Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

DeepSearch

REMOTE · DEEPSEARCH.APP · SCANNED SEP 20

Research a person's public footprint from a name, phone, email, or username. Sourced.

Available components

+2 this week 89 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security80
Transport & Reachability100
Schema Quality & AI Usability85
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 880 tokens (~125/item across 7 items; 3 tools + 4 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
  • Supports UI / widget rendering.Pass
Install

How do I install the DeepSearch MCP server?

DeepSearch is a hosted endpoint at https://deepsearch.app/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · deepsearch.app

# add to Claude Code
claude mcp add --transport http app-deepsearch-deepsearch 'https://deepsearch.app/api/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "app-deepsearch-deepsearch": {
      "url": "https://deepsearch.app/api/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "app-deepsearch-deepsearch": {
      "type": "http",
      "url": "https://deepsearch.app/api/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.app-deepsearch-deepsearch]
url = "https://deepsearch.app/api/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "app-deepsearch-deepsearch": {
      "type": "remote",
      "url": "https://deepsearch.app/api/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add app-deepsearch-deepsearch --url 'https://deepsearch.app/api/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  app-deepsearch-deepsearch:
    url: "https://deepsearch.app/api/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "app-deepsearch-deepsearch": {
      "Transport": "http",
      "Url": "https://deepsearch.app/api/mcp"
    }
  }
}
# add to Vellum
assistant mcp add app-deepsearch-deepsearch -t streamable-http -u 'https://deepsearch.app/api/mcp'
// mcp.json
{
  "mcpServers": {
    "app-deepsearch-deepsearch": {
      "type": "http",
      "url": "https://deepsearch.app/api/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 18 Sept 26 0
    • Stability: 0.97 → pass security
  • 17 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

  • 8 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

  • 6 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

  • 4 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Probed https://deepsearch.app/api/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=deepsearch.app CN=YR1,O=Let's Encrypt,C=US 17 Aug 2026 15 Nov 2026 RSA 2048 SHA256-RSA 65b392ee32cd7f71552c981a54d33e55d4e
SANs: deepsearch.app
CN=YR1,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA a20253f15f2691c05dc1ce13b9bcca4e
CN=Root YR,O=ISRG,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 RSA 4096 SHA256-RSA f24b6d17f9d9ad7cb1c9fea78782699f

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of deepsearch.app. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
app. present 23684 8 Verified
deepsearch.app. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=63072000

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://deepsearch.app/api/mcp Verified 200
http (plaintext) http://deepsearch.app/api/mcp HTTPS enforced 308 https://deepsearch.app/api/mcp
MCP tools · 3 exposed · ~521 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
ask_about_person ~150

Answer one specific question about a person, grounded in their public footprint, and suggest follow-ups. Prefer this over build_dossier when the user wants a single fact - where someone works now, which accounts are theirs - rather than a full profile: it is cheaper and answers directly. Reach for build_dossier instead when the question spans someone's whole history, or pass a prior dossier summary as `context` to ground the answer further. Public sources only - never private accounts or breach data.

NameTypeReqDescription
contextstringOptional extra grounding context, e.g. a prior dossier summary.
namestringyesThe person the question is about.
questionstringyesYour question about the person.

No output schema declared.

No examples provided.

build_dossier ~204

Assemble one person's entire public footprint into a single sourced profile: identity, contact details, social accounts unified across platforms, work history, education, relatives, locations, and web mentions - every claim linked to the page it came from. Prefer this over reading search results yourself when you need the whole picture of one person rather than a single fact; it does the cross-platform correlation that a web search leaves to you. Pass a name plus the headline or username from search_people so the right individual is profiled. Repeat profiles are served from a shared cache: free and instant. Public sources only - never private accounts or breach data.

NameTypeReqDescription
headlinestringOptional descriptor to disambiguate, e.g. 'Engineer, London'.
namestringyesThe person's full name.
refreshbooleanRebuild from scratch instead of using the shared cache. Always meters.
usernamestringOptional known handle to focus the profile on the right person.

No output schema declared.

No examples provided.

search_people ~167

Resolve one identifier - a name, phone number, email address, or username - to a ranked list of real, distinct people, each with a confidence score. Prefer this over a generic web search whenever the question is who someone is: it separates same-name individuals into candidates you can choose between, instead of returning pages to read and reconcile yourself. Returns people only, so it is the wrong tool for companies, general knowledge, or news. Public sources only - never private accounts or breach data.

NameTypeReqDescription
platformsarrayOptional: for a username search, restrict discovery to these platforms (e.g. instagram, x, github).
querystringyesName, phone number, email address, or username to look up.
typestringHow to interpret the query.

No output schema declared.

No examples provided.

Common questions

What is the DeepSearch MCP server?

DeepSearch is an MCP server listed in the public MCP registry as app.deepsearch/deepsearch. Research a person's public footprint from a name, phone, email, or username. Sourced. This page covers its hosted endpoint (https://deepsearch.app/api/mcp).

Is the DeepSearch MCP server safe to use?

DeepSearch scores 89 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the DeepSearch MCP server expose?

DeepSearch exposes 3 tools: search_people, build_dossier, ask_about_person. Their descriptions and schemas cost roughly 521 tokens of context every time the server is loaded.

Does the DeepSearch MCP server require authentication?

No. We connected to DeepSearch without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the DeepSearch MCP server still maintained?

DeepSearch is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.