Desearch MCP server

Which servers in the official MCP registry are Desearch's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-09

← Back to Desearch

Whose server it is

Registry nameio.github.Desearch-ai/mcp-desearchpublished by Desearch-ai on GitHub

Published under the GitHub organisation Desearch-ai, the same one desearch.ai links from its homepage. The registry ties that namespace to a GitHub sign-in.

When we asked itchecked 2026-10-09

Stateanswerschecked 2026-10-09
Tools15
Server calls itselfDesearch
Server version0.1.4
Protocol version2025-06-18

On 2026-10-09 the server answered initialize and tools/list without a sign-in. First answer in 180 ms.

Tools it offers15 tools · read 2026-10-09

ai-search
AI search and analysis on web using Desearch AI
x-search
Search X (Twitter) using Desearch AI. Optional filters narrow by user, date, language, verification, media, and engagement. Sort stays Top.
web-search
SERP-style web search using Desearch. Returns ranked titles, links, and snippets.
web-links-search
Search the web for links using Desearch. Only the web source is accepted.
x-links-search
AI search for X (Twitter) post links using Desearch. Returns links from posts that match the prompt.
x-posts-by-urls
Fetch full X (Twitter) posts for a list of post URLs.
x-post-by-id
Fetch a single X (Twitter) post by its ID.
x-posts-by-user
Search X (Twitter) posts by a specific user, with an optional keyword query.
x-post-retweeters
List users who retweeted an X (Twitter) post. Pass cursor to page through more users.
x-user-posts
Retrieve a user's X (Twitter) timeline posts by username. Pass cursor to page through more posts.
x-user-replies
Fetch posts and replies by an X (Twitter) user, with an optional keyword query.
x-post-replies
Fetch replies to an X (Twitter) post, with an optional keyword query.
extract
Extract a public URL and return its content as plain text or HTML using Desearch. Preferred over web-crawl for new integrations.
web-crawl
Crawl a public URL and return its content as plain text or HTML on the legacy Desearch /web/crawl route. The SDK marks webCrawl deprecated in favor of extract; this tool stays for parity with that route. Prefer extract for new integrations.
x-trends
Retrieve trending topics on X (Twitter) for a location by its WOEID using Desearch.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "mcp-desearch": {
      "type": "http",
      "url": "https://mcp.desearch.ai/mcp"
    }
  }
}

Also shipped through: npm

OpenAPI spec

34 paths, read 2026-10-09. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.