HackerRank Work for AI agents
HackerRank Work provides coding interviews and technical assessments, helping hiring teams evaluate engineering candidates through real-time collaboration and data-driven scoring during the recruiting process. 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 HackerRank Work.
List companies on the account
List the companies configured on the account before setting up a new assessment.
Generate a single sign-on link
Generate an SSO sign-on URL so a hiring manager can access the assessment dashboard.
Confirm access before changes
Look up SSO configuration read-only before recommending a change to login settings.
3 HackerRank Work actions, graded by risk.
Every HackerRank Work 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
3Create and change things. Allow, or ask the user first.
- hackerrank_work.companies_listList Companies
- hackerrank_work.sso_sign_on_urlGet SSO Sign-On URL
- hackerrank_work.sso_assertion_consumer_serviceConsume SAML Assertion
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
HackerRank Work in three steps.
- 01Your users connect HackerRank WorkThey add their HackerRank Work api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “list Companies” can wait for the user to approve.
- 03Any agent can actYour agent calls HackerRank Work through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('hackerrank_work', { read: 'allow', write: 'ask', // companies_list destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How HackerRank Work connects.
Users add their HackerRank Work 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 HackerRank Work 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 HackerRank Work from any agent.
HackerRank Work and Arc0, answered.
Can I use HackerRank Work with Claude, ChatGPT or Cursor?
Yes. Connect HackerRank Work 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 HackerRank Work actions you allow.
How do users connect HackerRank Work?
Users add their HackerRank Work 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 HackerRank Work actions can my agent take?
3 in total: 0 read, 3 write and 0 destructive, such as “list Companies”. Your policies decide which of them each agent may call.
Can I make my agent read-only in HackerRank Work?
Yes. Allow read actions and deny writes in the HackerRank Work policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call HackerRank Work too?
Yes. The same HackerRank Work connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug HackerRank Work into your agent.
Your users connect HackerRank Work 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