Lever connector for AI agents

Tools your recruiting agent reaches for on Lever, scoped per user.

CALL ANY TOOL

77 tools for recruiting in Lever: opportunities, stages, tags, sources, notes, interview panels, feedback, offers, postings, requisitions, and resumes.

lever_applications_deleted_list

List applications deleted

List applications deleted from the Lever account within a time window of at most 30 days. Returns a page of deleted applications with id, deletedAt, opportunityId and postingId. Use this to sync application deletions. Use lever_opportunity_get with expand applications for live applications.

Parameters

Name

Type

Required

Description

deleted_at_end

integer

Required

End of the deletion window (exclusive). The window may not exceed 30 days. Unix timestamp in milliseconds. Example: 1407460069499

deleted_at_start

integer

Required

Start of the deletion window (inclusive). The window may not exceed 30 days. Unix timestamp in milliseconds. Example: 1407460069499

limit

integer

Optional

Maximum number of results to return per page, between 1 and 100. Lever defaults to its own page size when omitted. Example: 50

offset

string

Optional

Pagination cursor. Pass the next value returned by the previous page of this list to fetch the following page. Omit for the first page. Example: 0.1414895548650.a6070140-33db-407c-91f5-2760e15c8e94

lever_archive_reason_get

Get archive reason

lever_contact_update

Update contact

lever_disposition_stages_list

List disposition stages

lever_diversity_survey_get

Get diversity survey

lever_feedback_create

Create feedback

lever_feedback_delete

Delete feedback

lever_file_get

Get file

lever_files_list

List files

lever_interview_get

Get interview

lever_interview_update

Update interview

Replace an interview in an externally managed panel. Send the whole interview; fields left out are removed. Returns the updated interview. Use this to reschedule or edit an API-created interview. Interviews created in the Lever app cannot be updated. Requires a perform_as user ID from lever_users_list.

Parameters

Name

Type

Required

Description

date

integer

Required

When the interview is scheduled to start. Unix timestamp in milliseconds. Example: 1407460069499

duration

integer

Required

Interview duration in minutes, at least 1. Example: 30

interview_id

string

Required

Interview UID. Get it from lever_interviews_list. Example: 6ff55c8e-fe04-4eb4-835a-630b1c0da421

interviewers

array

Required

Interviewers, at least one. Each item needs the user id and can set a feedbackTemplate UID for that interviewer. Example: [{"id": "412f5bf5-1509-4916-ba5b-8b16a5c3ce6d", "feedbackTemplate": "7fdd449e-0bb1-4ac8-9b96-9281c1dc2099"}]

opportunity_id

string

Required

UID of the opportunity (one candidacy of a contact for a role). Get it from lever_opportunities_list (id field). Example: 250d8f03-738a-4bba-a671-8a3d73477145

panel

string

Required

UID of the interview panel the interview belongs to. The panel must be externally managed (created through the API). Get it from lever_panels_list. Example: fdb313e8-13c5-47de-9e51-6a21a4d76ff6

perform_as

string

Required

UID of the Lever user to perform this action on behalf of. Lever requires it for this call and attributes the change to that user. Get user IDs from lever_users_list. Example: 8d49b010-cc6a-4f40-ace5-e86061c677ed

conferenceData

object

Optional

Video meeting details. conferenceUrl (http or https, required in the object) is the join link; conferenceSolution names the provider, for example zoom, teams or meet. Example: {"conferenceUrl": "https://zoom.us/j/1234567890", "conferenceSolution": "zoom"}

feedbackReminder

string

Optional

How often to remind interviewers to submit feedback. Allowed values: once, daily, frequently (every 6 hours, Lever's default), none. Example: once. One of: `once`, `daily`, `frequently`, `none`.

feedbackTemplate

string

Optional

Feedback template UID for the interview. Get it from lever_feedback_templates_list. Example: 7fdd449e-0bb1-4ac8-9b96-9281c1dc2099

location

string

Optional

Interview location, such as a room name or a phone number. Example: Call - (123) 456-7891

note

string

Optional

Interview note, such as the schedule. Example: 6:00 - 6:30 pm - Rachel Green - Call

subject

string

Optional

Interview subject. Example: On-site interview - Kristoff Bjorgman - Office Manager

lever_interviews_list

List interviews

lever_note_create

Create note

lever_note_delete

Delete note

lever_opportunities_deleted_list

List opportunities deleted

lever_opportunity_archive

Archive opportunity

lever_opportunity_links_add

Add opportunity links

lever_opportunity_links_remove

Remove opportunity links

lever_opportunity_unarchive

Opportunity unarchive

lever_panel_get

Get panel

lever_panel_update

Update panel

Replace an externally managed interview panel. Send the whole panel; fields left out are removed. Returns the updated panel. Use this to reschedule a panel your integration created. Panels created in the Lever app cannot be updated. Requires a perform_as user ID from lever_users_list.

Parameters

Name

Type

Required

Description

interviews

array

Required

Interviews in the panel, at least one. Each item has interviewers (list of {id, feedbackTemplate}), date (milliseconds), duration (minutes) and optionally subject, note, location, feedbackTemplate and feedbackReminder. On update, keep the id of existing interviews and omit id for new ones. Example: [{"subject": "On-site interview", "interviewers": [{"id": "412f5bf5-1509-4916-ba5b-8b16a5c3ce6d"}], "date": 1423188000000, "duration": 30}]

opportunity_id

string

Required

UID of the opportunity (one candidacy of a contact for a role). Get it from lever_opportunities_list (id field). Example: 250d8f03-738a-4bba-a671-8a3d73477145

panel_id

string

Required

Interview panel UID. Get it from lever_panels_list. Example: fdb313e8-13c5-47de-9e51-6a21a4d76ff6

perform_as

string

Required

timezone

string

Required

IANA time zone the panel is scheduled in. Example: America/Los_Angeles

applications

array

Optional

Application UIDs the panel is for. Lever defaults to all active applications on the profile; an empty list is invalid. Example: ["7988b225-3cc1-44f3-8fcb-bae013cc490d"]

externalUrl

string

Optional

Link to the panel in an external scheduling system. Example: https://scheduler.example.com/panels/123

feedbackReminder

string

Optional

How often to remind interviewers to submit feedback. Allowed values: once, daily (Lever's default for panels), frequently (every 6 hours), none. Example: daily. One of: `once`, `daily`, `frequently`, `none`.

note

string

Optional

Panel note. Example: Panel for Rachel

lever_panels_list

List panels

lever_posting_create

Create posting

Create a job posting. API-created postings skip the approval chain and default to draft. Returns the created posting with its id and urls. Use this to open a new role. Use lever_posting_update to change an existing posting. Requires a perform_as user ID from lever_users_list.

Parameters

Name

Type

Required

Description

tags

array

Optional

Additional posting tags. Example: ["engineering", "high-priority"]

workplaceType

string

Optional

Workplace type. Allowed values: onsite, remote, hybrid. Once set it cannot go back to unspecified. Example: remote. One of: `onsite`, `remote`, `hybrid`.

lever_posting_get

Get posting

lever_postings_deleted_list

List postings deleted

lever_referrals_list

List referrals

lever_requisition_field_get

Get requisition field

lever_requisitions_list

List requisitions

lever_resume_get

Get resume

lever_stages_list

List stages

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);

// Lever tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["lever"], toolNames: [
    "lever_opportunities_list",
    "lever_feedback_list",
    "lever_opportunity_stage_update"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Move Onsite opportunities for the Account Executive posting with completed feedback to the Offer stage" }] });

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: ["lever"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Move Onsite opportunities for the Account Executive posting with completed feedback to the Offer stage" }],
  tools,
});

// Execute the tool call with the user's vaulted Lever OAuth 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: ["lever"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Move Onsite opportunities for the Account Executive posting with completed feedback to the Offer stage" }],
  tools,
});

// Tool call runs with the user's vaulted Lever OAuth 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: ["lever"] }, pageSize: 100,
});

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

await agent.run("Move Onsite opportunities for the Account Executive posting with completed feedback to the Offer stage");

Try these prompts

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

Pipeline

Copy the prompt

Copied

List opportunities tagged Senior in the Phone Screen stage.

Copy the prompt

Copied

Move Jordan Lee's opportunity to the Onsite stage.

Copy the prompt

Copied

Archive the opportunity for sam@example.com with the reason Withdrew.

Interviews and feedback

Copy the prompt

Copied

Show the interview panels scheduled for Priya Shah.

Copy the prompt

Copied

List the feedback submitted for Chen Wei's onsite.

Copy the prompt

Copied

Add a note to Maria Lopez's profile: strong system design, check references.

Postings

Copy the prompt

Copied

List published postings in the Engineering department.

Copy the prompt

Copied

Create a draft posting for a Product Marketing Manager in London.

Copy the prompt

Copied

Show open requisitions and their headcount.

SEE HOW AUTH WORKS

Each user signs in to Lever once, and Scalekit stores and refreshes their tokens. Tokens stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Lever

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

Lever

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

Lever

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

Lever

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 recruiting and HR 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 Lever token looks fine in a demo. In production every stage move and archive 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.

Lever 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 Lever as the user or through a shared service account?

As the user. Each user signs in to Lever once, and Scalekit stores and refreshes their tokens. Stage moves, notes, and feedback the agent records are attributed to that user in your audit trail, not a shared service account.

Where is the Lever OAuth token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Lever?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example the pipeline read tools and lever_note_create without lever_feedback_delete or lever_file_delete, which remove interview feedback and files from an opportunity. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Lever 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.

What does Lever mean by an opportunity?

An opportunity is one candidacy: a person moving through your pipeline. A contact can have several opportunities, and lever_contact_get returns the contact record shared across them. Most pipeline tools, such as lever_opportunity_stage_update and lever_notes_list, act on one opportunity.