INDIVIDUAL MCP TOOL

check_coverage

Check whether a news domain is in the typesearch index (pass domain), or get the index coverage: how many sources and articles, by country and by language.

typesearch.ainone authenticationAvailability not checked

LIVE ENDPOINT

https://api.typesearch.ai/mcp

No auth detected

Connect to this endpoint to inspect the live schema for check_coverage and invoke it with your own arguments.

Indexed input schema

{}

Risk classification

Inferred read-only · medium confidence · heuristic, not a guarantee.

No write-capable action terms were found; this is not proof that invocation has no side effects.

Parent server

typesearch.ai

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.typesearch]
url = "https://api.typesearch.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "typesearch": {
      "type": "http",
      "url": "https://api.typesearch.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: typesearch
Remote MCP URL: https://api.typesearch.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "typesearch": {
      "url": "https://api.typesearch.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "typesearch": {
      "type": "http",
      "url": "https://api.typesearch.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "typesearch",
  "transport": "streamable-http",
  "url": "https://api.typesearch.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

Related tools

search_news — Search recent news on any topic across a curated index of news outlets worldwide, judged by a relevance model.
get_contents — Get the title, standfirst, date, source and a short verbatim excerpt (up to 25 words) of up to 10 news article URLs.
find_similar — Find other news articles about the same story as a given article URL, across the index (the last 7 days by default).