Connect DeepSearch and your agent gets 3 tools, among them ask_about_person, build_dossier, search_people. It answers at https://deepsearch.app/api/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 10 of 10 times since 4 September 2026; the last check, on 17 October 2026, succeeded.
Research a person's public footprint from a name, phone, email, or username. Sourced.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
ask_about_person | Answer a specific professional question using source excerpts about a selected possible match. Supports roles, education, publications, projects and professional mentions. Cannot assess trustworthiness, verify identity, link accounts, inves Inputs: name, profile_url, question |
build_dossier | Return sourced professional excerpts about a selected possible match: roles, education, publications, projects and professional mentions. Uses a separate professional research pipeline, never the shared personal dossier cache. Results may b Inputs: name, profile_url |
search_people | Find possible name matches in public professional sources for meeting preparation, professional research or journalism. Returns supporting source URLs and uncalibrated match confidence estimates, not verified identities. Ask the user to cho Inputs: query, type, professional_context |
Every block below points at https://deepsearch.app/api/mcp. Pick your client and copy.
claude mcp add --transport http deepsearch https://deepsearch.app/api/mcp
{
"mcpServers": {
"deepsearch": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://deepsearch.app/api/mcp"]
}
}
}{
"mcpServers": {
"deepsearch": {
"url": "https://deepsearch.app/api/mcp"
}
}
}{
"servers": {
"deepsearch": {
"type": "http",
"url": "https://deepsearch.app/api/mcp"
}
}
}{
"context_servers": {
"deepsearch": {
"url": "https://deepsearch.app/api/mcp"
}
}
}{
"mcpServers": {
"deepsearch": {
"serverUrl": "https://deepsearch.app/api/mcp"
}
}
}{
"mcpServers": {
"deepsearch": {
"url": "https://deepsearch.app/api/mcp"
}
}
}name: DeepSearch
version: 0.0.1
schema: v1
mcpServers:
- name: DeepSearch
type: streamable-http
url: https://deepsearch.app/api/mcp{
"mcpServers": {
"deepsearch": {
"httpUrl": "https://deepsearch.app/api/mcp"
}
}
}{
"mcpServers": {
"deepsearch": {
"type": "http",
"url": "https://deepsearch.app/api/mcp"
}
}
}{
"mcpServers": {
"deepsearch": {
"url": "https://deepsearch.app/api/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fdeepsearch.app%2Fapi%2Fmcp&type=streamable_http&id=deepsearch&name=DeepSearch
It answered our last check on 17 October 2026 in 406 ms. Over 10 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by deepsearch.app and served from deepsearch.app, the vendor's own domain: https://deepsearch.app/api/mcp.
3, as returned by the server's own tools/list on 9 September 2026: ask_about_person, build_dossier, search_people.
It answered our last check on 17 October 2026 in 406 ms. Over 10 checks since 4 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://deepsearch.app/api/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: app.deepsearch. Endpoint host: deepsearch.app. ARD identifier: urn:air:app.deepsearch:mcp:deepsearch.
First indexed 31 August 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.