Category · Domain data
Identity and business verification APIs for AI agents
Services that verify a person from an identity document and a selfie, or a business from registry records, and screen both against sanctions and watchlists. Compared on the checks covered, how a verification is started and read, webhooks and data retention.
Capability keys kyc.identity · kyc.business · kyc.documents · kyc.screening · kyc.cases · All tools
letme.dev/kyc.identity picks the top-graded tool in this list and says how to call it direct; calling through letme comes later.
The same listing from the live API. Graded results come first, then the official MCP registry when no graded-only filter is set.
https://www.anchorterminal.com/api/v1/searchFilters
| Compare | # | Tool | Category | Grade | Score | Agent rating | p95 | Context | Price / x402 | Auth | Where | Details |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 131 | PersonaPersona Identities, Inc. · HTTP API | Verification | B | 69.5 | none | n/a | n/a | $250 / mo | API key | Hosted | ||
|
Persona is an identity verification platform from Persona Identities, Inc. Its REST API and hosted MCP server create inquiries, run government ID, selfie, document and database verifications, screen people and businesses against watchlists, and manage review cases. Top strength Public OpenAPI 3.1 file with 231 operations and 141 webhook definitions, plus llms.txt and a Markdown copy of every docs page Top weakness Production access needs Persona's approval and a 12-month plan from $250 a month, and API-only integration is limited to Enterprise plans |
||||||||||||
| 147 | SumsubSum and Substance Ltd · HTTP API | Verification | B | 68.5 | none | n/a | n/a | $1.35 / tx | OAuth or key | Hosted | ||
|
Sumsub verifies people from identity documents and a liveness check, verifies businesses against registries, and screens both against sanctions and watchlists. Agents reach it through a signed REST API and a hosted MCP server. Top strength App tokens carry per-token permissions, an optional IP allowlist and expiry date, and can be disabled with a recorded reason Top weakness No idempotency keys and no Retry-After or backoff guidance found in the reviewed documentation |
||||||||||||
| 299 | VeriffVeriff OÜ · HTTP API | Verification | C | 61.1 | none | n/a | n/a | $0.80 / tx | API key | Local | ||
|
Identity verification service from Veriff in Tallinn. It checks an identity document and a selfie, with liveness, database checks and PEP and sanctions screening. Sessions are created and read through the Public API v1, with results sent by webhook. Top strength Public prices of $0.80, $1.39 and $1.89 a verification, with a 15-day trial of up to 50 sessions and no card Top weakness No server-side SDK and no MCP server. Official packages cover only browser and mobile capture |
||||||||||||
| 353 | MiddeskMiddesk, Inc. · HTTP API | Verification | C | 59 | none | n/a | n/a | Paid | OAuth or key | Hosted | ||
|
Business verification API from Middesk in San Francisco. It checks US and international businesses against registry, tax ID, sanctions and watchlist records, monitors them for changes, and files liens and state tax registrations, over REST and a hosted MCP server. Top strength Public OpenAPI 3.1 spec with 87 operations and 373 schemas, plus llms.txt and a Markdown copy of every docs page Top weakness No public price. Fees are set in an order form, and every docs page ends with a prompt to contact sales |
||||||||||||
| 369 | TruliooTrulioo Information Services Inc. · HTTP API | Verification | C | 58.2 | none | n/a | n/a | Paid | OAuth | Hosted | ||
|
Trulioo verifies people and businesses against registry and bureau data, checks identity documents and screens watchlists. Agents reach it through REST APIs with OAuth client credentials or a hosted MCP server, which is in early access. Top strength Hosted MCP server at mcp.trulioo.com/mcp with OAuth 2.1, PKCE and dynamic client registration, so no key is copied into the client Top weakness No public prices, terms of service or SLA. Live credentials come from Trulioo's sales and support teams |
||||||||||||
Nothing matches these filters. .
p95 latency and context cost come from our probes, which haven't run yet, so those columns start hidden. Grades run from AA to F, and agent-ready means BB or better. Filters, sorting and export run in your browser; the table is complete without JavaScript.
How we test this category
One test person and one test business run through each listing's sandbox. A verification is started, completed with the vendor's test documents and read back, with a watchlist screen. We check the result fields, status events, retention controls and redaction. In this run listings are graded from public evidence against the published checklist. This test hasn't run yet, so Task success is pending and the grades here come from the categories assessed from public evidence.
How the ranking works
Every listing is scored 0 to 100 and given a grade from AA to F. In the October 2026 research run, 7 of the 9 weighted categories are scored from public evidence (status history, docs, pricing, terms, source and security pages) against a published checklist, with the reason and sources for every score on the listing. Performance and Task success wait for our probes and task suites, so their weight is shared across the rest until they run. Negative events deduct up to 15 points. Read the methodology.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.