BetterContact connector for AI agents

CALL ANY TOOL

9 tools for contact enrichment in BetterContact: submit leads for waterfall email and phone enrichment, enrich person and company profiles, and run Lead Finder and Company Finder searches.

bettercontact_create_company_finder_search

Search create company finder

Start an asynchronous search for companies by firmographic, funding, and hiring criteria. Returns a request_id. The companies are not in this response. Use get_company_finder_results with the request_id to fetch companies. Use create_lead_finder_search to find people. Use enrich_company_profile for a single known company.

Parameters

Name

Type

Required

Description

filters

object

Required

Search criteria as an object. At least one filter must hold a value. List filters take only an include list: company (lowercase domains without a path), company_linkedin_url, company_industry, company_hq_location, company_technologies, company_keywords, company_description, revenue_ranges, last_funding_round_names, job_post_titles, job_posting_countries, job_posting_locations. Number filters are company_headcount_min and company_headcount_max. Boolean filters are is_b2b, is_b2c, and is_public. Range filters use gte and lte: last_funding_date_range (YYYY-MM-DD), last_amount_raised_usd, total_amount_raised_usd. Industry, technology, revenue range, and funding round values must match the vendor's fixed lists exactly. Example: {"company_industry": {"include": ["Software Development"]}, "company_hq_location": {"include": ["United States"]}, "company_headcount_min": 51, "company_headcount_max": 500, "is_b2b": true}.

limit

integer

Optional

Number of companies to return for this page, between 1 and 200. Defaults to 100 when omitted; a value above 200 is refused. Example: 25.

offset

integer

Optional

Number of matches to skip. To page, keep limit constant and increase offset by limit each call; the total match count is in the results summary. Example: 25.

bettercontact_create_lead_finder_search

Search create lead finder

Start an asynchronous search for new leads by company and person criteria. Returns a request_id. The leads are not in this response. Use get_lead_finder_results with the request_id to fetch leads. Use create_company_finder_search to find companies instead of people. Optionally enriches emails or phones for each lead found, which consumes extra credits.

Parameters

Name

Type

Required

Description

filters

object

Required

Search criteria as an object. At least one filter must hold a value. Company filters take an include list: company (domains), company_linkedin_url, company_industry, company_hq_location, company_technologies, company_keywords, company_description, revenue_ranges, last_funding_round_names, job_post_titles, job_posting_countries, job_posting_locations. Lead filters take include and optional exclude lists: lead_fullname, lead_linkedin_url, lead_job_title (also accepts exact_match true or false), lead_seniority, lead_department, lead_function, lead_skills, lead_location. An exclude list needs at least one include alongside it. Number filters are company_headcount_min, company_headcount_max, and limit_per_company (1 to 100). Range filters use gte and lte: last_funding_date_range (YYYY-MM-DD), last_amount_raised_usd, total_amount_raised_usd. Boolean filters are is_b2b, is_b2c, and is_public. Industry, technology, seniority, department, revenue range, and funding round values must match the vendor's fixed lists exactly. Example: {"company_industry": {"include": ["Computer Software"]}, "lead_seniority": {"include": ["cxo", "vp"]}, "company_hq_location": {"include": ["United States"]}}.

enrich_email_address

boolean

Optional

Whether to also run waterfall email enrichment on every lead found. Consumes enrichment credits on top of the search, and results stay in processing until enrichment is done. Example: false.

enrich_phone_number

boolean

Optional

Whether to also run waterfall mobile phone enrichment on every lead found. Consumes enrichment credits and requires the phone add-on on your plan. Example: false.

limit

integer

Optional

Number of leads to return for this request, between 1 and 200. Use with offset to paginate. When omitted, up to 100 leads are returned. Example: 100.

offset

integer

Optional

Number of leads to skip before returning matches. Only used when limit is set. To page, keep limit constant and increase offset by limit each call. Example: 100.

bettercontact_enrich_company_profile

Enrich company profile

bettercontact_enrich_lead_profile

Enrich lead profile

bettercontact_enrich_leads

Enrich leads

Submit 1 to 100 leads for waterfall enrichment of work email, mobile phone, and LinkedIn profile. Returns a request id with status Processing. The enriched data is not in this response. Use get_enrichment_results with that id to fetch the data. Use enrich_lead_profile for a single synchronous profile lookup without email or phone. Consumes credits per enriched lead. Phone and catch-all verification need the matching plan add-ons.

Parameters

Name

Type

Required

Description

leads

array

Required

The leads to enrich, between 1 and 100. Each lead needs first_name and last_name, plus either company_domain or company (company_domain gives better results). Add linkedin_url for better phone results; it is required when enrich_profile is true. Add custom_fields, a free-form object, to have your own data such as a CRM record id echoed back with the result. Example: [{"first_name": "Elon", "last_name": "Musk", "company_domain": "tesla.com", "linkedin_url": "https://www.linkedin.com/in/elonmusk", "custom_fields": {"crm_id": "8821"}}].

enrich_email_address

boolean

Optional

Whether to find the work email address. Email enrichment is applied by default when no enrich flag is set. Example: true.

enrich_phone_number

boolean

Optional

Whether to find the mobile phone number. Requires the phone add-on on your BetterContact plan, otherwise the call is rejected with 402. Providing linkedin_url on each lead gives the best results. Example: false.

enrich_profile

boolean

Optional

Whether to enrich the full LinkedIn profile such as headline, seniority, location, and current company. Every lead must include linkedin_url. Example: false.

timeout_seconds

integer

Optional

Maximum seconds the waterfall may run before the request is terminated with whatever has been found. Defaults to the timeout configured on your account when omitted. Example: 240.

verify_catch_all

boolean

Optional

Whether to run the extra catch-all verification layer so email status is reported as catch_all_safe or catch_all_not_safe instead of catch_all. Requires the catch-all add-on on your plan, otherwise the call is rejected with 402. Example: false.

bettercontact_get_company_finder_results

Get company finder results

bettercontact_get_credits_balance

Get credits balance

bettercontact_get_enrichment_results

Get enrichment results

bettercontact_get_lead_finder_results

Get lead finder results

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);

// BetterContact tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["bettercontact"], toolNames: [
    "bettercontact_enrich_leads",
    "bettercontact_get_enrichment_results",
    "bettercontact_get_credits_balance"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Find work emails and mobile phones for these 25 webinar leads" }] });

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

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Find work emails and mobile phones for these 25 webinar leads" }],
  tools,
});

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

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Find work emails and mobile phones for these 25 webinar leads" }],
  tools,
});

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

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

await agent.run("Find work emails and mobile phones for these 25 webinar leads");

Try these prompts

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

Enrichment

Copy the prompt

Copied

Find work emails and mobile phones for these 25 leads.

Copy the prompt

Copied

Get the results of this morning's enrichment request.

Copy the prompt

Copied

How many BetterContact credits do I have left?

Profiles

Copy the prompt

Copied

Look up the company profile for northwind.com.

Copy the prompt

Copied

Look up Priya Shah at Northwind and return her current role.

Copy the prompt

Copied

Summarize the size and industry of acme.io.

Lead and company search

Copy the prompt

Copied

Find VP of Marketing leads at fintech companies in London.

Copy the prompt

Copied

Find B2B software companies with 50 to 200 employees in Germany.

Copy the prompt

Copied

Get the results of my last Lead Finder search.

SEE HOW AUTH WORKS

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

1

Authorize

Your user connects

BetterContact

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

2

Store

Their

BetterContact

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

3

Resolve

When your agent calls a

BetterContact

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

4

Audit

Every

BetterContact

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 prospecting 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.

Test other agents

See the same per-user auth pattern across other sales and prospecting connectors.

SALES

Outbound prospecting agent

Search Apollo for ICP matches, rank them, draft personalised Gmail outreach, and log every send to Google Sheets.

GTM

CRM AI agent

Turn each Granola call transcript into a HubSpot record update, a drafted Gmail follow-up, and a Slack recap.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared BetterContact API key looks fine in a demo. In production every enrichment request 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.

BetterContact 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 BetterContact as the user or through a shared key?

As the user. Each user connects their own BetterContact API key once, and Scalekit sends it with every call. Credits come from that user's BetterContact account, and audit logs attribute every request to that user, not a shared service account.

Where is the BetterContact 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 BetterContact?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example the profile lookups without bettercontact_enrich_leads, which submits up to 100 leads at once. Scalekit also enforces scope checks before every API call.

What happens when a user revokes BetterContact 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.

How does BetterContact return enrichment results?

Asynchronously for bulk work. bettercontact_enrich_leads submits 1 to 100 leads and returns a request ID, and bettercontact_get_enrichment_results reads the results once they are ready. Lead Finder and Company Finder searches work the same way, while the single person and company profile lookups return right away.

BetterContact MCP server for AI agents

Tools your prospecting agent reaches for on BetterContact, scoped per user.