Datagma for AI agents
Datagma provides data intelligence for go-to-market teams, enriching people and companies and tracking signals like job changes for sales timing. 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 Datagma.
Enrich a person or company record
Enrich a contact record with company and title details before an outreach campaign.
Detect a recent job change
Check whether a contact has recently changed jobs before a rep reaches out.
Find a work email address
Find a person's work email address before adding them to an outreach sequence.
8 Datagma actions, graded by risk.
Every Datagma action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
6Look things up. Allowed by default.
- datagma.get_creditsGet Credits
- datagma.find_work_emailFind Work Email
- datagma.get_twitter_by_emailGet Twitter Profile By Email
- datagma.search_phone_numbersSearch Phone Numbers
- datagma.get_twitter_by_usernameGet Twitter Profile by Username
- datagma.detect_job_changeDetect Job Change
write
2Create and change things. Allow, or ask the user first.
- datagma.reverse_phone_lookupReverse Phone Lookup
- datagma.enrich_person_or_companyEnrich Person or Company
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Datagma in three steps.
- 01Your users connect DatagmaThey add their Datagma api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “reverse Phone Lookup” can wait for the user to approve.
- 03Any agent can actYour agent calls Datagma through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('datagma', { read: 'allow', write: 'ask', // reverse_phone_lookup destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Datagma connects.
Users add their Datagma 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 Datagma 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 Datagma from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Datagma and Arc0, answered.
Can I use Datagma with Claude, ChatGPT or Cursor?
Yes. Connect Datagma 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 Datagma actions you allow.
How do users connect Datagma?
Users add their Datagma 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 Datagma actions can my agent take?
8 in total: 6 read, 2 write and 0 destructive, such as “reverse Phone Lookup”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Datagma?
Yes. Allow read actions and deny writes in the Datagma policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Datagma too?
Yes. The same Datagma connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Datagma into your agent.
Your users connect Datagma once, under your brand. Your agent gets 8 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan