Client setup guide

Follow the instructions for your AI client to connect it to the OpenLM MCP Connector.

Before you begin

Before you set up your AI client, verify these prerequisites:

• An active OpenLM account with access to a cloud-hosted tenant (US or EU).
• A paid AI subscription, such as Claude Pro, ChatGPT Plus, or equivalent. Free-tier plans do not support custom MCP connectors.
• Your environment URL. Identify the correct OpenLM MCP Connector URL for your region from the following table.

Environment	OpenLM MCP Connector URL
Prod US	https://cloud-us.openlm.com/mcp
Prod EU	https://cloud-eu.openlm.com/mcp

note

Replace the OpenLM MCP Connector URL in the configurations that follow with the URL that corresponds to your target environment.

Cursor

Desktop app

1. Download and install Cursor from the official website.
2. Open Cursor. Go to Cursor Settings → Tools and MCP.
3. Select Add a custom MCP server. In the mcp.json file that opens, paste the following JSON configuration:

{
  "mcpServers": {
    "openlm-reporting": {
      "url": "https://cloud-us.openlm.com/mcp"
    }
  }
}

4. After successful login, the OpenLM MCP Connector name and the total number of available tools appear.
5. Press Ctrl + L to start a new chat and begin querying.

Windsurf

Desktop app

1. Download and install Windsurf from the official website.
2. Open Windsurf. Go to Windsurf Settings → Open MCP Marketplace.
3. Select Add Custom MCP. In the mcp_config.json file that opens, paste the following JSON configuration:

{
  "mcpServers": {
    "openlm-reporting": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://cloud-us.openlm.com/mcp",
        "9877"
      ]
    }
  }
}

4. After successful login, the OpenLM MCP Connector name and tool count appear in the MCP Marketplace.
5. Open the chat panel and start querying.

LibreChat

Web app

1. Set up LibreChat from GitHub and open it in your browser.
2. On the left side panel, go to MCP Settings.
3. Select the + icon to add a new MCP server.
4. Provide a name for the OpenLM MCP Connector and enter the OpenLM MCP Connector URL for your environment.
5. Select Streamable HTTP as the transport type, check I trust the application, and select Create.
6. You are redirected to the browser for authentication. After successful login, the OpenLM MCP Connector is connected.

Gemini CLI

CLI

1. Install Gemini CLI globally by running:

npm install -g @google/gemini-cli@latest

2. Run gemini in your terminal to initialize it for the first time.
3. Open the settings file at ~/.gemini/settings.json and paste the following configuration:

{
  "mcpServers": {
    "openlm-reporting": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://cloud-us.openlm.com/mcp",
        "9877"
      ],
      "timeout": 30000
    }
  },
  "security": {
    "auth": {
      "selectedType": "oauth-personal"
    }
  }
}

4. Save the file and run gemini again. You see openlm-reporting is connected in the terminal confirming the connection.
5. Start querying tenant-specific data directly from the Gemini CLI terminal.

Claude Code

CLI

1. Open your terminal and run the following command to add the OpenLM MCP Connector:

 claude mcp add --transport http openlm-reporting https://cloud-us.openlm.com/mcp

2. After successful authentication, the OpenLM MCP Connector is connected and ready to use.
3. Start querying tenant-specific reporting data directly from Claude Code.

ChatGPT

Web app

note

Developer Mode must be turned on in ChatGPT settings to access the Create Apps option.

1. Open ChatGPT in your browser and sign in to your account.
2. Go to Settings → Apps → Create Apps.
3. Provide a name for the OpenLM MCP Connector and paste the OpenLM MCP Connector URL for your environment.
4. Select OAuth as the authorization type, then check the confirmation checkbox and select Create.
5. You are redirected to the browser for authentication. After successful login, the OpenLM MCP Connector is connected.
6. Start a new chat, select the + icon, go to More Options, and select the OpenLM MCP Connector to begin querying.

Once connected, select the + icon and select the OpenLM MCP Connector. It will appear beside the + icon, and you can begin querying.

Claude.ai

Web app

1. Open claude.ai in your browser and sign in to your account.
2. Select your profile icon and go to Settings → Connectors.
3. Select Add custom connector.
4. Provide a name for the OpenLM MCP Connector and paste the OpenLM MCP Connector URL for your environment.
5. You are redirected to the browser for authentication. After successful login, the OpenLM MCP Connector is connected as a custom connector.
6. The OpenLM MCP Connector is available as a connector and can be used directly in any Claude.ai conversation.

tip

Before you can query, you need to select a connector. In the chat input area, select Connectors, select the OpenLM MCP Connector, and enter your question.

Grok

Web app

1. Open grok.com/connectors in your browser and sign in to your account. The Skills and Connectors page opens on the Connectors tab.
2. Select New Connector.
3. In the New Connector dialog, select Custom to add your own custom connector.
4. In the Custom Connector dialog, provide a name for the OpenLM MCP Connector and enter the OpenLM MCP Connector URL for your environment.
5. Select Add Connector.
6. The OpenLM login page opens. Sign in with your OpenLM credentials to authenticate. After successful login, the OpenLM MCP Connector appears under Installed on the Skills and Connectors page.

tip

Before you can query, you need to turn the connector on in the chat. In the Grok chat window, select the + icon, go to Connectors, and toggle the OpenLM MCP Connector on. Only then are the OpenLM tools available in your chat.

Microsoft Copilot Studio

Web app

Microsoft Copilot connects through Copilot Studio, where you add the OpenLM MCP Connector as a tool of a custom agent. This takes a few more steps than the chat clients, but the flow is straightforward.

Access Copilot Studio and create an agent

1. Go to copilotstudio.microsoft.com and sign in with your Microsoft work account.
2. Confirm that the correct Environment for your organization is selected in the top-right corner.
3. Create a new agent, or open an existing one, and give it a name. For example, openlm-mcp.

Add the OpenLM MCP Connector as a tool

4. Open your agent and go to the Tools tab in the top navigation.
5. Select + Add a tool, then select + New tool to register a new MCP server rather than picking a pre-built one.
6. Select Model Context Protocol as the tool type.
7. Enter the MCP server details:
   • Server name: a name for the connector. For example, openlm-mcp.
   • Server description: a short description of what the server does.
   • Server URL: the OpenLM MCP Connector URL for your environment. The connector uses the Streamable HTTP transport.
   • Authentication: select OAuth 2.0, with the type Dynamic discovery.
8. Select Create. This registers the OpenLM MCP Connector and creates a connection.
9. The OpenLM login page opens. Sign in with your OpenLM credentials and authorize the connection.

Enable and verify

10. The new tool appears in the Tools list under Model Context Protocol. Make sure its Enabled toggle is set to On.
11. If you created the tool outside your agent, open the agent, go to its Tools tab, and add the newly created tool to the agent.

Test the agent

12. Select Test in the top-right corner to open the Test your agent panel.
13. In the chat box, type a prompt that uses the OpenLM tools. For example: "Show me license usage for the last month" or "List available OpenLM tools."
14. The agent calls the OpenLM MCP Connector and returns the results in the chat. Confirm that the tools respond correctly.

warning

The MCP tool must be Enabled and the connection authenticated. Otherwise, the agent cannot call the OpenLM tools.

What else you can do in Copilot Studio

Unlike chat clients, Copilot Studio is a full agent-building platform. After you connect the OpenLM MCP Connector, you can:

Feature	What it lets you do
Test	Live-test the agent's real responses against the OpenLM tools in the built-in chat panel before publishing.
Evaluation	Systematically evaluate the agent's answer quality and accuracy across multiple test cases.
Agents	Build multiple specialized agents, each with its own instructions and tools.
Topics	Define conversational flows and triggers that guide the agent's behavior for specific user intents.
Flows (Power Automate)	Build workflows that combine the OpenLM tools with other actions, such as sending email or triggering automations.
Knowledge	Add knowledge sources, such as documents or websites, so the agent can answer beyond the OpenLM tool data.
Channels	Publish the agent to Microsoft Teams, a website, Copilot chat, or other channels, giving end users a polished chat interface without any code.
Monitor	Track usage, conversations, and performance analytics of the agent.
Publish	Push the agent live so your team or organization can use it.

This turns the OpenLM MCP Connector into a ready-made, branded chat experience that can combine your license data with automated workflows and additional data sources.

GitHub Copilot (VS Code)

Desktop app

GitHub Copilot reads MCP servers from a configuration file in the project.

1. In VS Code, open any project folder. In the project root, create a folder named .vscode if it doesn't already exist.
2. Inside .vscode, create a file named mcp.json and paste the following configuration, entering a name for the server and the OpenLM MCP Connector URL for your environment:

{
  "servers": {
    "openlm-mcp-copilot": {
      "type": "http",
      "url": "https://cloud-us.openlm.com/mcp"
    }
  }
}

3. Open the Command Palette (Ctrl+Shift+P) and select MCP: List Servers.
4. Select your server, for example openlm-mcp-copilot, and select Start Server.
5. The OpenLM login page opens. Sign in with your OpenLM credentials. After successful login, the server connects and the tools are discovered.
6. Open GitHub Copilot Chat and set the mode dropdown at the bottom of the chat box to Agent. Tools work only in Agent mode.

tip

In the Copilot chat box, select the tools icon and make sure the OpenLM MCP Connector's tools are toggled on. Only then are the OpenLM tools available in your chat.

Cline

Desktop app

Cline is a VS Code extension that reads MCP servers from its own settings file.

1. In VS Code, install the Cline extension from the Extensions marketplace.
2. Open Cline and select the MCP Servers icon in the top toolbar.
3. Go to the Configure tab and select Configure MCP Servers. The cline_mcp_settings.json file opens.
4. Paste the following configuration:

{
  "mcpServers": {
    "openlm-reporting": {
      "type": "streamableHttp",
      "url": "https://cloud-us.openlm.com/mcp"
    }
  }
}

5. Save the file. The OpenLM login page opens. If it does not open automatically, select Retry Connection.
6. Sign in with your OpenLM credentials. After successful login, the OpenLM MCP Connector and its tools appear in the MCP Servers list.

tip

You can also add the connector without editing JSON. On the MCP Servers panel, select the Remote Servers tab, enter a server name and the OpenLM MCP Connector URL for your environment, select the Streamable HTTP transport type, and select Add Server.

Codex

Desktop app

1. Download Codex from the official website and install it.
2. Complete the initial setup and sign in to your account.
3. Go to Settings → MCP servers, then select Add server.
4. Enter the server details:
   • Name: a name for the connector. For example, openlm-reporting.
   • Transport: select Streamable HTTP.
   • URL: the OpenLM MCP Connector URL for your environment.
5. Save the configuration, then restart Codex if you are prompted to.
6. Select Authenticate. The OpenLM login page opens. Sign in with your OpenLM credentials.
7. After successful authentication, the OpenLM MCP Connector is connected and its tools are available.

note

The same steps apply in the Codex IDE extension, which uses the same Settings → MCP servers panel.

Google Antigravity

Desktop app

Antigravity reads MCP servers from an mcp_config.json file.

1. Download and install Antigravity from the official website.
2. Open the MCP servers panel and choose the option to edit the configuration file directly. In the Antigravity IDE, select the … menu in the agent side panel and select MCP Servers.
3. In mcp_config.json, paste the following configuration:

{
  "mcpServers": {
    "openlm-reporting": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://cloud-us.openlm.com/mcp",
        "9880"
      ]
    }
  }
}

4. Save the file. The OpenLM login page opens. Sign in with your OpenLM credentials.
5. After successful login, the OpenLM MCP Connector and its tools appear in the MCP servers list.

note

The number after the URL (9880) is the local port that mcp-remote uses for the OAuth callback. If you run more than one MCP server through mcp-remote, give each one a different port so that they do not collide.

tip

Antigravity recommends keeping the number of enabled MCP tools small, around 50 across all your MCP servers, for best performance. The OpenLM MCP Connector exposes 19 tools, so you do not normally need to trim it. If you connect several MCP servers at once and need to reduce the count, add a disabledTools array to the OpenLM entry that lists the tool names to withhold from the model. See the tools and capabilities reference for the current tool names.