Neurobird Search MCP server

A hosted Model Context Protocol server that gives anAI agent web search with the page content already extracted, plus clean markdownextraction of any URL.

There is nothing to install and nothing to run locally. The server is hosted athttps://search.neurobird.com/mcp over the streamable HTTP transport.

claude mcp add --transport http neurobird-search \
  https://search.neurobird.com/mcp \
  --header "Authorization: Bearer $NEUROBIRD_KEY"

Get a key with one unauthenticated request. No signup form, no email, no card:

curl -X POST https://search.neurobird.com/keys

Every key carries 1,000 free credits a month.

Tools

`web_search`

Search the live web and get ranked results with the relevant passages alreadyextracted from each page, so a follow up fetch is usually unnecessary.

Parameter	Type	Default	Notes
`query`	string	required	The search query.
`search_depth`	`basic` \| `standard` \| `advanced`	`standard`	`advanced` expands the query and reads more pages.
`max_results`	integer	6	1 to 20.
`include_answer`	boolean	true	A grounded answer written only from retrieved passages.
`include_domains`	string[]		Only return results from these domains.
`exclude_domains`	string[]
`days`	integer		Restrict to the last N days.
`topic`	`general` \| `news` \| `code` \| `science` \| `finance`	`general`

`extract_url`

Fetch one or more URLs and return their main content as clean markdown, withnavigation, adverts and boilerplate removed. PDFs are converted to text.

Parameter	Type	Notes
`urls`	string[]	Required.
`query`	string	Trims each page to the passages relevant to it.
`format`	`markdown` \| `text`	Default `markdown`.

Other MCP clients

The same URL works in any client that supports the streamable HTTP transport.

{
  "mcpServers": {
    "neurobird-search": {
      "type": "http",
      "url": "https://search.neurobird.com/mcp",
      "headers": { "Authorization": "Bearer nbs-..." }
    }
  }
}

Tested with Claude Code. Cursor, Windsurf, Zed and the Claude desktop app all accept astreamable HTTP MCP server in this shape.

What makes the results different

Page passages, not snippets. Each result carries the part of the page that answersthe query, extracted from the live page, at no extra credit.
Quotes checked against the source. When an answer is requested, every supportingquote is matched back against the extracted source text. A quote that fails is returnedmarked unverified rather than silently dropped, so an agent can audit a claim instead oftrusting it.
Rank fusion across engines. Results are fused from several engines with reciprocalrank fusion, so agreement between independent rankings drives the ordering.
Per stage timings in every response, so latency can be attributed from outside.

Pricing

Credits: basic or standard search 1, advanced search 2, grounded answer +1,extract_url 1 per page.

	Per 1,000 searches
Free tier	1,000 credits a month, no card
Basic search	$2
Deep search	$4
Deep search with grounded answer	$6
At 1M credits a month	$1 per 1,000

Honest limits

Median latency on the current single server deployment is about 15 seconds basic,22 seconds standard and 28 seconds advanced. Upstream engines and the answer modelaccount for nearly all of it. The HTTP streaming endpoint returns ranked links atabout 5 seconds.
There is no index of our own. Coverage and freshness inherit from upstream engines.
Retrieval capacity, not code, is the scaling limit today.

License

MIT. See LICENSE.

Neurobird Search MCP server