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.
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.
Thousands of Searches
Available Worldwide
256-bit Encryption
High Match Accuracy
A hosted Model Context Protocol server that gives Claude, Cursor, and any MCP-compatible client five typed face-search tools.
- What you search with
- One photo containing a face. There is no text-query search.
- What you get back
- Ranked pages where a matching face appears, each with a confidence score and a source link.
- How a match is made
- Facial recognition. The face is turned into an embedding — a list of numbers — and compared by distance, not by filename, caption or pixels. How Does Facial Recognition Work?
- Cost per search
- 3 credits. New accounts start with 3 free credits and no credit card.
- Photo retention
- Uploads are deleted within 24 hours of the search finishing.
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
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
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
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.
Five Typed Tools
submit_face_search, get_search_status, list_searches, delete_search, get_credits. Each comes with a zod input schema, a 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, because 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.
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.
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
10 MB
Max Upload Size
JPEG, PNG, or WebP photos
24 h
Image Retention
Uploads deleted automatically
24/7
Search Availability
Search any time, anywhere
3
Credits per Search
Simple, transparent pricing
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.”
“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.”
“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.”
Simple, Transparent Pricing
Choose the plan that fits your needs. No hidden fees, cancel anytime.
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
Or Buy Credit Packs
Pay As You Go
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
