> **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 Prospeo MCP server

The Prospeo MCP connector routes your AI agent's tool calls to Prospeo's own MCP server through Scalekit. Each user signs in to Prospeo once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 8 tools.

**Authentication:** OAuth 2.1/DCR
**Categories:** CRM & Sales
**Tools:** 8: 8 read, 0 write, 0 destructive
**Users sign in with:** OAuth
**OAuth app:** Your own Prospeo MCP server app
**Built by:** Vendor MCP
**Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=PROSPEOMCP)

## 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 Prospeo MCP connection

   In **AgentKit > Connections**, create a Prospeo 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

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

   Then enter the app's Client ID and Client Secret on the Prospeo 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 = 'prospeomcp'
   const identifier = 'user_123'

   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Prospeo 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: 'prospeomcp_enrich_company',
     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 = "prospeomcp"
   identifier = "user_123"

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

   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="prospeomcp_enrich_company",
       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: 'prospeomcp_bulk_enrich_company',
  toolInput: {
    data: [],
  },
  connector: 'prospeomcp',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="prospeomcp_bulk_enrich_company",
    tool_input={
        "data": [],
    },
    connection_name="prospeomcp",
    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.

### `prospeomcp_bulk_enrich_company`

Bulk Enrich Companies · Read-only

Enrich up to 25 companies in ONE call — the canonical lookup tool when you already have a list of company names/domains (CRM exports, account lists, competitor maps). Each record needs one of: company_id, company_website, company_linkedin_url, or company_name. Returns the full company profile per match (tech stack, attributes, funding, job postings — same shape as enrich_company). identifier defaults to company_id when provided so search_company → bulk_enrich_company chains correlate without extra bookkeeping. Use search_company instead when you don't yet know which companies to target. 1 credit per matched company.

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

Inputs:

- `data` (`array`, required): Up to 25 company records to enrich in a single request.

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

### `prospeomcp_bulk_enrich_person`

Bulk Enrich People · Read-only

Enrich up to 25 people in ONE call — the canonical follow-up to search_person. Pass each search result's person_id as a record; the matched.identifier in the response equals that person_id so you can stitch results back to the original list. Per-record cost is identical to enrich_person (1 credit per matched email, 10 per matched email+mobile). Response also includes free_enrichment per record so you can attribute credit consumption. Returns a compact response per record (no job_history, no skills, abbreviated company summary) — use enrich_person if you need the full profile for a specific person. For >25 records, call this multiple times — do not auto-batch.

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

Inputs:

- `data` (`array`, required): Up to 25 person records to enrich in a single request.
- `enrich_mobile` (`boolean`, optional): Also look up mobile numbers (10 credits per matched record; email is included at no extra cost). Default: `false`.
- `only_verified_email` (`boolean`, optional): Only return records where a verified email is found. Applies to every record in `data`. Default: `false`.
- `only_verified_mobile` (`boolean`, optional): Only return records where a verified mobile is found (automatically enables enrich_mobile). Default: `false`.

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

### `prospeomcp_enrich_company`

Enrich Company · Read-only

Enrich a company — return its full profile (headcount, industry, revenue, tech stack, funding, social links, HQ phone). Provide at least one identifier: company_website (most accurate), company_linkedin_url, company_name, or company_id (from a prior search result). Credits: 1 per successful match. No charge if no match is found. Check free_enrichment in the response to confirm whether credits were deducted.

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

Inputs:

- `company_id` (`string`, optional): Prospeo company_id from a prior Enrich Person or Search result
- `company_linkedin_url` (`string`, optional): Company LinkedIn URL
- `company_name` (`string`, optional): Company name, e.g. Acme Inc
- `company_website` (`string`, optional): Company website domain, e.g. acme.com

Example input: `{}`

### `prospeomcp_enrich_person`

Enrich Person · Read-only

Enrich a SINGLE person — return their full profile with verified email and/or mobile, job history, and current company. Provide at least one identifier: linkedin_url, email, person_id (from a prior search result), or full_name/first_name+last_name plus company_name/company_website. Credits: 1 for email, 10 for email + mobile (set enrich_mobile=true; email is included free when mobile is requested). Credits are only deducted when the requested contact data is actually returned. No charge if no person is matched, and no charge if only_verified_email/only_verified_mobile is set but no verified contact exists. Check free_enrichment in the response to confirm. If you have MULTIPLE people to enrich (e.g. a full page of search_person results), use bulk_enrich_person instead — same per-record cost, one call.

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

Inputs:

- `company_linkedin_url` (`string`, optional): Company LinkedIn URL
- `company_name` (`string`, optional): Current employer name
- `company_website` (`string`, optional): Company website domain, e.g. acme.com
- `email` (`string`, optional): Person's email address
- `enrich_mobile` (`boolean`, optional): Also look up the person's mobile phone number (costs 10 credits; email is included at no extra cost when mobile is requested). Default: `false`.
- `first_name` (`string`, optional): Person's first name
- `full_name` (`string`, optional): Person's full name (alternative to first_name + last_name)
- `last_name` (`string`, optional): Person's last name
- `linkedin_url` (`string`, optional): LinkedIn profile URL, e.g. https://www.linkedin.com/in/johndoe
- `only_verified_email` (`boolean`, optional): Only return the result if a verified email is found. Default: `false`.
- `only_verified_mobile` (`boolean`, optional): Only return the result if a verified mobile is found (automatically enables enrich_mobile). Default: `false`.
- `person_id` (`string`, optional): Prospeo person_id from a prior Search Person result

Example input: `{}`

### `prospeomcp_get_account_info`

Account Info · Read-only

Check your Prospeo account status — credits remaining, plan name, renewal date, and team size. Free endpoint, does not consume credits. Useful to verify the API key works or check remaining quota.

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

Inputs: none.

Example input: `{}`

### `prospeomcp_search_company`

Search Companies · Read-only

Search Prospeo's company database using typed filters. Returns up to 25 results per page (max 1000 pages). Costs 1 credit per page that returns results. WORKFLOW: (1) call search_suggestions first for any location/technology/industry/NAICS/SIC the user mentioned. (2) build filters. (3) pass any company_id from results to enrich_company for full profile (tech stack, attributes, job postings — not included in search). Available filters include firmographics (industry, headcount, technology, revenue, funding) and intent/event filters (company_news, company_key_execs, company_lookalike, company_icp, company_website_search, company_google_discovery) — see each filter's description for when to use it. At least one positive (include) filter is required.

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

Inputs:

- `filters` (`object`, required): Company search filters. At least one positive (include) filter is required. For values that can't be guessed (locations, technologies, industries, NAICS, SIC), call search_suggestions first.
- `page` (`integer`, optional): Page number (1–1000). Each page returns up to 25 results. Default: `1`.

Example input: `{"filters":{}}`

### `prospeomcp_search_person`

Search People · Read-only

Search Prospeo's professional database using typed filters. Returns up to 25 results per page (max 1000 pages). Costs 1 credit per page that returns results. WORKFLOW: (1) for any filter value the user mentioned by description (location, technology, industry, job title, NAICS/SIC code), call search_suggestions first to get the canonical string. (2) build filters mixing person fields (person_job_title, person_seniority, person_location_search) with company fields (company_industry, company_headcount_range, company_technology). (3) take each result's person_id and pass it to bulk_enrich_person in one call to reveal verified emails/mobiles. Each result includes person fields (name, title, location, linkedin_url) and a company summary. email and mobile are obfuscated previews in search results (revealed=false) with status (VERIFIED / UNVERIFIED / null) — use status to gauge coverage before enriching. At least one positive (include) filter is required.

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

Inputs:

- `filters` (`object`, required): Filter object combining person-specific filters and company filters. At least one positive (include) filter is required — exclude-only payloads are rejected for performance. For values that can't be guessed (locations, technologies, industries, NAICS, SIC, job titles), call search_suggestions first.
- `page` (`integer`, optional): Page number (1–1000). Each page returns up to 25 results. Default: `1`.

Example input: `{"filters":{}}`

### `prospeomcp_search_suggestions`

Search Suggestions · Read-only

Resolve canonical filter values BEFORE building a search. Free — no credit cost. Use type='location' for person/company location filters, 'job_title' for job-title filters, 'technology' for company_technology, 'industry' for company_industry, 'naics' / 'sic' for the code filters. Locations and technologies in particular cannot be guessed — call this first or your search will return zero results.

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

Inputs:

- `query` (`string`, required): Search query (min 2 chars). Case-insensitive.
- `type` (`string`, required): Which value type to resolve. 'location' for person/company location filters; 'job_title' for person_job_title.include and company_job_posting_hiring_for; 'technology' for company_technology; 'industry' for company_industry; 'naics' / 'sic' return {code, label} pairs for company_naics / company_sics. NAICS results follow the NAICS 2022 revision — legacy codes like 5112 (NAICS 2017 Software Publishers, now 5132) may not match; prefer label-based queries (e.g. 'software') when unsure of the current code. One of: `location`, `job_title`, `technology`, `industry`, `naics`, `sic`.

Example input: `{"query":"<query>","type":"software"}`

## 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 |
