Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.prontohq.com/llms.txt

Use this file to discover all available pages before exploring further.

The Pronto MCP server enables your AI agents and tools to interact directly with Pronto’s products via the Model Context Protocol. Once connected, your AI assistant can find companies, search leads, and enrich contacts on your behalf. Server URL: https://mcp.prontohq.com/mcp
Pronto doesn’t have an authentication system yet. The MCP server is compatible with any tool that allows custom installation (Claude Desktop, Claude Code, Cursor, etc.) by passing your API key as a header. OAuth support for web-based assistants is on the roadmap.

​
Prerequisites

  • A Pronto API key
  • Node.js (required by npx to run mcp-remote)

​
Installation

​
Claude Desktop

1

Open the Claude Desktop config

In Claude Desktop, go to Settings → Developer → Edit Config, then open claude_desktop_config.json.
2

Add the Pronto MCP server

Add the following entry inside mcpServers. Replace YOUR-API-KEY with your Pronto API key.
claude_desktop_config.json
{
  "mcpServers": {
    "pronto": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://mcp.prontohq.com/mcp",
        "--header",
        "X-API-Key: ${API_KEY}"
      ],
      "env": {
        "API_KEY": "YOUR-API-KEY"
      }
    }
  }
}
3

Restart Claude Desktop

Fully quit and relaunch Claude Desktop. The Pronto tools become available in the next conversation.

​
Claude Code

Run the following command in your terminal, replacing YOUR-API-KEY with your Pronto API key: 
claude mcp add pronto -e API_KEY=YOUR-API-KEY -- npx mcp-remote https://mcp.prontohq.com/mcp --header "X-API-Key:\${API_KEY}"

​
Available tools

Tools trigger actions on behalf of the user based on the goals and information already in the LLM’s context.

​
Companies

ToolDescription
enrich_accountEnrich a company with firmographic data
search_accountsSearch companies on LinkedIn Sales Navigator by filters
find_lookalike_companiesFind companies similar to one or more reference companies
get_company_stackGet the technology stack of a company

​
Leads

ToolDescription
search_leadsExtract leads from a LinkedIn Sales Navigator URL
search_leads_in_companySearch for leads at a specific company
get_searchesRetrieve all lead searches
get_searchGet the status and results of a lead search

​
Contacts

ToolDescription
single_enrich_contactSynchronously enrich a single contact with email and/or phone
bulk_enrich_contactsEnrich multiple contacts with email or phone (min 2, max 100)
get_contact_enrichmentGet the enrichment result for a contact by its enrichment ID

​
Lists

ToolDescription
get_listsRetrieve all Sales Navigator lists
get_listRetrieve a single list by its ID

​
Jobs

ToolDescription
get_job_resultPoll for the result of an async job

​
Utilities

ToolDescription
search_locationsSearch for LinkedIn Sales Navigator location IDs by name
get_creditsGet remaining Pronto credits

​
Example prompts

Here are some examples of what you can ask your AI agent to do with the Pronto MCP server.

​
People enrichment

Find the workers at ProntoHQ and find their phones and emails.
The agent uses enrich_account to find ProntoHQ’s LinkedIn ID, then search_leads_in_company to list employees, then bulk_enrich_contacts to retrieve their emails and phones.

​
Targeted prospecting

Find the [job title] of [industry] companies in Paris.
The agent uses search_locations to get the Paris location ID, then search_accounts to find [industry] companies, then search_leads_in_company to find [job title] at each company, then bulk_enrich_contacts to retrieve their emails and phones.

​
Roadmap

The MCP server is updated regularly. Upcoming work:
  • OAuth authentication, so the server can be used from any web-based AI assistant (Claude, ChatGPT, etc.)
  • Additional tools for Signals, Lists, and Personas
  • CSV download support
  • Custom UI cards
  • Token-usage optimizations