People Data Labs for AI agents
People Data Labs provides B2B data enrichment and identity resolution for building accurate profiles of people and companies. Sales, recruiting, and data teams use it to fill gaps in their records. 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 People Data Labs.
Enrich a person's profile
Fill in missing job title and company details for a contact using their available identifiers.
Search companies by criteria
Run a company search to find firms matching size, industry, or location criteria.
Check enrichment schema read-only
Look up the data schema before mapping enrichment fields into an internal record.
27 People Data Labs actions, graded by risk.
Every People Data Labs action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
11Look things up. Allowed by default.
- people_data_labs.get_schemaGet schema
- people_data_labs.get_column_detailsGet column details
- people_data_labs.search_company_postSearch Company Records (POST)
- people_data_labs.search_job_postingsSearch job postings
- people_data_labs.get_subject_requestsGet subject requests
- people_data_labs.query_person_changelogQuery person changelog
- people_data_labs.search_company_elasticCompany Search with Elasticsearch
- people_data_labs.get_autocomplete_suggestionsAutocomplete field suggestions
- people_data_labs.get_autocomplete_suggestions_postGet autocomplete suggestions (POST)
- people_data_labs.retrieve_personRetrieve person
- people_data_labs.identify_person_dataIdentify person data
write
16Create and change things. Allow, or ask the user first.
- people_data_labs.enrich_ip_dataEnrich IP Data
- people_data_labs.clean_school_dataClean school data
- people_data_labs.enrich_skill_dataEnrich skill data
- people_data_labs.clean_company_dataClean company data
- people_data_labs.clean_company_postClean company data (POST)
- people_data_labs.enrich_person_dataEnrich person data
- people_data_labs.clean_location_dataClean location data
- people_data_labs.clean_location_postClean location data (POST)
- people_data_labs.enrich_company_dataEnrich Company Data
- people_data_labs.bulk_retrieve_personsBulk Retrieve Persons
- people_data_labs.enrich_job_title_dataEnrich job title data
- people_data_labs.generate_search_queryGenerate Search Query
- people_data_labs.people_search_elasticPeople Search with Elasticsearch
- people_data_labs.clean_school_data_postClean school data (POST)
- people_data_labs.enrich_bulk_person_dataEnrich bulk person data
- people_data_labs.enrich_bulk_company_dataEnrich Bulk Company Data
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
People Data Labs in three steps.
- 01Your users connect People Data LabsThey add their People Data Labs api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “enrich IP Data” can wait for the user to approve.
- 03Any agent can actYour agent calls People Data Labs through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('people_data_labs', { read: 'allow', write: 'ask', // enrich_ip_data destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How People Data Labs connects.
Users add their People Data Labs 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 People Data Labs 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 People Data Labs from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
People Data Labs and Arc0, answered.
Can I use People Data Labs with Claude, ChatGPT or Cursor?
Yes. Connect People Data Labs 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 People Data Labs actions you allow.
How do users connect People Data Labs?
Users add their People Data Labs 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 People Data Labs actions can my agent take?
27 in total: 11 read, 16 write and 0 destructive, such as “enrich IP Data”. Your policies decide which of them each agent may call.
Can I make my agent read-only in People Data Labs?
Yes. Allow read actions and deny writes in the People Data Labs policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call People Data Labs too?
Yes. The same People Data Labs connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug People Data Labs into your agent.
Your users connect People Data Labs once, under your brand. Your agent gets 27 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan