Connect Desearch and your agent gets 22 tools, among them ai-search, extract, fetch. It answers at https://mcp.desearch.ai/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 1 of 1 times since 27 October 2026; the last check, on 27 October 2026, succeeded.
MCP server at mcp.desearch.ai, verified by introspection: 22 tools exposed.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
ai-search | AI search and analysis on web using Desearch AI Inputs: prompt, tools, date_filter, start_date, end_date, result_type |
extract | Extract a public URL and return its content as plain text or HTML using Desearch. Preferred over web-crawl for new integrations. API docs: https://www.desearch.ai/docs/api-reference/get-web-extract Inputs: url, format, js, wait |
fetch | Read a public page as text. Pass a URL returned by search. Inputs: id |
people-profiles | Everyone your People Searches found on one platform, one entry per person: their best-scoring result and the search that found them (found_by). Free; it does not run a new search. Search by name, handle, bio, or location with q, filter by c Inputs: platform, q, sort, limit, cursor, has |
people-search | Start a paid job billed to the user's Desearch balance: find people on X, YouTube, LinkedIn, or TikTok who match a plain-language description. Each person comes back with a fit score, why they matched, their audience, and public contacts an Inputs: platform, query, count, min_score, exclude, idempotency_key |
people-search-control | Pause, resume, or cancel a People Search task. Free. pause: a queued search pauses at once; a running one finishes its current batch first (status pausing, then paused). A search paused for more than 7 days is cancelled. resume: continues a Inputs: task_id, action |
people-search-status | Status, progress, and cost of one People Search task, plus a page of the people found so far: name, handle, url, platform, audience, location, fit score, why they matched, contacts, and links. Free. People arrive while the search runs: pass Inputs: task_id, cursor, limit, include_people |
people-search-tasks | Your People Search tasks, newest first, with status, counts, cost, why each ended search stopped (completion_reason, coverage_limited), and the metadata labels set on people-search. Free. Use it to find a task_id (filter by metadata to find Inputs: platform, status, limit, cursor, metadata |
search | Search the public web and return titles and links. Use fetch with a result URL to read the page. Inputs: query |
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. Inputs: url, format, js, wait |
web-links-search | Search the web for links using Desearch. Only the web source is accepted. Inputs: prompt, tools, count |
web-search | SERP-style web search using Desearch. Returns ranked titles, links, and snippets. Inputs: query, start |
x-links-search | AI search for X (Twitter) post links using Desearch. Returns links from posts that match the prompt. Inputs: prompt, count |
x-post-by-id | Fetch a single X (Twitter) post by its ID. Inputs: id |
x-post-replies | Fetch replies to an X (Twitter) post, with an optional keyword query. Inputs: post_id, count, query |
x-post-retweeters | List users who retweeted an X (Twitter) post. Pass cursor to page through more users. Inputs: id, cursor |
x-posts-by-urls | Fetch full X (Twitter) posts for a list of post URLs. Inputs: urls |
x-posts-by-user | Search X (Twitter) posts by a specific user, with an optional keyword query. Inputs: user, query, count |
x-search | Search X (Twitter) using Desearch AI. Optional filters narrow by user, date, language, verification, media, and engagement. Sort stays Top. Inputs: query, count, user, start_date, end_date, lang |
x-trends | Retrieve trending topics on X (Twitter) for a location by its WOEID using Desearch. Inputs: woeid, count |
x-user-posts | Retrieve a user's X (Twitter) timeline posts by username. Pass cursor to page through more posts. Inputs: username, cursor |
x-user-replies | Fetch posts and replies by an X (Twitter) user, with an optional keyword query. Inputs: user, count, query |
Every block below points at https://mcp.desearch.ai/mcp. Pick your client and copy.
claude mcp add --transport http desearch https://mcp.desearch.ai/mcp
{
"mcpServers": {
"desearch": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.desearch.ai/mcp"]
}
}
}{
"mcpServers": {
"desearch": {
"url": "https://mcp.desearch.ai/mcp"
}
}
}{
"servers": {
"desearch": {
"type": "http",
"url": "https://mcp.desearch.ai/mcp"
}
}
}{
"context_servers": {
"desearch": {
"url": "https://mcp.desearch.ai/mcp"
}
}
}{
"mcpServers": {
"desearch": {
"serverUrl": "https://mcp.desearch.ai/mcp"
}
}
}{
"mcpServers": {
"desearch": {
"url": "https://mcp.desearch.ai/mcp"
}
}
}name: Desearch
version: 0.0.1
schema: v1
mcpServers:
- name: Desearch
type: streamable-http
url: https://mcp.desearch.ai/mcp{
"mcpServers": {
"desearch": {
"httpUrl": "https://mcp.desearch.ai/mcp"
}
}
}{
"mcpServers": {
"desearch": {
"type": "http",
"url": "https://mcp.desearch.ai/mcp"
}
}
}{
"mcpServers": {
"desearch": {
"url": "https://mcp.desearch.ai/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.desearch.ai%2Fmcp&type=streamable_http&id=desearch&name=Desearch
It answered our last check on 27 October 2026. Over 1 checks since 27 October 2026 it answered 1. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by desearch.ai and served from mcp.desearch.ai, the vendor's own domain: https://mcp.desearch.ai/mcp.
22, as returned by the server's own tools/list on 27 October 2026: ai-search, extract, fetch, people-profiles, people-search, people-search-control, people-search-status, people-search-tasks, and 14 more.
It answered our last check on 27 October 2026. Over 1 checks since 27 October 2026 it answered 1.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.desearch.ai/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: mcp.desearch.ai. Endpoint host: mcp.desearch.ai. ARD identifier: urn:air:mcp.desearch.ai:mcp:desearch.
First indexed 27 October 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.