HackerRank Work connector for AI agents

Tools your technical hiring agent reaches for on HackerRank Work, scoped per user.

CALL ANY TOOL

36 tools for technical hiring in HackerRank Work: create tests and invite candidates, read scores and PDF reports, schedule live coding interviews, read transcripts, and browse the question bank.

hackerrankwork_archive_test

Archive test

Archive an assessment test so it no longer appears among active tests. Returns an empty success response (HTTP 204) when the test is archived. Use hackerrankwork_archive_test to retire a test without deleting its data.

Parameters

Name

Type

Required

Description

test_id

string

Required

ID of the test to archive.

hackerrankwork_cancel_candidate_invite

Invite cancel candidate

hackerrankwork_create_interview

Create interview

hackerrankwork_create_interview_template

Create interview template

hackerrankwork_delete_interview

Delete interview

hackerrankwork_get_candidate_report_pdf

Get candidate report pdf

hackerrankwork_get_interview

Get interview

hackerrankwork_get_interview_template

Get interview template

hackerrankwork_get_interview_transcript

Get interview transcript

hackerrankwork_get_invite_template

Get invite template

hackerrankwork_get_team

Get team

hackerrankwork_get_team_membership

Get team membership

hackerrankwork_get_test

Get test

hackerrankwork_get_test_candidate

Get test candidate

hackerrankwork_invite_candidate

Invite candidate

Invite a single candidate to a published test, optionally sending the invitation email. Returns the candidate's id, email and the test_link they use to take the test. Use hackerrankwork_invite_candidate to invite one person per call. No email is sent unless send_email is true. The test must be published (not draft).

Parameters

Name

Type

Required

Description

string

Required

Email address of the candidate.

test_id

string

Required

ID of the published test to invite the candidate to.

accept_result_updates

boolean

Optional

Set true to also send score and status updates to test_result_url. API default is false.

accommodations

object

Optional

Accommodations object, for example {"additional_time_percent": 25} to add 25 percent extra time.

ats_state

integer

Optional

Current state of the candidate application, an integer from 0 to 22.

evaluator_email

string

Optional

Email of the evaluator, if different from the test admins and owner.

force

boolean

Optional

Set true to send the email even if the candidate was already invited.

force_reattempt

boolean

Optional

Set true to re-invite even if the candidate already attempted the test.

full_name

string

Optional

Full name of the candidate.

invite_metadata

object

Optional

Custom metadata object stored with the candidate, for example {"ats_candidate_id": 1}.

invite_valid_from

string

Optional

ISO 8601 time from which the invite is valid. Omit for no start restriction.

invite_valid_to

string

Optional

ISO 8601 time until which the invite is valid. Omit for a permanently valid invite.

message

string

Optional

Custom message prepended to the invite email body.

send_email

boolean

Optional

Set true to send the invitation email. When false or omitted the invite is recorded but no email is sent.

subject

string

Optional

Subject of the invite email.

tags

array

Optional

Tags to associate with the test, for example ["Java","Senior"].

test_admins

array

Optional

Email addresses of test admins, who also receive summary mails when a candidate completes the test.

For more tools, view docs.

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// HackerRank Work tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["hackerrankwork"], toolNames: [
    "hackerrankwork_list_tests",
    "hackerrankwork_list_test_candidates",
    "hackerrankwork_invite_candidate"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Invite alex@example.com to the Frontend Engineer test" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["hackerrankwork"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Invite alex@example.com to the Frontend Engineer test" }],
  tools,
});

// Execute the tool call with the user's vaulted HackerRank Work access token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["hackerrankwork"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Invite alex@example.com to the Frontend Engineer test" }],
  tools,
});

// Tool call runs with the user's vaulted HackerRank Work access token
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["hackerrankwork"] }, pageSize: 100,
});

const agent = new Agent({
  name: "hiring_agent",
  model: "gemini-2.5-pro",
  instruction: "HackerRank Work tools scoped to this user",
  tools,
});

await agent.run("Invite alex@example.com to the Frontend Engineer test");

Try these prompts

Copy any prompt into your agent. Each maps directly to a HackerRank Work tool. Click to copy, paste into your agent, done.

Tests

Copy the prompt

Copied

List our active assessment tests and their durations.

Copy the prompt

Copied

Invite alex@example.com to the Frontend Engineer test and send the email.

Copy the prompt

Copied

Cancel the test invite for sam@example.com on the Data Engineer test.

Candidates

Copy the prompt

Copied

Show candidates on the Backend Engineer test who scored above 80%.

Copy the prompt

Copied

Get the PDF report for Jordan Lee's Frontend Engineer test.

Copy the prompt

Copied

Search all tests for the candidate maya@example.com.

Interviews

Copy the prompt

Copied

Schedule a live coding interview with Priya tomorrow at 3pm with Sam as interviewer.

Copy the prompt

Copied

Get the transcript from yesterday's interview with Chen Wei.

Copy the prompt

Copied

List medium-difficulty Python questions in our question bank.

SEE HOW AUTH WORKS

Each user connects their own HackerRank Work access token once, and Scalekit sends it with every call. Access tokens stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

HackerRank Work

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

HackerRank Work

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

HackerRank Work

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

HackerRank Work

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other developer and productivity connectors.

People Ops and HR teams

Offer letter routing agent

Drafts the offer in PandaDoc, blocks on the hiring manager's approval in Slack, then emails the candidate their e-signature link. Every call runs as the recruiter who triggered it, never a shared HR bot.

Support and Ops Teams

Meeting prep

Pulls agenda, participant context, and open action items before every meeting.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared HackerRank Work access token looks fine in a demo. In production every test invite and interview looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

HackerRank Work today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access HackerRank Work as the user or through a shared token?

As the user. Each user connects their own HackerRank Work access token once, and Scalekit sends it with every call. Test invites and interviews the agent creates are attributed to that user in your audit trail, not a shared service account.

Where is the HackerRank Work access token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new access token. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in HackerRank Work?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example the test and candidate read tools without hackerrankwork_delete_interview, which removes an interview permanently, or hackerrankwork_cancel_candidate_invite. Scalekit also enforces scope checks before every API call.

What happens when a user revokes HackerRank Work access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Can the agent review a live interview after it ends?

Yes. hackerrankwork_get_interview returns the interview's status, interviewers, candidate, notes, feedback, and report URL, and hackerrankwork_get_interview_transcript returns the recorded conversation as a list of messages.