Skip to main content
FaceSearch MCP Server

Face Search for AI Agents, Natively

A hosted Model Context Protocol server that gives Claude, Cursor, and any MCP-compatible client five typed face-search tools. One Bearer token, zero infrastructure.

5 tools • streamable HTTP • same API keys as the REST API

Trusted by thousands worldwide

15,000+ Searches
50+ Countries
256-bit Encryption
99.7% Accuracy

How the MCP Server Works

Install once in your MCP client config, then let your agent drive face searches on command.

Generate an API Key
1

Generate an API Key

Log in to the dashboard, create a key scoped to search:read and search:write, and copy the plaintext. The same key works for REST and MCP.

Register the Server
2

Register the Server

Paste the MCP server block into your client config. Restart your client. Five tools appear automatically: submit_face_search, get_search_status, list_searches, delete_search, get_credits.

Let the Agent Run
3

Let the Agent Run

Ask your agent to 'find where this photo appears online' and it handles the rest: submit, poll, present results, flag low-confidence matches, and refuse unsafe requests.

MCP Server Features

Built to the current MCP spec with guardrails that AI agents actually need.

MCP Server face search features visualization

Five Typed Tools

submit_face_search, get_search_status, list_searches, delete_search, get_credits — each with a zod input schema, clear description, and mapped errors that Claude can explain to the user.

Bearer-Token Auth

Uses the same API keys as the REST API. One key, two surfaces. Revocation propagates to both within one request, so a lost key can be killed once from the dashboard.

SSRF-Protected URL Input

When a tool call supplies imageUrl, the server resolves the hostname, rejects private CIDR ranges, forbids HTTP (HTTPS only), disables redirects, and enforces a 10-second timeout and 10 MB body cap.

MCP-Level Idempotency

The server derives the client idempotency key from each MCP call's requestId. Transport-level retries automatically dedupe, so an agent that replays a tool call gets the same jobId without double-charging credits.

Shared Rate Limits

MCP tool calls share the same rate-limit bucket as REST. A leaked key cannot be used to flood both surfaces independently — the ceiling is shared and enforced at Redis speed.

Structured Tool Errors

Instead of bare protocol errors, every failure returns CallToolResult with isError: true, a human-readable text content block (for Claude to explain to the user), and a structuredContent payload for programmatic clients.

Where the MCP Server Fits

When your AI agent needs to do face search as part of a larger workflow.

Claude Desktop calling the FaceSearch MCP tools
Claude

Claude Code Workflows

Engineers using Claude Code for investigation, OSINT, or content moderation can drop the MCP server into their config and let Claude run searches conversationally.

A Cursor IDE session using MCP face-search tools
IDE

Cursor and IDE Agents

Cursor-style IDE agents can submit face searches as part of larger pipelines: scrape a page, extract a face, call FaceSearch, annotate the results — all in one run.

A custom AI agent invoking the MCP server
Custom

Custom MCP Hosts

Any MCP-compatible host works. Build a voice assistant, a Discord bot, or a custom agent framework and plug FaceSearch in via the same Bearer-auth HTTP endpoint.

Trusted Face Search Platform

10M+
Searches Completed
Trustworthy results worldwide
95%
Match Accuracy
Powered by advanced AI
50K+
Active Users
Growing community
100M+
Sources Scanned
Comprehensive coverage

What AI Builders Say

Feedback from teams wiring FaceSearch into their agent workflows.

"The shared Bearer auth between MCP and REST was the feature that sold me. I test with curl during development and switch to Claude Code with the same key, no re-plumbing."
Lena K.
AI Researcher
"SSRF protection on imageUrl saved me from a dumb mistake on day two. I passed a redirect URL by accident and the server rejected it cleanly instead of hitting our internal metadata service."
Arjun N.
OSINT Engineer
"Structured error payloads mean Claude can actually explain rate limits to our analysts. Before, failures were opaque protocol errors; now they come back as plain English with actionable details."
Jamie W.
Trust and Safety Tooling Lead

Simple, Transparent Pricing

Choose the plan that fits your needs. No hidden fees, cancel anytime.

FREE

$0/month

Perfect for getting started

  • Face Search
Start Free
MOST POPULAR

PRO

$29/month

For professionals and power users

  • 60 Credits per month ($0.48 per credit)
  • Face Search
  • Search History
  • Can Export Profile to PDF
Pay As You Go

Or Buy Credit Packs

Starter

3credits

$6

$2.00/credit

SAVE 20%

Basic

30credits

$24

$0.80/credit

SAVE 31%

Standard

100credits

$69

$0.69/credit

SAVE 34%

Pro

300credits

$199

$0.66/credit

SAVE 40%

Enterprise

1000credits

$599

$0.60/credit

MCP Server FAQ

What agent builders ask before wiring the server into production.

Connect Your Agent to FaceSearch

Drop five lines into your MCP client config and your agent can run face searches conversationally.

Generate an MCP Key

No credit card required