Enrich Layer for AI agents
Enrich Layer provides person, company, and professional network data enrichment, used to fill in and verify contact profiles for sales, recruiting, and marketing teams. 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.
What agents do in Enrich Layer.
Enrich a contact's profile
Enrich a person record with company and role details before it is added to a CRM.
Find a person by email
Find a person's professional profile using their email address for a lead handoff.
Check credit balance before a batch
Read the credit balance as a check before running enrichment across a large contact list.
9 Enrich Layer actions, graded by risk.
Every Enrich Layer action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
7Look things up. Allowed by default.
- enrich_layer.get_credit_balanceGet Credit Balance
- enrich_layer.find_person_by_roleFind Person By Role
- enrich_layer.find_person_by_emailFind Person By Email
- enrich_layer.find_social_profiles_by_phoneFind Social Profiles By Phone
- enrich_layer.resolve_personResolve Person
- enrich_layer.resolve_companyResolve Company
- enrich_layer.check_email_typeCheck Email Type
write
2Create and change things. Allow, or ask the user first.
- enrich_layer.enrich_personEnrich Person
- enrich_layer.enrich_companyEnrich Company
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Enrich Layer in three steps.
- 01Your users connect Enrich LayerThey add their Enrich Layer api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “enrich Person” can wait for the user to approve.
- 03Any agent can actYour agent calls Enrich Layer through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('enrich_layer', { read: 'allow', write: 'ask', // enrich_person destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Enrich Layer connects.
Users add their Enrich Layer 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 Layer 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
Use Enrich Layer from any agent.
Enrich Layer and Arc0, answered.
Can I use Enrich Layer with Claude, ChatGPT or Cursor?
Yes. Connect Enrich Layer 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 Layer actions you allow.
How do users connect Enrich Layer?
Users add their Enrich Layer 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.
Which Enrich Layer actions can my agent take?
9 in total: 7 read, 2 write and 0 destructive, such as “enrich Person”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Enrich Layer?
Yes. Allow read actions and deny writes in the Enrich Layer policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Enrich Layer too?
Yes. The same Enrich Layer connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Enrich Layer into your agent.
Your users connect Enrich Layer once, under your brand. Your agent gets 9 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan