> **Building with AI coding agents?** Install the authstack plugin with one command. This equips your agent with accurate Scalekit implementation patterns.
>
> **Recommended** (the `-y` flags skip prompts, so the command runs without an interactive terminal):
> ```bash
> npx -y @scalekit-inc/cli setup -y
> ```
>
> Global:
> ```bash
> npm install -g @scalekit-inc/cli
> scalekit setup -y
> ```
>
> Supports Claude Code, Cursor, GitHub Copilot, Codex + skills for other Agent Skills-compatible agents in `~/.agents/skills`.
> Skills: integrate-agentkit, implement-saaskit, add-mcp-oauth, implement-sso, implement-scim.
> [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/)

---

# Connect AI agents to the Icypeas MCP server

The Icypeas MCP connector routes your AI agent's tool calls to Icypeas's own MCP server through Scalekit. Each user signs in to Icypeas once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 21 tools.

**Authentication:** OAuth 2.1/DCR
**Categories:** CRM & Sales, Marketing
**Tools:** 21: 3 read, 18 write, 0 destructive
**Users sign in with:** OAuth
**OAuth app:** Your own Icypeas MCP server app
**Built by:** Vendor MCP
**Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=ICYPEASMCP)

## Setup

1. ### Install the SDK

   **Node.js**

   ```bash
   npm install @scalekit-sdk/node dotenv
   ```

   **Python**

   ```bash
   pip install scalekit-sdk-python python-dotenv
   ```

2. ### Set your credentials

   Add your Scalekit credentials to your `.env` file. Find values in **[app.scalekit.com](https://app.scalekit.com)** > **Developers** > **API Credentials**.

   ```sh title=".env"
   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>
   ```

3. ### Create the Icypeas MCP connection

   In **AgentKit > Connections**, create an Icypeas MCP connection and copy its redirect URI. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/).

4. ### Register an OAuth app

   Icypeas MCP server connections use your own OAuth app. Register one with Icypeas MCP server and add the redirect URI you copied.

   Then enter the app's Client ID and Client Secret on the Icypeas MCP connection.

5. ### Authorize a user and make your first call

   **Node.js** (`quickstart.mts`)

   ```typescript
   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   import { createInterface } from 'node:readline/promises'

   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENVIRONMENT_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions

   const connector = 'icypeasmcp'
   const identifier = 'user_123'

   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Icypeas MCP:', link)
   const rl = createInterface({ input: process.stdin, output: process.stdout })
   await rl.question('Press Enter after authorizing...')
   rl.close()

   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'icypeasmcp_subscription_information',
     toolInput: {},
   })
   console.log(result)
   ```

   ```bash
   npx tsx quickstart.mts
   ```

   **Python** (`quickstart.py`)

   ```python
   import os
   from scalekit import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()

   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions

   connection_name = "icypeasmcp"
   identifier = "user_123"

   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize Icypeas MCP:", link_response.link)
   input("Press Enter after authorizing...")

   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="icypeasmcp_subscription_information",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)
   ```

   ```bash
   python quickstart.py
   ```

   Each user signs in once. See [Authorize a user](/agentkit/tools/authorize/) for the full flow and statuses.

## Tools

Pass the exact name to `execute_tool`, with an input like each tool's example. To ask for a tool that's missing, use the [request form](https://scalekitsupport.portal.usepylon.com/forms/request-a-connector-tool).

**Node.js**

```typescript
const result = await actions.executeTool({
  toolName: 'icypeasmcp_find_companies_count',
  toolInput: {
    query: {},
  },
  connector: 'icypeasmcp',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="icypeasmcp_find_companies_count",
    tool_input={
        "query": {},
    },
    connection_name="icypeasmcp",
    identifier="user_123",
)
```

`result.data` is the app's response as JSON, and `result.execution_id` (`executionId` in Node.js) is the ID of the call.

### `icypeasmcp_find_companies_count`

Find Companies Count · Read-only

Count the number of companies matching a query in the Icypeas lead database. This is free and does not consume credits. Use it to assess result size before fetching. Supports filters: name, lid, urn, companyId, type, industry, location, headcount, keyword, domain, revenue, headcountGrowth.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `query` (`object`, required): The search query with filters

Example input: `{"query":{}}`

### `icypeasmcp_find_people_count`

Find People Count · Read-only

Count the number of people matching a query in the Icypeas lead database. This is free and does not consume credits. Use it to assess result size before fetching. Supports filters: firstname, lastname, currentJobTitle, pastJobTitle, currentCompanyName, pastCompanyName, currentCompanyUrn, pastCompanyUrn, currentCompanyWebsite, pastCompanyWebsite, currentCompanyId, pastCompanyId, school, languages, skills, location, keyword.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `query` (`object`, required): The search query with filters

Example input: `{"query":{}}`

### `icypeasmcp_subscription_information`

Subscription Information · Read-only

Retrieve the current user's Icypeas subscription information: plan name, account status (free, none, cancelled, paid, unpaid), remaining credits, and daily SalesNav quota. Takes no input. Use this to check the user's account status or remaining credits.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs: none.

Example input: `{}`

### `icypeasmcp_bulk_company_scraper`

Bulk Company Scraper · Write

Scrape full LinkedIn company data for multiple companies at once. Use this tool whenever 2 or more LinkedIn company URLs are provided. For a single company URL, use company-scraper instead. Handles any number of URLs automatically (batched internally at 50 per call, maximum 50,000).

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `urls` (`array`, required): List of LinkedIn company URLs to scrape (minimum 2, maximum 50,000)

Example input: `{"urls":[]}`

### `icypeasmcp_bulk_company_search`

Bulk Company Search · Write

Find LinkedIn company page URLs for multiple companies at once. Use this tool whenever 2 or more companies are provided. For a single company, use company-search instead. Handles any number of entries automatically (batched internally at 50 per call).

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `companies` (`array`, required): List of companies to look up (minimum 2, maximum 50,000)

Example input: `{"companies":[]}`

### `icypeasmcp_bulk_domain_search`

Bulk Domain Search · Write

Find all known email addresses for multiple domains or companies at once. Use this tool whenever 2 or more domains/companies are provided. For a single domain, use domain-search instead. Handles any number of entries automatically (batched internally at 50 per call).

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `domains` (`array`, required): List of domains or company names to search (minimum 2, maximum 50,000)

Example input: `{"domains":[]}`

### `icypeasmcp_bulk_email_search`

Bulk Email Search · Write

Find professional email addresses for multiple people at once. Use this tool whenever 2 or more people are provided. For a single person, use email-search instead. Handles any number of entries automatically (batched internally at 50 per call).

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `prospects` (`array`, required): List of people to look up (minimum 2, maximum 50,000)

Example input: `{"prospects":[]}`

### `icypeasmcp_bulk_email_verification`

Bulk Email Verification · Write

Verify whether multiple email addresses are valid and deliverable at once. Use this tool whenever 2 or more emails are provided. For a single email, use email-verification instead. Handles any number of entries automatically (batched internally at 50 per call).

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `emails` (`array`, required): List of email addresses to verify (minimum 2, maximum 50,000)

Example input: `{"emails":[]}`

### `icypeasmcp_bulk_profile_scraper`

Bulk Profile Scraper · Write

Scrape full LinkedIn profile data for multiple people at once. Use this tool whenever 2 or more LinkedIn profile URLs are provided. For a single profile URL, use profile-scraper instead. Handles any number of URLs automatically (batched internally at 50 per call, maximum 50,000).

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `urls` (`array`, required): List of LinkedIn profile URLs to scrape (minimum 2, maximum 50,000)

Example input: `{"urls":[]}`

### `icypeasmcp_bulk_profile_search`

Bulk Profile Search · Write

Find LinkedIn profile URLs for multiple people at once. Use this tool whenever 2 or more people are provided. For a single person, use profile-search instead. Handles any number of entries automatically (batched internally at 50 per call).

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `profiles` (`array`, required): List of people to look up (minimum 2, maximum 50,000)

Example input: `{"profiles":[]}`

### `icypeasmcp_bulk_reverse_email_lookup`

Bulk Reverse Email Lookup · Write

Find LinkedIn profile URLs for multiple professional email addresses at once. Use this tool whenever 2 or more emails are provided. For a single email, use reverse-email-lookup instead. Handles any number of emails automatically (batched internally at 50 per call).

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `emails` (`array`, required): List of professional email addresses to look up (minimum 2, maximum 50,000)

Example input: `{"emails":[]}`

### `icypeasmcp_company_scraper`

Company Scraper · Write

Scrape a single LinkedIn company page by URL and return all available company data (name, description, industry, headcount, revenue, specialties, address, employee growth, etc.). Use this tool for exactly one company URL. If the user provides 2 or more URLs, use bulk-company-scraper instead.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `url` (`string`, required): LinkedIn company URL (e.g. https://www.linkedin.com/company/my-linkedin-id)

Example input: `{"url":"<url>"}`

### `icypeasmcp_company_search`

Company Search · Write

Find the LinkedIn company page URL for a single company name or domain. Use this tool for exactly one company. If the user provides 2 or more companies, use bulk-company-search instead.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `companyOrDomain` (`string`, required): Company name (e.g. 'NEC Technologies') or domain name (e.g. 'nec.com')

Example input: `{"companyOrDomain":"NEC Technologies"}`

### `icypeasmcp_domain_search`

Domain Search · Write

Scan a domain or company and return all role-based email addresses associated with it. Useful for finding generic email addresses inside an organisation.Use this tool for exactly one domain. If the user provides 2 or more items, use bulk-domain-search instead.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `domainOrCompany` (`string`, required): Company name (e.g. 'Icypeas') or domain (e.g. 'icypeas.com')

Example input: `{"domainOrCompany":"Icypeas"}`

### `icypeasmcp_email_search`

Email Search · Write

Find the professional email address of a person given their first name, last name, and company name or domain. Returns the email, certainty level, and MX provider when found.Use this tool for exactly one email address. If the user provides 2 or more items, use bulk-email-search instead.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `domainOrCompany` (`string`, required): Company name (e.g. 'Icypeas') or domain (e.g. 'icypeas.com')
- `firstname` (`string`, required): First name of the person
- `lastname` (`string`, required): Last name of the person

Example input: `{"domainOrCompany":"Icypeas","firstname":"<firstname>","lastname":"<lastname>"}`

### `icypeasmcp_email_verification`

Email Verification · Write

Verify whether an email address is valid and deliverable. Returns the certainty level and MX provider when the address is confirmed to exist.Use this tool for exactly one email address. If the user provides 2 or more items, use bulk-email-verification instead.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `email` (`string`, required): The email address to verify

Example input: `{"email":"<email>"}`

### `icypeasmcp_find_companies`

Find Companies · Write

Search for companies in the Icypeas lead database and retrieve detailed results. Automatically fetches all pages up to a maximum of 50,000 companies (or up to maxResults if specified). Supports filters: name, lid, urn, companyId, type, industry, location, headcount, keyword, domain, revenue, headcountGrowth. Use find-companies-count first to check result size without consuming credits.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `query` (`object`, required): The search query with filters
- `maxResults` (`integer`, optional): Maximum number of companies to retrieve (1–50,000). Defaults to all results up to 50,000.

Example input: `{"query":{}}`

### `icypeasmcp_find_people`

Find People · Write

Search for people in the Icypeas lead database and retrieve detailed results. Automatically fetches all pages up to a maximum of 50,000 people (or up to maxResults if specified). Supports filters: firstname, lastname, currentJobTitle, pastJobTitle, currentCompanyName, pastCompanyName, currentCompanyUrn, pastCompanyUrn, currentCompanyWebsite, pastCompanyWebsite, currentCompanyId, pastCompanyId, school, languages, skills, location, keyword. Use find-people-count first to check result size without consuming credits.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `query` (`object`, required): The search query with filters
- `maxResults` (`integer`, optional): Maximum number of people to retrieve (1–50,000). Defaults to all results up to 50,000.

Example input: `{"query":{}}`

### `icypeasmcp_profile_scraper`

Profile Scraper · Write

Scrape a single LinkedIn profile by URL and return all available profile data (name, headline, work experience, education, skills, contact info, etc.). Use this tool for exactly one profile URL. If the user provides 2 or more URLs, use bulk-profile-scraper instead.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `url` (`string`, required): LinkedIn profile URL (e.g. https://www.linkedin.com/in/my-linkedin-id)

Example input: `{"url":"<url>"}`

### `icypeasmcp_profile_search`

Profile Search · Write

Find the LinkedIn profile URL for a single person given their name and company or job title. Use this tool for exactly one person. If the user provides 2 or more people, use bulk-profile-search instead.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `firstname` (`string`, required): First name of the prospect
- `lastname` (`string`, required): Last name of the prospect
- `companyOrDomain` (`string`, optional): Company name or domain name (required if jobTitle is not provided)
- `jobTitle` (`string`, optional): Job title of the prospect (required if companyOrDomain is not provided)

Example input: `{"firstname":"<firstname>","lastname":"<lastname>"}`

### `icypeasmcp_reverse_email_lookup`

Reverse Email Lookup · Write

Find the LinkedIn profile URL behind a single professional email address. Use this tool for exactly one email. If the user provides 2 or more emails, use bulk-reverse-email-lookup instead.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `email` (`string`, required): The professional email address to look up

Example input: `{"email":"<email>"}`

## Related

Other CRM & Sales connectors ([all 174](/agentkit/connectors/?category=crm-sales)):

- [Salesforce](/agentkit/connectors/salesforce/): Scalekit connector, OAuth, 74 tools
- [HubSpot](/agentkit/connectors/hubspot/): Scalekit connector, OAuth, 457 tools
- [Close](/agentkit/connectors/close/): Scalekit connector, OAuth, 103 tools


---

## More Scalekit documentation

| Resource | What it contains | When to use it |
|----------|-----------------|----------------|
| [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content |
| [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas |
| [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |
