes, and sortby — require a paid plan. On the free plan, use search-news with q and max. See pricing.

AI filtering

search-news and headlines accept AI-analyzed filters:

ai_sentiment — overall article sentiment (positive, negative, neutral)
ai_entity_name — a named entity in the article (e.g. United Nations)
ai_entity_type — entity category (person, organization, location)

Returned articles may also include AI sentiment scores, detected entities, and a short AI summary when available.

Example prompts

"Get me the latest technology news from the US"
"Find articles about climate change from European sources"
"Show me top business headlines from the past week"
"Find positive news about renewable energy"
"Show me articles mentioning Apple as an organization"
"Check my API usage and remaining quota"

Supported values

Full lists of accepted values live in the AllNewsAPI docs:

License

MIT © AllNewsAPI — see LICENSE for details.

Available Tools

3 tools

headlinesGet HeadlinesB

Read-only

Inspect

Get top headlines with optional filtering by country, category, and language

ParametersJSON Schema

Name	Required	Description
`max`	No	Number of articles to return (1-100)
`lang`	No	Language code of the articles (e.g., 'en', 'fr')
`country`	No	Country code(s) of publication (e.g., 'us', 'gb')
`category`	No	Category to filter by (e.g., 'business', 'technology')
`ai_sentiment`	No	Filter by AI-analyzed sentiment (e.g., 'positive', 'negative', 'neutral')
`ai_entity_name`	No	Filter by entity name detected in articles
`ai_entity_type`	No	Filter by entity type (e.g., 'person', 'organization', 'location')

TDQS

B3.2/5.0

Behavior3/5

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

The readOnlyHint annotation already communicates the safety profile, and the description's 'Get' verb is consistent with that. The description adds no extra behavioral context such as pagination, result ordering, or handling of empty results, so it does not go beyond the annotations, but it also does not mislead.

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 with no filler. It communicates the core action first and then mentions filtering, making it easy to parse quickly.

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

Completeness2/5

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

With 7 optional parameters, no output schema, and sibling tools like search-news, the description should help the agent choose the right tool and invoke it correctly. It only covers three filters and gives no guidance on the role of max or the AI-based filters, nor does it explain how it differs from search-news. This leaves material gaps for the agent.

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 description coverage is 100%, so the baseline applies. The description merely names three of the seven filters (country, category, language) without adding any meaning beyond the schema, and it ignores the AI-related and max parameters. It neither enriches nor contradicts the schema.

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 uses a specific verb and resource ('Get top headlines') and clarifies the main function, distinguishing it from a general search by focusing on headlines. However, it does not explicitly contrast with the sibling tool search-news, and it omits several available filters (max, ai_sentiment, ai_entity_name, ai_entity_type), so it falls short of a 5.

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?

The description gives no explicit guidance on when to use this tool instead of search-news or usage. It only states that filtering is optional, leaving the agent to infer the appropriate context without any comparison to alternatives.

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

search-newsSearch NewsB

Read-only

Inspect

Search for news articles using various parameters including keywords, date ranges, and filters

ParametersJSON Schema

Name	Required	Description
`q`	No	Keywords to search for in news articles
`max`	No	Number of articles to return (1-100)
`lang`	No	Language code(s) of the articles (e.g., 'en', 'fr')
`page`	No	Page number for pagination
`region`	No	Region(s) to filter by (e.g., 'americas', 'europe')
`sortby`	No	Sort results by 'publishedAt' or 'relevance' (paid plans only; omitted by default)
`content`	No	Whether to retrieve full article content
`country`	No	Country code(s) of publication (e.g., 'us', 'gb')
`endDate`	No	Filter articles published on or before this date (YYYY-MM-DD)
`category`	No	Category/categories to filter by (e.g., 'business', 'technology')
`publisher`	No	Filter by specific publisher(s)
`startDate`	No	Filter articles published on or after this date (YYYY-MM-DD)
`attributes`	No	Where to search for keywords: title, description, content (paid plans only; omitted by default)
`ai_sentiment`	No	Filter by AI-analyzed sentiment (e.g., 'positive', 'negative', 'neutral')
`ai_entity_name`	No	Filter by entity name detected in articles
`ai_entity_type`	No	Filter by entity type (e.g., 'person', 'organization', 'location')

TDQS

B3.3/5.0

Behavior3/5

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

Annotations declare readOnlyHint=true, so the safety profile is already covered. The description adds only a generic summary of parameter types, not behavioral details like pagination behavior, result limits, or paid-plan restrictions. It does not contradict the read-only hint, but adds minimal insight beyond the schema.

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, focused sentence that front-loads the core action and resource, with no filler or redundancy. It is appropriately sized for the tool's purpose.

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?

With 16 optional parameters and no output schema, the description is somewhat sparse. It conveys the basic search purpose and result type (news articles), but omits operational details like pagination, result size, and paid-plan constraints, which an agent would need to discover through the schema.

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?

The input schema covers 100% of the 16 parameters with descriptions, so the baseline is 3. The description's mention of keywords, date ranges, and filters provides a high-level grouping but no additional semantic detail beyond what the schema already documents.

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 uses the specific verb 'Search' with the resource 'news articles' and names parameter categories (keywords, date ranges, filters), clearly conveying the core function. It does not explicitly differentiate from sibling tools like headlines, so it stops short of a top score.

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?

The description offers no guidance on when to use this tool versus the siblings headlines or usage, and provides no exclusions, prerequisites, or alternative routing. It simply states the action, leaving the agent to infer appropriate use cases.

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

usageAPI UsageA

Read-only

Inspect

Check your current API plan, usage limits, and remaining quota

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, and the description is consistent with that by using 'Check'. It adds concrete context about what is checked (plan, limits, quota), giving the agent a clear picture of the read-only scope without needing extra behavior details.

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?

A single, front-loaded sentence with no filler. Every word contributes meaning, and the key action ('Check') appears first. This is an ideal size for such a simple tool.

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

Completeness5/5

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

For a parameterless, read-only tool with no output schema, the description fully covers what an agent needs to know: what the tool checks and that it is non-destructive. No additional context is required.

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?

The tool has zero parameters, so the description carries no parameter burden. The baseline of 4 applies, and the description appropriately focuses on the return subject rather than inputs.

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 uses a specific verb ('Check') and identifies the exact resource ('your current API plan, usage limits, and remaining quota'). It is clearly distinct from the news-focused sibling tools, making the tool's purpose unambiguous.

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 clearly frames the tool as a usage/quota check, which makes its context obvious even without explicitly excluding alternatives. There are no exclusions stated, but the sibling news tools are so different that an agent can easily infer when this tool applies.

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.

3 tool updatesv0.1.0Sep 6, 2026
- First observedheadlines
- First observedsearch-news
- First observedusage

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.5/5.0

Scored 2026-09-06 20:00 across 3 tools

Disambiguation4/5

search-news and headlines are clearly distinct in purpose—one returns filtered article search results, the other returns top headlines by source/category. usage is completely separate, so there is little risk of selecting the wrong tool.

Naming Consistency3/5

Tool names are readable but follow mixed conventions: search-news uses a verb-noun pattern, while headlines and usage are bare nouns. This is not chaotic, but the naming style is inconsistent across the set.

Tool Count4/5

Three tools is a reasonable minimal set for a news API server covering search, headlines, and account usage. It is slightly thin but appropriate for the apparent scope.

Completeness3/5

The core news retrieval operations are covered, and usage is a nice operational addition. However, a typical news API also exposes available sources or categories, and that capability is missing, leaving a notable gap for agents that need source metadata.

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Related MCP Connectors

Search1API AOAuth
io.github.superagents-lab
Web search, news, page retrieval, sitemaps, and trending topics through Search1API.
Search Browser Automation
1173
newsflash A
sh.newsflash
Real-time corroborated news events + 5-year archive, for agents. Free tier, no key.
Search Open Data
52
finlight Financial NewsOAuth
me.finlight
Real-time financial news for AI agents: search by ticker and source, with sentiment and entities.
Finance Search AI & Machine Learning
2
QY-Stream Data Server A
ltd.qianyuan
One call instead of crawling 29 news/finance/AI sources mid-task. 100 free queries/day.
Search Finance
61

Related MCP Servers

News API MCP Server
Search Open Data
kcjonnyc
F
license
Not graded
quality
D
maintenance
Enables AI assistants to search news articles, get top headlines, and browse sources via the NewsAPI.org service.
Updated a year ago (2025-05-30 18:41 UTC)
-
mcp-newsdata
Search Research & Data
pipeworx-io
A
license
Not graded
quality
C
maintenance
Wraps the NewsData.io global news API, enabling AI agents to access and query global news data through natural language.
Updated 3 days ago (2026-09-18 22:51 UTC)
1 npm
MIT
mcp-newsapi
Search Entertainment & Media
pipeworx-io
A
license
Not graded
quality
B
maintenance
Enables fetching top headlines and searching news archives from NewsAPI.org, allowing AI agents to access current and historical news data.
Updated 3 days ago (2026-09-19 00:57 UTC)
MIT
Top News MCP Server
Search Entertainment & Media
aloewright
F
license
Not graded
quality
D
maintenance
Enables fetching top headlines, searching news articles across 150,000+ sources, and listing available news sources via NewsAPI.
Updated 6 months ago (2026-04-03 21:58 UTC)
-