LeadMagic connector for AI agents

Tools your enrichment agent reaches for on LeadMagic, scoped per user.

CALL ANY TOOL

72 tools for data enrichment in LeadMagic: find and validate emails, find mobiles and profiles, research companies and competitors, search jobs and ads, and run bulk jobs.

leadmagic_add_suppression_emails

Add suppression emails

Add email addresses to an existing suppression list. Emails are stored as SHA-256 hashes. Returns a success response. Use this to grow a list. Use leadmagic_create_suppression_list to start a new one.

Parameters

Name

Type

Required

Description

emails

array

Required

Email addresses to add to the list, for example ["bounced1@example.com"].

list_id

string

Required

Identifier of the suppression list, for example bounced-2026-q3.

leadmagic_create_suppression_list

List create suppression

leadmagic_detect_job_change

Detect job change

leadmagic_find_email

Find email

leadmagic_find_lookalike_companies

Find lookalike companies

leadmagic_find_personal_email

Find personal email

leadmagic_find_role

Find role

leadmagic_get_account_summary

Get account summary

leadmagic_get_bulk_capabilities

Get bulk capabilities

leadmagic_get_bulk_job_events

Get bulk job events

leadmagic_get_campaign_metrics

Get campaign metrics

leadmagic_get_company_technographics

Get company technographics

leadmagic_get_daily_metrics

Get daily metrics

leadmagic_get_job_search_catalogs

Get job search catalogs

leadmagic_get_product_usage

Get product usage

leadmagic_get_suppression_list

List get suppression

leadmagic_list_bulk_jobs

List bulk jobs

leadmagic_list_job_countries

List job countries

leadmagic_list_job_regions

List job regions

leadmagic_lookup_job_search_companies

Lookup job search companies

leadmagic_lookup_job_search_occupations

Lookup job search occupations

leadmagic_lookup_job_search_tags

Lookup job search tags

leadmagic_preview_batch_cost

Preview batch cost

leadmagic_remove_suppression_emails

Remove suppression emails

leadmagic_review_bulk_job

Review bulk job

leadmagic_search_b2b_ads

Search b2b ads

leadmagic_search_google_ads

Search google ads

leadmagic_search_meta_ads

Search meta ads

leadmagic_set_bulk_job_priority

Set bulk job priority

leadmagic_submit_bulk_job

Submit bulk job

Submit rows for asynchronous bulk enrichment with one product. Spends credits for each processed row. Returns jobId, status, queue position and URLs for status, results and errors, plus a progress token. Use this for large lists. Track it with leadmagic_get_bulk_job_progress or leadmagic_get_bulk_job, then read rows with leadmagic_get_bulk_job_results. Use leadmagic_submit_batch to mix several products in one request.

Parameters

Name

Type

Required

Description

product

string

Required

The enrichment product to run on every row, for example email_finder, email_validation, mobile_finder, profile_search or company_search. leadmagic_get_bulk_capabilities lists every product and its input fields.

callback

object

Optional

Optional webhook notified when the job ends. Give an HTTPS url and the events to send (completed, failed, canceled or any; default completed). Example: {"url": "https://hooks.example.com/leadmagic", "events": ["completed"]}.

csv

string

Optional

The input rows as an inline CSV string with a header row, for example "first_name,last_name,domain\nJane,Doe,example.com". Provide exactly one of rows, csv or file_url.

file_name

string

Optional

Optional label for the job shown in the LeadMagic dashboard, for example q4-outbound-leads.

file_url

string

Optional

Public HTTPS URL of a CSV, JSON or JSONL file with the input rows, for example https://example.com/leads.csv. Private, internal and non-HTTPS URLs are rejected. Provide exactly one of rows, csv or file_url.

format

string

Optional

Format of the file at file_url: csv, json or jsonl. One of: `csv`, `json`, `jsonl`.

idempotency_key

string

Optional

Optional key that makes retries safe: submitting the same key again does not create a second job.

input_mapping

object

Optional

Optional mapping from your column names to the product's input fields. Each key is a product input field and each value says where it comes from, for example {"profile_url": {"source": "column", "column": "LinkedIn"}}.

metadata

object

Optional

Optional free-form metadata stored with the job, for example {"campaign": "q4-outbound"}.

priority

integer

Optional

Optional numeric processing priority from -1000 to 1000.

rows

array

Optional

The input rows as a JSON array of objects whose keys are the product's input fields. Example for email_finder: [{"profile_url": "https://www.linkedin.com/in/jane-doe", "company_name": "LeadMagic"}]. Provide exactly one of rows, csv or file_url.

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);

// LeadMagic tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["leadmagic"], toolNames: [
    "leadmagic_find_email",
    "leadmagic_validate_email",
    "leadmagic_get_company"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Find and verify the work email for Priya Shah at northwind.io" }] });

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

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Find and verify the work email for Priya Shah at northwind.io" }],
  tools,
});

// Execute the tool call with the user's vaulted LeadMagic API key
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: ["leadmagic"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Find and verify the work email for Priya Shah at northwind.io" }],
  tools,
});

// Tool call runs with the user's vaulted LeadMagic API key
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: ["leadmagic"] }, pageSize: 100,
});

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

await agent.run("Find and verify the work email for Priya Shah at northwind.io");

Try these prompts

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

People

Copy the prompt

Copied

Find the work email for Priya Shah at northwind.io.

Copy the prompt

Copied

Check whether jordan@acme.com is deliverable.

Copy the prompt

Copied

Has Sam Lee left Globex? Check for a job change.

Companies

Copy the prompt

Copied

Get the funding history for ramp.com.

Copy the prompt

Copied

Which technologies does linear.app use?

Copy the prompt

Copied

Find 10 companies similar to notion.so.

Bulk jobs and credits

Copy the prompt

Copied

How many LeadMagic credits do we have left?

Copy the prompt

Copied

Show the progress of my latest bulk enrichment job.

Copy the prompt

Copied

Estimate the credit cost of enriching these 200 emails before running it.

SEE HOW AUTH WORKS

Each user connects their own LeadMagic API key once, and Scalekit sends it with every call. Keys stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

LeadMagic

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

LeadMagic

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

LeadMagic

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

LeadMagic

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 sales and marketing data connectors.

GTM and RevOps Teams

Outbound prospecting agent

Searches Apollo for prospects matching your ICP, scores and ranks them, drafts personalized outreach in Gmail, and logs every send to Google Sheets. Mail goes out as the rep, not from a shared inbox.

GTM and RevOps Teams

CRM AI agent

Reads the Granola transcript after every call, extracts next steps and updates the HubSpot record, drafts the follow-up in Gmail, and confirms in Slack, all on the rep's own delegated OAuth.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared LeadMagic API key looks fine in a demo. In production every email lookup and bulk job 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 key
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

LeadMagic 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 LeadMagic as the user or through a shared key?

As the user. Each user connects their own LeadMagic API key once, and Scalekit sends it with every call. Audit logs attribute every lookup, bulk job, and credit spend to that user, not a shared service account.

Where is the LeadMagic API key stored?

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

Can I limit what the agent does in LeadMagic?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example the lookup and search tools without leadmagic_submit_bulk_job, which spends credits for every processed row, or leadmagic_delete_suppression_list, which cannot be undone. Scalekit also enforces scope checks before every API call.

What happens when a user revokes LeadMagic 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.

Do LeadMagic tools spend credits?

Many do. Lookups such as leadmagic_find_employees charge per result, and leadmagic_submit_batch and leadmagic_submit_bulk_job spend credits for each processed row. leadmagic_preview_batch_cost and leadmagic_validate_bulk_job check a job without spending credits, and leadmagic_get_credit_balance returns what the workspace has left.