Getting Started
This guide will help you connect the HG MCP Server to your MCP client and make your first API call.
MCP (Model Context Protocol) is an open standard that lets AI assistants call external
tools and data through one uniform interface — HG Insights exposes its data as MCP tools. For
technographic, firmographic, hg_id, and the rest, see the Glossary.
Prerequisites
- An HG Insights account with API access, registered with your corporate email address
- An MCP-compatible client (Claude Desktop, Cline, etc.)
HG Insights requires a corporate email address to sign up. Personal addresses (Gmail, Outlook, Yahoo, and similar) aren't accepted.
HG Insights auto-configures parts of the app based on your company domain — that's how we recognize your organization, connect you with teammates who have already signed up, and tailor your workspace. A personal address gives us none of that, so we ask everyone to register with their work address.
Authentication
HG Insights uses API keys for authentication. Each API key is scoped to your organization and provides access to all HG MCP Server tools and REST APIs.
Get Your API Key
- Log in to your HG Insights account
- Navigate to MCP in the sidebar
- Copy your API key from the MCP page
Keep your API keys secure. Never commit them to version control or share them publicly.
HG Insights also supports OAuth 2.1 for third-party integrations like ChatGPT. If you're building an application that needs user-delegated access, see the OAuth 2.1 Reference for full flow details.
MCP Setup
HG Insights supports the Model Context Protocol (MCP), allowing AI assistants to directly access HG Insights data and capabilities.
Claude Desktop
- Open Claude Desktop
- Navigate to Customize → Connectors (or visit claude.ai/customize/connectors)
- Add a new connector with the URL:
https://phoenix.hginsights.com/api/ai/YOUR_API_KEY/mcp
Replace YOUR_API_KEY with your actual HG Insights API key.
- Save and verify by asking Claude: "What HG MCP Server tools are available?"
Cline (VS Code Extension)
- Open VS Code settings (Cmd/Ctrl + ,)
- Search for "Cline MCP"
- Click Edit in settings.json
- Add the HG MCP Server using HTTP transport:
{
"cline.mcpServers": {
"hg-mcp-server": {
"url": "https://phoenix.hginsights.com/api/ai/YOUR_API_KEY/mcp"
}
}
}
Replace YOUR_API_KEY with your actual HG Insights API key.
- Reload VS Code
- Open Cline and verify HG MCP Server tools are available
Other MCP Clients
HG Insights supports many MCP clients including Cursor, Windsurf, n8n, and ChatGPT. For detailed setup instructions for each client, see our MCP Clients Guide.
Quick connection details:
- URL:
https://phoenix.hginsights.com/api/ai/{YOUR_API_KEY}/mcp - Transport: Streamable HTTP
- Authentication: API key in URL path
Replace {YOUR_API_KEY} with your actual HG Insights API key.
Choosing an API version (v1 vs v2)
HG Insights serves two MCP tool versions. v1 is the default — it is what every example above connects to, so you don't need to do anything special to use it. v2 is a newer tool suite (see the v1 → v2 changelog) that is currently in preview.
| You want… | Endpoint | Authentication |
|---|---|---|
v1 (default) | https://phoenix.hginsights.com/api/ai/YOUR_API_KEY/mcp | API key in URL path |
v1 (explicit) | https://phoenix.hginsights.com/api/mcp/v1 | API key as Bearer token |
v2 | https://phoenix.hginsights.com/api/mcp/v2 | API key as Bearer token |
v2 (OAuth) | https://phoenix.hginsights.com/api/ai/mcp/v2 | OAuth 2.1 |
Two things to know before pointing a client at v2:
- The API-key-in-URL method is
v1-only. The/api/ai/YOUR_API_KEY/mcppath always servesv1. To reachv2, authenticate with a Bearer token (sendAuthorization: Bearer YOUR_API_KEYto/api/mcp/v2) or with OAuth 2.1 (/api/ai/mcp/v2). v2requires enrollment. Its data is limited to enrolled organizations; a request from a non-enrolled org returns a hard403— never a silentv1fallback. Ask your HG contact to enroll your organization.
Bearer-token auth uses the same key you already have — just supplied as an Authorization: Bearer header instead of in the URL path. See Authentication for header examples.
Verify Your Setup
Once connected, your AI assistant should have access to HG MCP Server tools. Try asking:
- "What companies are in the healthcare industry?"
- "What technologies does Salesforce use?"
- "Generate a research rule for enterprise SaaS companies"
Your first run
Once you're connected, you don't have to figure out where to start on your own. HG Insights ships a guided first run that takes you from "connected" to a real, useful result in about a minute — ideal if you're trying HG Insights self-serve through Claude.ai, ChatGPT, or AWS QuickSuite.
Open your MCP client's prompt menu (the slash menu or prompt picker) and choose the
getting-started prompt. From there, HG Insights walks you through five steps:
- It checks what you can do. HG Insights looks at the tools available in your session — that set defines what it can run for you. It won't ask you to do any org or admin setup; your API key is all it needs.
- It asks you two quick questions. First, your role (reply with a number: 1. Sales, 2. Marketing, 3. Customer Success, 4. Exec / Strategy, 5. Other). Then, the company or product you represent, so the rest is tailored to your business. That's all it asks — no long questionnaire.
- It recommends one to three workflows. Based on your role and the tools you have, HG Insights picks the best few of its curated GTM workflows to start with.
- It runs one with you, live. HG Insights runs an Account Research Brief right away — pre-filling realistic example inputs from the company you named — and shows you the result. It also renders an interactive launchpad widget so you can see your recommended workflows and the full set at a glance. (See the Onboarding tool for what the launchpad includes and how to run a workflow from it.)
- It offers one next step. HG Insights suggests a single, specific follow-up — for example, a pre-call brief for a contact at that account — so you always have an obvious next move.
When you're ready to go further, browse the curated workflows and the full MCP tool catalog.
Next Steps
- Try the guided first run
- See the onboarding launchpad tool
- Browse available MCP tools
- Learn about MCP prompts
- View REST API documentation
- See example workflows
Troubleshooting
Connection Issues
If your MCP client can't connect to the HG MCP Server:
- Verify your API key is correct
- Check that the API URL is properly formatted
- Ensure your network allows connections to HG Insights
- Review MCP client logs for error messages
Authentication Errors
If you receive authentication errors:
- Regenerate your API key in HG Insights settings
- Update your MCP configuration with the new key
- Restart your MCP client
Tool Execution Errors
If tools fail to execute:
- Check that you have the necessary permissions
- Verify the tool parameters match the expected schema
- Review the error message for specific guidance
- Contact support if the issue persists
Support
Need help?
- View examples
- Contact your HG Insights account team for support
- Browse developer guides