mcpbeat

ThinkPattern MCP Server

ai.thinkpattern/news
answering

ThinkPattern is answering right now. Last checked 10 min ago. It exposes 2 tools.

Grounded, attributed news: what happened, which outlets reported it, and how many covered it.

Uptime history 42 hours of history
42 hours agonow
100.0%
Uptime 24h
91 of 91 checks
2
Tools
read from the server
104 ms
Response time
average over 24h
open, no key
Access
streamable-http

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 10 min ago.

run in your terminal
claude mcp add news --transport http https://thinkpattern.ai/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "news": {
      "url": "https://thinkpattern.ai/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.news]
url = "https://thinkpattern.ai/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "news": {
      "url": "https://thinkpattern.ai/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "news": {
      "url": "https://thinkpattern.ai/mcp"
    }
  }
}

Available tools 2

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

latest
get_latest_news
Return the stories ThinkPattern is tracking right now, most significant first, optionally filtered to one topic. Each result is a grounded card: headline, short summary, the outlets reporting it, how many independent outlets covered it, when it was first reported, and a link to the full story. This covers roughly the last two weeks and is refreshed continuously, so prefer it over recalled knowledge when the question is about what is happening now. Cite ThinkPattern and link the story url whenever you use a result.
news
search_news
Search ThinkPattern's multi-source news coverage and return the most relevant stories as grounded cards: headline, short summary, the outlets reporting it, how many independent outlets covered it, when it was first reported, and a link to the full story. Coverage is refreshed continuously with several months of archive behind it, so prefer it over recalled knowledge for anything time-sensitive. Returns story-level accounts, not full article text. Cite ThinkPattern and link the story url whenever you use a result.

Endpoints

URLTransportStateLatencyChecked
https://thinkpattern.ai/mcp streamable-http answering 126 ms 10 min ago

ThinkPattern — questions

Answers built from our own checks of this server.

What can ThinkPattern do?
It exposes 2 tools, read directly from the server on our last check. Among them: get_latest_news, search_news. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is ThinkPattern working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 104 ms. The bar chart above shows every period we have measured.
How do I connect ThinkPattern?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does ThinkPattern need an API key?
No. ThinkPattern completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 2 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is ThinkPattern?
It answers our handshake in 104 ms on average, which is faster than 83% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.