Build on Employbl data

1. Open Settings → Connectors → Advanced, and turn on Developer mode.
2. Choose Create. Name it Employbl, set the MCP server URL to https://www.employbl.com/api/chatgpt/mcp, and pick OAuth for authentication.
3. Start a new chat, open the + menu, pick Employbl, and sign in to Employbl when ChatGPT asks.

ChatGPT gets a curated surface — company and job search, funding rounds, company profiles that render as a card in the conversation — rather than the full 27 tools. Adding it by hand needs Developer mode, which ChatGPT offers on its paid plans; the directory listing removes that step once it is live.

1. In claude.ai or Claude Desktop, open Settings → Connectors.
2. Choose Add custom connector. Name it Employbl and paste https://www.employbl.com/api/mcp.
3. Click Connect, sign in to Employbl in the window that opens, and click Authorize.

One connection covers claude.ai, Claude Desktop and the Claude mobile apps on the same account.

1. Run the command below once.
2. Inside a session, type /mcp and pick Employbl to sign in. A browser window opens; click Authorize.

claude mcp add --transport http employbl https://www.employbl.com/api/mcp

1. Click Add to Cursor. Cursor opens with the server pre-filled; confirm Install.
2. Click the sign-in prompt next to Employbl in Settings → MCP and authorize in the browser.

{
  "mcpServers": {
    "employbl": {
      "url": "https://www.employbl.com/api/mcp"
    }
  }
}

1. Click Add to VS Code and confirm the server. Or run MCP: Add Server from the command palette and paste the URL.
2. Start the server from the MCP panel; VS Code opens a browser to sign in.

{
  "servers": {
    "employbl": {
      "type": "http",
      "url": "https://www.employbl.com/api/mcp"
    }
  }
}

1. Add the block below to ~/.codex/config.toml.
2. Restart Codex. On first use it opens a browser to sign in to Employbl.

[mcp_servers.employbl]
url = "https://www.employbl.com/api/mcp"

1. Add the block below to ~/.gemini/settings.json.
2. Run /mcp auth employbl inside Gemini CLI to sign in.

{
  "mcpServers": {
    "employbl": {
      "httpUrl": "https://www.employbl.com/api/mcp"
    }
  }
}

1. Add the block below to ~/.codeium/windsurf/mcp_config.json (Settings → MCP → Manage opens it).
2. Refresh the MCP list and authorize Employbl when prompted.

{
  "mcpServers": {
    "employbl": {
      "serverUrl": "https://www.employbl.com/api/mcp"
    }
  }
}

1. Add a streamable-HTTP server named employbl at https://www.employbl.com/api/mcp.
2. If the client supports OAuth, sign in when it asks. If it does not, create an access token at Profile → MCP and send it as a Bearer header.

{
  "mcpServers": {
    "employbl": {
      "url": "https://www.employbl.com/api/mcp",
      "headers": {
        "Authorization": "Bearer {your-mcp-key}"
      }
    }
  }
}

Or use an access token

For clients without an OAuth flow, generate a permanent access token at Profile → MCP and send it as a Bearer header. The token authenticates every MCP and REST request and is rate-limited per token.

{
  "mcpServers": {
    "employbl": {
      "url": "https://www.employbl.com/api/mcp",
      "headers": {
        "Authorization": "Bearer {your-mcp-key}"
      }
    }
  }
}

What to ask first

Once connected, your assistant can call the tools in Section II on your behalf. Three prompts that use the data well:

• “Find Series A to C companies in San Francisco hiring senior backend engineers who use Go.”
• “Which companies raised in the last 30 days and have open product roles?”
• “Update my Employbl preferences: remote, staff level, fintech or developer tools.”