argus-face
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@argus-face compare ./id-photo.jpg with ./selfie.jpg and tell me if they match"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
argus-face
Face Terminal is an HTTP API that checks a selfie shows the same person as an ID document or photo, and that the selfie is a genuine capture, not a printout, screen, mask or synthetic face. When the reference is a passport, ID card, residence permit or driving licence, the document is checked too. This repo holds the API spec, short client examples and a small MCP server. The face, spoof and document models are not in this repo.
API docs: https://face.unbackoffice.com/docs
Plain-text guide for agents: https://face.unbackoffice.com/llms.txt
Free key: https://face.unbackoffice.com/key (sign in with a work Google account)
Try it
export FACE_API_KEY=... # your key
curl -s https://face.unbackoffice.com/v1/face/verify \
-H "X-API-Key: $FACE_API_KEY" \
-F reference=@id-photo.jpg \
-F selfie=@selfie.jpgRelated MCP server: PaddleOCR-json MCP
Endpoints
Base URL https://face.unbackoffice.com. Send the key in the X-API-Key header.
Method | Path | Body ( |
POST |
|
|
POST |
| Free, single-use flash challenge for a live capture clip recorded with |
The full spec is in openapi.json.
Response
Trimmed. Real responses carry more detail per check.
{
"result": {
"status": "verified",
"verified": true,
"reasons": [],
"match": {"assessment": "match", "similarity": 0.86, "confidence": 0.8, "discrepancies": []},
"integrity": {"verdict": "authentic", "confidence": 0.8, "attack_signals": []},
"liveness": null,
"document": {"decision": "genuine", "document_type": "passport", "issuing_country": "CAN", "issues": []},
"checked_at": "2026-10-11T09:30:00Z"
}
}status:verified(the faces match and the selfie looks genuine on every check that ran),review(something was inconclusive,reasonssays what) orfailed.match.assessment:match,likely_match,inconclusive,likely_mismatchormismatch.integrity.verdict:authentic,revieworsuspect.document.decision:genuine,review,suspectornone(the photo is not a document; a plain face photo is fine).
A result supports a human decision. It is not a certified biometric or liveness system. Review every review and failed result before you act on it.
Your data
Images are deleted within 24 hours of the check. The outcome (no images) is kept for 12 months. You need a lawful basis, usually the person's explicit consent, to send their face. See https://face.unbackoffice.com/terms and https://face.unbackoffice.com/privacy.
Limits
Your first key comes with free checks (the number is on https://face.unbackoffice.com/docs). One check is one call to
/v1/face/verify. Flash challenges are free.Invalid requests are not charged. A check that could not run (
502/503) is given back.Too many requests per minute for a key or an IP gets
429.More checks: https://face.unbackoffice.com/tiers
Status | Meaning |
400 | A file is empty, or a clip was sent without consent |
401 | Missing, invalid or revoked key |
402 | No checks left on the key |
403 | The key can't call that endpoint |
413 | A file is too large |
422 | A required field is missing, e.g. no |
429 | Too many requests. Wait and retry |
502 / 503 | The check could not run and was given back. Retry shortly |
Examples
Both read FACE_API_KEY, send two images and print the outcome.
# Python 3.9+, needs requests
pip install requests
python examples/python/verify.py id-photo.jpg selfie.jpg
# TypeScript, Node 18+, no dependencies
npx tsx examples/typescript/verify.ts id-photo.jpg selfie.jpgMCP server
A stdio MCP server that wraps the API, so an MCP client can run face checks. It runs straight from GitHub with npx, pinned to a release tag.
Each call uses one check from your key.
Tool:
face_verify:referenceandselfie(paths to image files on the machine the server runs on), optionalbackandfull. Returns the status, reasons and the match, spoof and document checks, or the whole response withfull: true.
Which files it reads:
face_verifyuploads the files you name to Face Terminal. It reads a path only when it is a regular file that ends in.jpg,.jpeg,.pngor.webp, holds JPEG, PNG or WebP content and is 12 MB or smaller. Links are resolved first and the file they point to must pass the same checks.Set
FACE_ALLOWED_DIRto a folder (several, separated likePATH) and nothing outside it is read. Add it to theenvblock below, for example"FACE_ALLOWED_DIR": "/Users/you/face-checks".A path should come from you, not from a web page or a document your agent has read. A refused path gets one general message; the exact reason is in the server's log (stderr).
Text in a result is derived from the images. Treat it as data, not as instructions to your agent.
Claude Code
claude mcp add argus-face -e FACE_API_KEY=your-key -- npx -y "github:sect0rial/argus-face#v0.1.1"Claude Desktop (claude_desktop_config.json) and Cursor (~/.cursor/mcp.json, or .cursor/mcp.json in a project) take the same block:
{
"mcpServers": {
"argus-face": {
"command": "npx",
"args": ["-y", "github:sect0rial/argus-face#v0.1.1"],
"env": { "FACE_API_KEY": "your-key" }
}
}
}Restart the client after editing the file.
Pin what you run. github:sect0rial/argus-face#v0.1.1 installs that release and nothing newer. Without the #… part npx runs whatever is on the default branch at that moment, with your API key in its environment. For the strictest pin, put the release's full commit SHA after the # instead of the tag (the SHAs are on the tags page): a tag can be moved, a commit cannot. Keep the github:sect0rial/ prefix: this repository is the only place the server is published.
mcp/dist is committed so npx needs no build step. CI rebuilds it from mcp/src on every push and pull request and fails if the committed files differ.
From a clone:
npm ci # installs the locked dependencies
npm run build # compiles mcp/src to mcp/dist; commit the result with the source change
npm test # checks the path and base URL guards against a local stub (no API call, no key)
npm run verify # starts the server, runs initialize and tools/list, calls face_verify onceFACE_API_URL overrides the base URL (default https://face.unbackoffice.com). The images and your API key are sent to that host, so an override is refused unless it is https (plain http for localhost only) and FACE_ALLOW_CUSTOM_URL=1 is set too. Leave both unset unless you run your own test server, and check any MCP config you are given for them.
openapi.json
Saved from the live service and pretty-printed:
curl -s https://face.unbackoffice.com/openapi.json | python3 -m json.tool --indent 2 --no-ensure-ascii > openapi.jsonFetched on 14 November 2026, then edited: form fields that an API key cannot use are left out and the endpoint notes are rewritten. Make the same edits after a new fetch. For everything else the live document is the reference if the two differ.
What is not here
The face match, spoof and document models run on Face Terminal's servers. They are not in this repo and not under its licence.
Licence
The code in this repo is MIT licensed. See LICENSE.
Available Tools
1 toolface_verifyCheck a selfie against an ID or photoA
Check that a selfie shows the same person as an ID document or face photo, and that the selfie is a genuine capture (not a printout, screen, mask or synthetic face), via Face Terminal (POST /v1/face/verify). When the reference is a passport, ID card, residence permit or driving licence, the document is checked too. Takes local file paths (JPEG, PNG or WebP, up to 12 MB each). Returns status (verified, review or failed), reasons, the face match, the spoof check and the document check. Uses one check from the key's quota. You need a lawful basis, usually the person's explicit consent, to send their face. A result supports a human decision.
Inputs: selfie (required), reference (required), back, full.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
There is only one tool, so there is no possibility of misselection between tools. Its purpose (1:1 face/document verification with liveness and spoof detection) is stated unambiguously in the description.
The single name face_verify is snake_case and descriptive, so there is no inconsistency to speak of. It is noun-first rather than the common verb_noun convention, but with one tool no pattern is broken.
The server wraps what appears to be a single Face Terminal verification endpoint, so one tool is defensible, but the surface is thin. There are no adjacent tools such as checking API/quota status or retrieving prior verification results, which would be reasonable companion operations.
The one tool covers the full verification lifecycle in a single call: status, reasons, face match, spoof check and document check, with clear input constraints (file paths, formats, size). Minor gaps remain, such as no way to query remaining quota or fetch historical/async results.
Maintenance
Related MCP Connectors
Run AI-powered analysis on images including moderation, captioning, tagging, and more.
Hosted veraPDF: check a PDF against PDF/A or PDF/UA and get the full validation report.
Face recognition: index photos, find a person's photos from a selfie, batches, webhooks, billing.
Run multi-step AI pipelines for video, image, audio and text: upload media, run, poll results.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients to analyze images through DeepSeek's vision model using three input methods: local image files, external image URLs, and uploaded file IDs.Apache 2.0
- AlicenseNot gradedqualityNot gradedmaintenanceEnables MCP clients to perform local OCR on image files or base64-encoded images, returning recognized text with optional bounding boxes and confidence scores.1Apache 2.0
- AlicenseAqualityBmaintenancefixRAgent, by AR Logic LLC, turns one photo of a building problem into what it is, how urgent it is (EMERGENCY, TODAY, THIS WEEK or WHENEVER), which trade to call, and what to tell the resident. For property managers, landlords and companies. NARPM member. Free Test Drive for up to 10 doors; paid plans from $39/mo. fixragent.com/pricing Remote MCP server: fixragent.com/mcp3MIT
- AlicenseNot gradedqualityCmaintenanceEnables agents to run checklist-driven e-commerce image quality inspection with auditable local rules, returning pass/needs-work/fail verdicts, actionable fixes, SKU consistency checks, report files, threshold advice from reviewer overrides, and token cost estimates.MIT