Close MCP: connect Close to Claude, ChatGPT and Cursor

How to connect Close to Claude or ChatGPT via MCP

1. 1
   Click Connect Close free and sign in to Close.
2. 2
   Choose which Close tools stay on. Switch off the ones that create, update or delete leads, tasks and opportunities until you need them.
3. 3
   Add ContextGate to your AI app as a connector or MCP server:

   ClaudeChatGPTClaude CodeCursorGitHub CopilotCodexGemini CLIOther

   1. 1

      In Claude, open Settings → Connectors and click Add custom connector.

   2. 2

      Name it ContextGate and paste this URL:

      https://api.contextgate.ai/mcp

   3. 3

      Click Add, then Connect, and sign in to ContextGate.

   4. 4

      In a chat, turn ContextGate on from the + menu → Connectors. Cowork and the desktop app use the same connectors.

   The full Claude guide

   1. 1

      In ChatGPT settings, open Apps & Connectors (or Connectors) → Advanced and turn on Developer mode.

   2. 2

      Create a connector, choose OAuth, and paste this URL:

      https://api.contextgate.ai/mcp

   3. 3

      Sign in to ContextGate when ChatGPT redirects you, then pick the connector in a chat.

   The full ChatGPT guide

   1. 1

      Run this in a terminal:

      claude mcp add --transport http contextgate https://api.contextgate.ai/mcp

   2. 2

      Start Claude Code, run /mcp, choose contextgate and sign in to ContextGate.

   The full Claude Code guide

   Add to Cursor

   1. 1

      Click Add to Cursor, or add this to ~/.cursor/mcp.json:

      {
        "mcpServers": {
          "contextgate": {
            "url": "https://api.contextgate.ai/mcp"
          }
        }
      }

   2. 2

      In Cursor Settings → MCP, sign in to ContextGate when Cursor asks.

   The full Cursor guide

   Add to VS Code

   1. 1

      Click Add to VS Code, or add this to .vscode/mcp.json:

      {
        "servers": {
          "contextgate": {
            "type": "http",
            "url": "https://api.contextgate.ai/mcp"
          }
        }
      }

   2. 2

      Start the server when VS Code asks, sign in to ContextGate, and use it from Copilot Chat in Agent mode.

   The full GitHub Copilot guide

   1. 1

      Run this in a terminal:

      codex mcp add contextgate --url https://api.contextgate.ai/mcp

   2. 2

      Then sign in to ContextGate:

      codex mcp login contextgate

   The full Codex guide

   1. 1

      Run this in a terminal:

      gemini mcp add --transport http contextgate https://api.contextgate.ai/mcp

   2. 2

      In Gemini CLI, run /mcp auth contextgate and sign in to ContextGate.

   The full Gemini CLI guide

   1. 1

      Add a remote (HTTP) MCP server with this URL:

      https://api.contextgate.ai/mcp

   2. 2

      Apps that support MCP sign-in ask you to sign in to ContextGate the first time they connect.

   3. 3

      An app that can't sign in can use a workspace API key instead: create one under API keys and add ?api_key=<your key> to the URL.

   More on adding it to any MCP app
4. 4
   Ask your AI app to use Close through ContextGate, then open Activity to see the call.

Close's own MCP server

• ContextGate now connects to Close's own MCP server by default: in Add Connection, search for Close and sign in with your Close account. There's nothing to copy or paste.
• ContextGate's app connector for Close is still there, under Ways to connect on the same card.
• Whichever way you connect, your tool switches, policies and Activity work the same.

What you get with Close and ContextGate

• Your AI apps can use CloseClaude, Cursor, ChatGPT and other AI apps reach Close through the one ContextGate connection you add to them.
• You choose which tools they can useSwitch off any Close tool you don't want used. It's hidden from your AI apps and refused if called.
• Every call is checked and recordedYour policies check each call (for example, personal data is hidden and secrets are blocked), and Activity keeps a record of it.

ContextGate sees only the tool calls that go through it, not your AI app's built-in tools or your chats.

Close tools

Examples of what your AI apps can do in Close. You'll see the exact list of tools after you connect it.

• create_taskThis tool creates a new task in close.com. tasks are used to track to-do items and can be associated with leads. the tool will create a task with the specified parameters using the provided text, due date, and is complete flags.
• create_leadThis tool creates a new lead in close crm. it allows users to create a lead with basic company information and optional contact details, including company name, description, website url, lead status, contacts, and addresses. it operates by sending a request to the api endpoint /lead/ on the close crm platform.
• close_create_smsThis tool creates a new sms message in close. the tool allows sending immediate sms messages or logging received sms messages using the provided phone numbers and message content. it includes parameters such as local phone, remote phone, text, status, and source.
• create_callCreates a new call record in close.com. this tool allows you to log both inbound and outbound calls associated with a lead, supporting parameters such as lead id, direction, and optional support for contact id, phone, duration, note, recording url, and user id.
• delete_callThis tool allows you to delete a specific call activity in close.com. it is useful for removing incorrectly logged calls or cleaning up call records. the action deletes a call activity using its unique call id and cannot be undone.
• get_noteThis tool retrieves a list of note activities from close. it allows users to fetch notes with optional filtering parameters, including filtering by lead id, user id, and date ranges. the tool returns details such as note content, creation and update dates, and any associated attachments.