Enrich for AI agents

Enrich provides email validation, contact discovery, and profile enrichment APIs to help sales teams research and reach leads without manually searching for contact details. 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.

SalesAPI keyMCP + RESTenrich.so
AUDIT LOG · ENRICHPOLICY: acme-support
09:41:07 · claude · u_8f2read
enrich.list_credit_transactions
List Credit Transactions✓ allowed · 212ms
09:41:08 · claude · u_8f2read
enrich.count_leads
Count Leads✓ allowed · 164ms
09:41:09 · claude · u_8f2write
enrich.resume_batch
Resume Existing Batch✓ approved · approved by user
EVERY ENRICH CALL, ON THE RECORD
01 · USE CASES

What agents do in Enrich.

01

Find a lead's work email

Find the work email for a named contact before adding them to an outreach sequence.

02

Search for leads by criteria

Search leads matching a target company profile to build a prospecting list.

03

Check credit balance first

Read the credit balance before running a large batch enrichment job.

02 · ACTIONS

14 Enrich actions, graded by risk.

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

read

10

Look things up. Allowed by default.

  • enrich.search_leads
    Search Leads
  • enrich.find_work_email
    Find Work Email
  • enrich.get_credit_balance
    Get Credit Balance
  • enrich.search_company_icp
    Search Company ICP
  • enrich.find_company_employees
    Find Company Employees
  • enrich.get_lead_filter_options
    Get Lead Filter Options
  • enrich.list_credit_transactions
    List Credit Transactions
  • enrich.count_leads
    Count Leads
  • enrich.validate_email
    Validate Email
  • enrich.lookup_person_by_email
    Lookup Person by Email

write

4

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

  • enrich.resume_batch
    Resume Existing Batch
  • enrich.batch_validate_emails
    Batch Validate Emails
  • enrich.batch_find_work_emails
    Batch Find Work Emails
  • enrich.batch_lookup_people_by_email
    Batch Lookup People by Email

destructive

0

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

  • No destructive actions.
03 · HOW IT WORKS

Enrich in three steps.

  1. 01Your users connect EnrichThey add their Enrich api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “resume Existing Batch” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Enrich 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('enrich', {
  read: 'allow',
  write: 'ask',        // resume_batch
  destructive: 'deny',  
})

# 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 Enrich connects.

Users add their Enrich 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 Enrich 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 Enrich from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Enrich and Arc0, answered.

Q01

Can I use Enrich with Claude, ChatGPT or Cursor?

Yes. Connect Enrich 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 Enrich actions you allow.

Q02

How do users connect Enrich?

Users add their Enrich 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 Enrich actions can my agent take?

14 in total: 10 read, 4 write and 0 destructive, such as “resume Existing Batch”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Enrich?

Yes. Allow read actions and deny writes in the Enrich policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Enrich too?

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

Get started

Plug Enrich into your agent.

Your users connect Enrich once, under your brand. Your agent gets 14 actions behind your policies, with every call on the record.

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