Dice for AI agents
Dice is a job search engine focused on technology roles, letting recruiters and candidates search listings by title, company, and location. 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 Dice.
Search open roles by criteria
Search jobs by title, location, and employment type to build a shortlist for a hiring manager.
Pull details on one listing
Get the full job details for a posting an agent is comparing against a candidate's resume.
Look up a hiring company
Get a company profile to check who else is hiring before drafting outreach.
3 Dice actions, graded by risk.
Every Dice action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
3Look things up. Allowed by default.
- dice.get_companyGet company
- dice.search_jobsSearch jobs
- dice.get_job_detailsGet job details
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Dice in three steps.
- 01Your users connect DiceThey add their Dice no auth on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls Dice through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('dice', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Dice connects.
Dice needs no credentials. Arc0 still applies your policies and records every call, so public tools get the same controls as private ones.
The same Dice 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
- No auth
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Dice from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Dice and Arc0, answered.
Can I use Dice with Claude, ChatGPT or Cursor?
Yes. Connect Dice 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 Dice actions you allow.
How do users connect Dice?
Dice needs no credentials. Arc0 still applies your policies and records every call, so public tools get the same controls as private ones.
Which Dice actions can my agent take?
3 in total: 3 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Dice?
Yes. Allow read actions and deny writes in the Dice policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Dice too?
Yes. The same Dice connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Dice into your agent.
Your users connect Dice once, under your brand. Your agent gets 3 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan