Talenthr for AI agents
TalentHR centralizes HR records and permissions for small and mid-sized businesses running day-to-day people operations from one system. 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 Talenthr.
Assign a permission to an employee
Grant a specific HR system permission to an employee's account once the change is approved.
Require sign-off before granting access
Hold a permission assignment for a manager's approval before it is applied to an employee record.
Confirm the correct role before assigning
Check the requested permission against the employee's role before submitting the change.
1 Talenthr actions, graded by risk.
Every Talenthr action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
0Look things up. Allowed by default.
- No read actions.
write
1Create and change things. Allow, or ask the user first.
- talenthr.assign_permissionAssign Permission
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Talenthr in three steps.
- 01Your users connect TalenthrThey add their Talenthr api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “assign Permission” can wait for the user to approve.
- 03Any agent can actYour agent calls Talenthr through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('talenthr', { read: 'allow', write: 'ask', // assign_permission destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Talenthr connects.
Users add their Talenthr 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 Talenthr 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 Talenthr from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Talenthr and Arc0, answered.
Can I use Talenthr with Claude, ChatGPT or Cursor?
Yes. Connect Talenthr 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 Talenthr actions you allow.
How do users connect Talenthr?
Users add their Talenthr 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 Talenthr actions can my agent take?
1 in total: 0 read, 1 write and 0 destructive, such as “assign Permission”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Talenthr?
Yes. Allow read actions and deny writes in the Talenthr policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Talenthr too?
Yes. The same Talenthr connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Talenthr into your agent.
Your users connect Talenthr once, under your brand. Your agent gets 1 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan