Get started

Enigma for AI agents

Enigma provides identity and financial data on U.S. businesses, used for sales research, risk assessment, and compliance screening by teams onboarding new business customers or vendors. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect EnigmaSee the 19 actions ↓
AnalyticsAPI keyMCP + RESTenigma.com
AUDIT LOG · ENIGMAPOLICY: acme-support
09:41:07 · claude · u_8f2read
enigma.list_decisions
List Screening Decisions✓ allowed · 212ms
09:41:08 · claude · u_8f2read
enigma.get_account
Get Account Information✓ allowed · 164ms
09:41:09 · claude · u_8f2write
enigma.create_list
Create List✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
enigma.delete_list
Delete List✕ blocked · policy: deny
EVERY ENIGMA CALL, ON THE RECORD
01 · USE CASES

What agents do in Enigma.

01

Look up a business profile

Get a business by its Enigma ID to check its identity and financial health before a sales call.

02

Screen against sanctions lists

Screen a business against sanctions and watchlists as part of an onboarding compliance check.

03

Read-only KYB verification

Run a KYB business verification as a read-only check before approving a new vendor.

02 · ACTIONS

19 Enigma actions, graded by risk.

Every Enigma action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

13

Look things up. Allowed by default.

  • enigma.get_account
    Get Account Information
  • enigma.get_business
    Get Business by Enigma ID
  • enigma.get_decision
    Get Screening Decision
  • enigma.search_lists
    Search User-Created Lists
  • enigma.list_decisions
    List Screening Decisions
  • enigma.search_graph_ql
    Search Enigma Entities via GraphQL
  • enigma.get_background_task
    Get Background Task Status
  • enigma.get_aggregate_counts
    Get Aggregate Counts
  • enigma.get_attribute_groups
    Get Attribute Groups
  • enigma.get_sanctioned_entity
    Get Sanctioned Entity Details
  • enigma.get_list_materialization
    Get List Materialization
  • enigma.get_graph_ql_schema_extended
    Get Extended GraphQL Schema
  • enigma.verify_business_v2
    Verify Business Identity (KYB v2)

write

5

Create and change things. Allow, or ask the user first.

  • enigma.create_list
    Create List
  • enigma.create_suggestion
    Create Suggestion
  • enigma.match_business
    Match Business Profile
  • enigma.kyb_verification
    KYB Business Verification
  • enigma.screening_verification
    Screen Against Sanctions and Watchlists

destructive

1

Delete, cancel or archive. Ask first, or deny outright.

  • enigma.delete_list
    Delete List
03 · HOW IT WORKS

Enigma in three steps.

  1. 01Your users connect EnigmaThey add their Enigma api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create List” can wait for the user, and “delete List” can be denied outright.
  3. 03Any agent can actYour agent calls Enigma through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('enigma', {
  read: 'allow',
  write: 'ask',        // create_list
  destructive: 'deny',  // delete_list
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Enigma connects.

Users add their Enigma api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Enigma connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Enigma from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More analytics apps.

Gong58 actionsSerpApi59 actionsPeople Data Labs27 actionsPostHog507 actions21risk8 actionsAkta19 actionsAlpha Vantage56 actionsAmplitude54 actions
ALL ANALYTICS APPS →
07 · FAQ

Enigma and Arc0, answered.

Q01

Can I use Enigma with Claude, ChatGPT or Cursor?

Yes. Connect Enigma to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Enigma actions you allow.

Q02

How do users connect Enigma?

Users add their Enigma api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Enigma actions can my agent take?

19 in total: 13 read, 5 write and 1 destructive, such as “create List”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Enigma?

Yes. Actions like “delete List” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Enigma too?

Yes. The same Enigma connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Enigma into your agent.

Your users connect Enigma once, under your brand. Your agent gets 19 actions behind your policies, with every call on the record.

Connect EnigmaBrowse all apps →

Free to build · MCP + REST · Audit log on every plan