MCP.Market

Onfido MCP server

by codespar·io.github.codespar/mcp-onfido·v0.2.2·271 stars
No reviews yet

MCP server for Onfido — global identity verification + KYC: applicants, documents, checks, workflows

B82/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B82/100

full report

Adoption
Growing

271 stars

Reviews

Write one

Nobody has reviewed Onfido yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Onfido tools (20, 8 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • create_applicantwrite action

    Create an Onfido applicant — the person record that documents, live photos, and checks attach to. Required before any verification.

  • create_checkwrite action

    Run a verification check on an applicant. A check is a bundle of one or more reports (document, facial_similarity_photo, watchlist, etc). This is the step that actually triggers the verification.

  • create_workflow_runwrite action

    Start an Onfido Studio workflow run. Studio is Onfido's newer product: instead of manually orchestrating checks/reports, you configure a workflow in the dashboard and trigger it here. The run drives the applicant through document capture, facial similarity, watchlist, etc automatically.

  • delete_applicantwrite action

    Soft-delete an applicant. Onfido retains the record for 30 days before permanent deletion; during that window it can be restored via the dashboard.

  • download_document

    Download the raw binary of an uploaded document. Returns the bytes as base64 plus content_type. Useful for re-viewing or re-processing after upload.

  • generate_sdk_token

    Mint a short-lived SDK token for embedding the Onfido Web / iOS / Android SDKs in your frontend. The token is scoped to a single applicant and is how capture flows (document photo, selfie, video) run in-browser/in-app without exposing your API token.

  • list_checks

    List all checks for a given applicant.

  • list_documents

    List all documents uploaded for a given applicant.

  • list_live_photos

    List all live photos (selfies) uploaded for a given applicant.

  • list_reports

    List the reports contained within a given check.

  • resume_check

    Resume a check that was paused (typically awaiting_applicant or paused states). No-op on checks that are already running / complete.

  • retrieve_applicant

    Retrieve an applicant by id.

  • retrieve_check

    Retrieve a check by id. Returns the overall status ('in_progress' | 'awaiting_applicant' | 'complete' | 'withdrawn' | 'paused' | 'reopened'), result ('clear' | 'consider'), and ids of contained reports — poll this to track progress.

  • retrieve_document

    Retrieve document metadata by id.

  • retrieve_live_photo

    Retrieve a live photo record by id.

  • retrieve_report

    Retrieve an individual report by id. A report is one verification component of a check (e.g. the document report, the facial_similarity report). Contains the detailed breakdown of sub-checks.

  • retrieve_workflow_runwrite action

    Retrieve a workflow run by id. Returns status ('awaiting_input' | 'processing' | 'approved' | 'declined' | 'review' | 'abandoned' | 'error'), output data, link and sdk_token (if applicable).

  • update_applicantwrite action

    Update fields on an existing applicant. Send only the fields you want to change.

  • upload_documentwrite action

    Upload an identity document image for an applicant. Sent as multipart/form-data. Pass file as base64-encoded bytes plus file_name and content_type (image/jpeg, image/png, application/pdf).

  • upload_live_photowrite action

    Upload a live photo (selfie) for an applicant, used by facial_similarity_photo reports. Sent as multipart/form-data. NOTE: Onfido recommends capturing live photos via their SDK; direct API upload may be restricted on some accounts.

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan5 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 29 days ago15/15
  • Maintainer identityregistry namespace matches repository owner7/10
Overall 82/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Onfido compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
82/100
higher than 63% of 48,255 servers
Tools
20
the typical server has 7
Tools that change things
40%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
271
more than 95% of 28,688 servers

What its tools let an agent do: 11 read · 6 create · 2 change · 1 delete

Install Onfido in Claude Code, Cursor or VS Code

Runs npx -y @codespar/mcp-onfido on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add mcp-onfido -- npx -y @codespar/mcp-onfido
Add to Cursor

What the publisher says

From the Onfido repository's README, as published. We do not edit it. Read it on GitHub

MCP Dev LATAM 🌎 Every commerce API your AI agent needs to run a business in Latin America. Brazil 🇧🇷 · Mexico 🇲🇽 · Argentina 🇦🇷 · Colombia 🇨🇴 · Chile 🇨🇱 · Peru 🇵🇪 · plus 4 agentic payment protocols. MCP servers for LATAM commerce · live in the official MCP Registry · MIT License Machine-readable catalog: codespar.dev/api/servers Catalog · Quick Start · Agentic Protocols · All Servers · Contribute

The Problem

AI agents can write code, analyze data, and chat. But they can't operate a business — collect payments, issue invoices, ship products, or notify customers. Especially not in Latin America, where every service has its own API, auth pattern, and quirks (mTLS for BACEN Pix v2, JWT-RSA for STP-SPEI, AFIP web services, contract-gated developer portals, and on).

Meanwhile, four agentic payment protocols are shipping in parallel — checkout protocols (Stripe ACP, Google UCP), authorization layers (AP2), and micropayment rails (x402) — and none of them compose cleanly with each other or with the regional rails businesses actually run on.

MCP Dev LATAM bridges both gaps. Traditional LATAM services + the new agentic payment protocols, all accessible through a single MCP interface.

The Solution

Each MCP server in this repo wraps a real provider — payments, fiscal, logistics, messaging, banking, ERP, identity, fraud, crypto, and the agentic protocols — so your agent can operate a complete business workflow.

🛒 Customer places order
  → 💳 Agent charges via Pix (Asaas / Mercado Pago / Zoop)
  → 📄 Agent issues NFe (Nuvem Fiscal / Focus NFe / NFe.io)
  → 📦 Agent generates shipping label (Melhor Envio / Skydropx)
  → 📱 Agent sends tracking via WhatsApp (Z-API / WhatsApp Cloud)
  → 📊 Agent records in ERP (Omie / Bling / Tiny)
  → 🏦 Agent reconciles balance (Stark Bank / Itaú / BTG)

Six systems. Zero human intervention. One agent.

Agentic Payment Protocols

Four servers for the emerging agentic payment stack:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Onfido: common questions

Is Onfido MCP server safe?
Mostly: it is graded B (82/100). Read the Onfido safety report
How do I install Onfido?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Onfido need an API key?
Yes. The registry entry asks for ONFIDO_API_TOKEN.
Is Onfido maintained?
The last commit was 67 days ago (2026-08-29). The latest release is v0.2.2.
How does Onfido compare with other MCP servers?
safety score 82/100 (higher than 63% of 48,255 servers); tools 20 (the typical server has 7); tools that change things 40% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

More from codespar →