DeepSearch

app.deepsearchPublished by deepsearch.appOfficial publisherv1.0.1Updated Oct 25, 2026

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

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingBusiness & Commerce

Overview

AI-generated overview

DeepSearch is a remote MCP server that lets an assistant research people and companies from public sources, returning sourced dossiers, answers and lookups.

What you can do
Resolve a name, phone number, email or username to ranked candidate people, and answer single questions about a person or build a full sourced profile of them, including contacts, social accounts, work history and mentions. Search companies and build company dossiers from public sources. Run reverse image searches for image appearances and look up vehicles by VIN. Create, list, inspect, cancel and page through durable lookup jobs, including reading saved progress events.
When to use it
Useful when a question is about who someone is or what a company or vehicle looks like across public sources, and you want results with links to their origin rather than raw search results. Also suited to longer lookups that should run as durable jobs.
Requirements
A remote streamable HTTP endpoint at deepsearch.app; no local package, environment variables or headers are declared. Lookups require the relevant account scope (search or dossier), and account usage is charged for provider work.
Before you install
Provider work is billed to the account, and valid empty results can still consume usage; refreshing a cached dossier forces a paid rebuild, and cancelled jobs may keep charges for work already delivered. The server is limited to public sources and states it does not use private accounts, breach data or facial recognition, but it still aggregates personal data about individuals, so consider privacy and consent before running lookups.

Installation

In SourceWeft

  1. Open DeepSearch in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/app.deepsearch%2Fdeepsearch/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "deepsearch": {
      "type": "http",
      "url": "https://deepsearch.app/api/mcp"
    }
  }
}

Tools

12

search_people

Search people

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. Requires search scope. Provider work consumes account usage; cached results consume none.

Parameterstypequeryrequiredformatsandboxplatformsidempotency_key

build_dossier

Build dossier

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. Repeating the same request from the same account replays its cached profile: free and instant. Profiles are not shared between accounts. Public sources only - never private accounts or breach data. Requires dossier scope. Provider work consumes account usage; cached results consume none.

Parametersnamerequiredrefreshsandboxheadlineusernameidempotency_key

ask_about_person

Ask about a person

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. Requires chat scope. Provider work consumes account usage; cached results consume none.

Parametersnamerequiredcontextsandboxquestionrequiredidempotency_key

search_companies

Search companies

Search companies using public sources. Requires the search scope. Account usage is charged for provider work; valid empty results can still consume usage. For long requests use create_lookup_job. Public sources only - never private accounts or breach data. Requires search scope. Provider work consumes account usage; cached results consume none.

Parametersqueryrequiredformatsandboxidempotency_key

build_company_dossier

Build company dossier

Build company dossier using public sources. Requires the dossier scope. Account usage is charged for provider work; cached results are free and refresh forces a paid rebuild. For long requests use create_lookup_job. Public sources only - never private accounts or breach data. Requires dossier scope. Provider work consumes account usage; cached results consume none.

Parametersformatcompanyrequiredrefreshsandboxidempotency_key

lookup_vin

Look up vehicle

Look up vehicle using public sources. Requires the dossier scope. Account usage is charged for provider work; cached results are free and refresh forces a paid rebuild. For long requests use create_lookup_job. Public sources only - never private accounts or breach data. Requires dossier scope. Provider work consumes account usage; cached results consume none.

Parametersvinrequiredformatrefreshsandboxidempotency_key

get_lookup_job_events

Get lookup progress

Read saved progress after a numeric event ID. Free; account-owned jobs only. The next_cursor resumes subsequent calls.

Parametersidrequiredafterlimitidempotency_key

create_lookup_job

Create lookup job

Run one of the seven lookups durably. The operation's existing scope and billing apply; creating a job adds no surcharge. Use Idempotency-Key to retry safely.

Parametersidempotency_key

get_lookup_job

Get lookup job

Get saved progress status and the completed result. Free; account-owned jobs only.

Parametersidrequiredidempotency_key

cancel_lookup_job

Cancel lookup job

Cancel your queued or running job. Work already delivered can remain charged; cancellation adds no charge.

Parametersidrequiredidempotency_key

list_lookup_jobs

List lookup jobs

Page through your saved lookup jobs. Free.

Parameterslimitcursoridempotency_key

Version history

1
  1. v1.0.1LatestSep 16, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.

Other Deepsearch integrations

Deepsearch

Published by GitHub account CloudCorpRecords

Local MCP server that gives an assistant Exa-powered neural web search, code context packs, and full-page crawling.

STDIODesktop only
Web Search & Scraping3 toolsOct 31, 2026