Prospeo connector for AI agents

CALL ANY TOOL

8 tools for contact enrichment in Prospeo: search people and companies, look up valid filter values, enrich people with verified emails and mobiles, enrich companies, and run bulk enrichment of up to 50 records.

prospeo_bulk_enrich_company

Bulk enrich company

Enrich up to 50 companies in one request with firmographics, funding, technology and headcount. Returns matched (identifier, company), not_matched identifiers, invalid_datapoints identifiers and total_cost in credits. Use for batches. Use prospeo_enrich_company for a single company. Each record needs an identifier plus at least one company field; records without one are returned in invalid_datapoints. Costs 1 credit per matched company.

Parameters

Name

Type

Required

Description

data

array

Required

List of up to 50 companies to enrich. Each item needs an identifier plus at least one of company_website, company_linkedin_url, company_name or company_id. Example: [{"identifier":"1","company_website":"intercom.com"},{"identifier":"2","company_linkedin_url":"https://www.linkedin.com/company/deloitte"}].

prospeo_bulk_enrich_person

Bulk enrich person

prospeo_enrich_company

Enrich company

prospeo_enrich_person

Enrich person

Enrich one person with verified work email, optional mobile number, job history and current company details. Returns the matched person (identity, email, mobile, location, job history, skills) and their current company, or an error with NO_MATCH when nothing matches. Use for a single person. Use prospeo_bulk_enrich_person for up to 50 people in one call, and prospeo_search_person to find people before enriching. Provide one of: first_name + last_name + a company field, full_name + a company field, linkedin_url, email, or person_id. Costs 1 credit per email found and 10 credits when a mobile is found.

Parameters

Name

Type

Required

Description

company_linkedin_url

string

Optional

Public LinkedIn URL of the person's company.

company_name

string

Optional

Name of the person's company. Many companies share names, so prefer company_website when you have it.

company_website

string

Optional

Website or domain of the person's company. Preferred over company_name for accuracy.

email

string

Optional

Work email address of the person. This alone is enough to match.

enrich_mobile

boolean

Optional

When true, also reveal the person's mobile number if one exists. Costs 10 credits per record with a mobile instead of 1 credit for an email.

first_name

string

Optional

First name of the person. Combine with last_name and a company field.

full_name

string

Optional

Full name of the person. Combine with a company field when first_name and last_name are not given.

last_name

string

Optional

Last name of the person. Combine with first_name and a company field.

linkedin_url

string

Optional

Public LinkedIn profile URL of the person. This alone is enough to match.

only_verified_email

boolean

Optional

When true, only return a record if it has a verified email; records without one come back as no match and are not charged.

only_verified_mobile

boolean

Optional

When true, only return records that have a mobile number. Setting this to true automatically turns on enrich_mobile.

person_id

string

Optional

Prospeo person_id returned by prospeo_search_person. This alone is enough to match.

prospeo_get_account_information

Get account information

prospeo_search_company

Search company

prospeo_search_person

Search person

prospeo_search_suggestions

Search suggestions

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);

// Prospeo tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["prospeo"], toolNames: [
    "prospeo_search_person",
    "prospeo_enrich_person",
    "prospeo_enrich_company"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Find VPs of Sales at SaaS companies in Canada with verified emails" }] });

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

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Find VPs of Sales at SaaS companies in Canada with verified emails" }],
  tools,
});

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

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Find VPs of Sales at SaaS companies in Canada with verified emails" }],
  tools,
});

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

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

await agent.run("Find VPs of Sales at SaaS companies in Canada with verified emails");

Try these prompts

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

Search

Copy the prompt

Copied

Find VPs of Sales at SaaS companies in Canada.

Copy the prompt

Copied

Find fintech companies with 50 to 200 employees that use Stripe.

Copy the prompt

Copied

What job title values does Prospeo accept for RevOps?

Enrich

Copy the prompt

Copied

Get the work email for Daniel Ortiz at fabrikam.com.

Copy the prompt

Copied

Enrich northwind.io with funding and headcount.

Copy the prompt

Copied

Enrich these 40 people with verified emails.

Account

Copy the prompt

Copied

How many Prospeo credits do I have left?

Copy the prompt

Copied

When does my Prospeo quota renew?

Copy the prompt

Copied

Enrich these 20 company domains in one request.

SEE HOW AUTH WORKS

Each user connects their own Prospeo 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

Prospeo

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

Prospeo

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

Prospeo

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

Prospeo

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 CRM and sales 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 CRM and sales 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 Prospeo API key looks fine in a demo. In production every enrichment 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.

Prospeo 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 Prospeo as the user or through a shared API key?

As the user. Each user connects their own Prospeo API key once, and Scalekit sends it with every call. Audit logs attribute every search and enrichment to that user, not a shared service account.

Where is the Prospeo 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 Prospeo?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example search and single enrichment without the bulk enrichment tools, which process up to 50 records per call. Prospeo has no delete tools. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Prospeo 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 Prospeo return when it enriches a person?

prospeo_enrich_person returns the matched person with a verified work email, an optional mobile number, job history, and current company details. prospeo_bulk_enrich_person does the same for up to 50 people and lists the identifiers it could not match.

Prospeo MCP server for AI agents

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