Close MCP Server

Close’s MCP server is officially supported across the Claude ecosystem. Watch this video to learn more about connecting Claude to Close and see some example use cases:

1. Navigate to Settings by clicking your name in the bottom left sidebar on web or desktop.
2. In the Settings sidebar, select Connectors, then Organization connectors.
3. Find and select the Close connector, then click Connect.
4. Grant access to your desired Close organization and scopes.
5. Make sure to enable the tools in any new chats.

1. In your terminal, add the MCP server:

$
claude mcp add --scope user --transport http close https://mcp.close.com/mcp 

If you prefer to use API key instead of OAuth, you can specify it in headers:

$
export CLOSE_API_KEY=YOUR_API_KEY
$
$
claude mcp add --scope user --transport http close https://mcp.close.com/mcp \
>
  --header "Close-API-Key: ${CLOSE_API_KEY}" \
>
  --header "Close-Scope: mcp.read"

Optionally, change mcp.read to mcp.write_safe or mcp.write_destructive to increase the scope.

2. Launch a Claude Code session with claude and type /mcp to verify Close MCP was set up.

See the Claude Code MCP Docs for more information on using MCP servers with Claude Code.

On any ChatGPT paid plan, you can give ChatGPT access to Close by adding a custom Connector:

1. Navigate to your Connectors settings in ChatGPT.
2. If you are not already in Developer Mode, scroll down to Advanced settings and toggle on Developer Mode.
3. Click Create at the top right.
4. Fill out the New Connector form with the following details:
   • Icon: Use the Close logo icon
   • Name: Close (or the name of your Close organization)
   • Description: Connects to the Close MCP Server
   • MCP Server URL: https://mcp.close.com/mcp
   • Authentication: OAuth
5. Click Create and ChatGPT should take you to Close to select your organization and desired scopes.
6. Ask ChatGPT to “List all available tools in the Close connector” to test the tool is connected.

You can use n8n’s “AI Agent” node to set up a chatbot with read access to your Close Organization.

1. Create a new Workflow and add Chat Trigger as your first step.

2. Add an AI Agent node as your second step. The AI Agent node has three components:
   • Chat Model — The LLM of your choice (n8n supports all major LLM providers)
   • Memory — Allows a model to remember and reference past interactions. While not required, we recommend n8n’s “Simple Memory,” which requires no setup.
   • Tool — This is where you will connect to Close’s MCP server.
3. Connect the Chat Model and Memory options of your choice, and then add the MCP Client Tool node under Tool.
4. For the MCP Client Tool node, use the following configuration:
   • Endpoint: https://mcp.close.com/mcp
   • Server Transport: HTTP Streamable
   • Authentication: Header Auth
   • Create a new Header Auth Credential in your n8n account with:
     • Name: Close-API-Key
     • Value: Your Close API Key
   • Tools to Include: All

5. Start chatting with your new AI Agent in the “Chat” window at the bottom left of the Workflow Editor.

1. Click: Add Close to Cursor, or manually add the server URL https://mcp.close.com/mcp in Cursor’s MCP Tools settings.

2. You should see the Close MCP Server listed in MCP Tools in the Cursor desktop app. Click Install.

3. The connection will be in the “Needs authentication” status. Click Connect and allow the Cursor app to direct you to the Close OAuth Authentication Page.

4. Select the correct Close Organization and scope for your use case and click Allow.

5. Return to the Cursor app. You should see that the connection is now “Loading Tools” or “Enabled”.

Step 1: Configure the MCP server

Add the following to your settings.json:

1
{
2
  "mcp": {
3
    "servers": {
4
      "close": {
5
        "url": "https://mcp.close.com/mcp",
6
        "type": "http",
7
        "headers": {
8
          "Close-API-Key": "${input:close-api-key}",
9
          "Close-Scope": "mcp.read"
10
        }
11
      }
12
    },
13
    "inputs": [
14
      {
15
        "id": "close-api-key",
16
        "description": "Enter your Close API key",
17
        "type": "promptString"
18
      }
19
    ]
20
  }
21
}

This will add a read-only MCP server to your VS Code. You can change Close-Scope to mcp.write_safe or mcp.write_destructive to increase the scope. Alternatively, you can add the snippet to your mcp.json file for workspace-level server access.

Step 2: Start the server

Use the command palette (Cmd+Shift+P on Mac, Ctrl+Shift+P on Windows) to list the MCP servers, select close, and click “Start Server.” Enter your Close API Key when prompted.

If the server is not in the list, use the command palette to “Reload Window.” The console will confirm that the server is connected:

Step 3: Start using the server

Open Copilot in the sidebar (Cmd+Shift+I on Mac, Ctrl+Alt+I on Windows) and switch to agent mode. You can click the tool icon to list the available tools. Ask Chat what Close Organization you are working in and you should see that it uses the server to return organization information.

Any MCP client that supports HTTP Streamable transport can connect to Close’s MCP server at https://mcp.close.com/mcp. Use either OAuth 2.0 or API key authentication via the Close-API-Key and Close-Scope headers as described above.