Icypeas MCP server for AI agents

Live

API KEY

LEAD ENRICHMENT

CRM & Sales

Icypeas gives your agent lead enrichment from email and LinkedIn data: search its people and company databases, discover and verify professional emails, scrape profiles and company pages, and run bulk searches.

  • Per-user credentials: each call uses the actual user's API key, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
Icypeas
agent · Acme Q3
Run
How many heads of growth work at SaaS companies in France?
S
icypeas_count_people
94ms
Lead enrichment agent
Icypeas counts 1,284 people who match heads of growth at SaaS companies in France. I can fetch them next with a people search.
Sources: Icypeas lead database
icypeas
1,284 people
18:29
Message Claude...

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

CALL ANY TOOL
23 tools for lead enrichment in Icypeas: search people and companies, discover and verify emails, find and scrape LinkedIn profiles and company pages, and run bulk searches of up to 5000 rows.
icypeas_bulk_search
Search bulk
Start a bulk search that runs email discovery, email verification or domain scanning over up to 5000 rows. Returns success, the bulk file id and its status (for example in_progress); results are fetched separately. Use this for many rows at once. Check progress with icypeas_list_bulk_search_files and read rows with icypeas_list_bulk_search_results. Use the single-search tools for one item. Rate limit is 1 call per second.
Parameters
Name
Type
Required
Description
data
array
Required
The rows to process, as an array of rows where each row is itself an array of strings. For email-search each row has three items: first name, last name and domain or company, for example ["John", "Doe", "icypeas.com"] (first or last name may be an empty string but not both). For email-verification each row is a single email address, for example ["john.doe@icypeas.com"]. For domain-search each row is a single domain or company name, for example ["icypeas.com"]. Maximum 5000 rows.
name
string
Required
A name for this bulk search so you can find it later.
task
string
Required
The type of search to run on every row. One of email-search, email-verification or domain-search. One of: `email-search`, `email-verification`, `domain-search`.
external_ids
array
Optional
Your own identifiers, one per row, in the same order and with the same length as data. Not checked for uniqueness.
icypeas_count_companies
Count companies
icypeas_count_people
Count people
icypeas_domain_search
Search domain
icypeas_email_search
Search email
icypeas_email_verification
Email verification
icypeas_find_companies
Find companies
icypeas_find_company_url
Find company url
icypeas_find_company_urls_bulk
Find company urls bulk
icypeas_find_people
Find people
icypeas_find_profile_url
Find profile url
icypeas_find_profile_urls_bulk
Find profile urls bulk
icypeas_get_search_result
Get search result
icypeas_get_subscription
Get subscription
icypeas_list_bulk_search_files
List bulk search files
icypeas_list_bulk_search_results
List bulk search results
icypeas_list_single_searches
List single searches
icypeas_reverse_email_lookup
Reverse email lookup
icypeas_reverse_email_lookup_bulk
Reverse email lookup bulk
icypeas_scrape_companies_bulk
Scrape companies bulk
icypeas_scrape_company
Scrape company
icypeas_scrape_profile
Scrape profile
icypeas_scrape_profiles_bulk
Scrape profiles bulk
Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
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);

// Icypeas tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["icypeas"], toolNames: [
    "icypeas_find_people",
    "icypeas_email_search",
    "icypeas_get_search_result"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Find the email of the head of growth at contoso.com" }] });
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: ["icypeas"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Find the email of the head of growth at contoso.com" }],
  tools,
});

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

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Find the email of the head of growth at contoso.com" }],
  tools,
});

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

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

await agent.run("Find the email of the head of growth at contoso.com");
Try these prompts
Copy any prompt into your agent. Each maps directly to a Icypeas tool. Click to copy, paste into your agent, done.
Search the database
Copy the prompt
Copied
How many heads of growth work at SaaS companies in France?
Copy the prompt
Copied
Find marketing directors at fintech companies in London.
Copy the prompt
Copied
Find the LinkedIn company URL for northwind.io.
Emails
Copy the prompt
Copied
Find the professional email of Camille Martin at contoso.com.
Copy the prompt
Copied
Verify whether jordan@fabrikam.com can receive mail.
Copy the prompt
Copied
Find role-based addresses like contact@ for northwind.io.
Profiles and bulk
Copy the prompt
Copied
Scrape this LinkedIn profile and summarize the person's role.
Copy the prompt
Copied
Run a bulk email verification on these 300 addresses.
Copy the prompt
Copied
Show the progress of my bulk searches.
SEE HOW AUTH WORKS
Each user connects their own Icypeas 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
Icypeas
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
Icypeas
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
Icypeas
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
Icypeas
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 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 marketing 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 Icypeas API key looks fine in a demo. In production every email search 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.
Icypeas 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 Icypeas as the user or through a shared API key?
As the user. Each user connects their own Icypeas API key once, and Scalekit sends it with every call. Audit logs attribute every search and bulk job to that user, not a shared service account.
Where is the Icypeas 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 Icypeas?
Yes. Filter by tool name in listScopedTools to expose only what you want, for example the count and search tools without icypeas_bulk_search, which starts a job over up to 5000 rows. Icypeas has no delete tools. Scalekit also enforces scope checks before every API call.
What happens when a user revokes Icypeas 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.
Why does an Icypeas email search not return the email right away?
Email discovery, verification, and domain scans run as searches. icypeas_email_search returns a search _id with an initial status, and the agent calls icypeas_get_search_result with that _id until the status is final. Bulk results come back through icypeas_list_bulk_search_results.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""icypeas"": {
""url"": ""https://mcp.scalekit.com/icypeas"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.icypeas]
url = ""https://mcp.scalekit.com/icypeas""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""icypeas"": {
""url"": ""https://mcp.scalekit.com/icypeas"",
""type"": ""http""
}
}
}