Skip to main content

OpenLM MCP Connector FAQ and troubleshooting

To find answers about the OpenLM MCP Connector or to fix a connection problem, use the following sections.

Frequently asked questions​

The following questions cover what the OpenLM MCP Connector is, what it supports, and how it behaves.

What is the OpenLM MCP Connector?​

The OpenLM MCP Connector is a service that connects your AI assistant, such as Claude, ChatGPT, or Cursor, to your OpenLM license management data. It uses the Model Context Protocol (MCP) standard so that you can query reporting data in natural language.

Do I need a paid subscription to my AI client?​

Yes. Connecting the OpenLM MCP Connector requires a minimum paid subscription to your AI platform, such as Claude Pro, ChatGPT Plus, or an equivalent paid plan. Free-tier plans don't support adding custom MCP connectors or servers.

Which AI clients are supported?​

The OpenLM MCP Connector supports Claude Desktop, Claude.ai, Claude Code, Cursor, Windsurf, ChatGPT, Gemini CLI, LibreChat, Grok, Microsoft Copilot Studio, GitHub Copilot, Cline, Codex, and Google Antigravity. An AI platform that supports the MCP standard can integrate with the same connector URL.

Is the OpenLM MCP Connector available for on-premises deployments?​

No. The OpenLM MCP Connector is available only for OpenLM Platform (US and EU tenants). It isn't offered for on-premises deployments.

What data can I query?​

You can query any data available in the OpenLM reporting database for your tenant. This includes license usage, feature utilization, user and group analytics, historical trends, and optimization recommendations. For example prompts, see Tools and capabilities reference.

Can I generate charts and dashboards?​

Yes, but the level of visual output depends on your AI subscription tier. Higher-tier plans, such as Claude Pro or ChatGPT Plus, can generate interactive HTML dashboards, charts, and graphs. Basic paid plans return text-based responses and tables.

How accurate is the data?​

The OpenLM MCP Connector returns your actual reporting data from the OpenLM database. However, the AI assistant's interpretation and presentation of that data might contain errors. AI models can have up to 3% inaccuracy in data interpretation. Verify AI-generated insights, especially license optimization recommendations, against your OpenLM Platform BI reports and dashboards.

What authentication method does the connector use?​

The OpenLM MCP Connector uses OAuth authentication. When you connect for the first time, your browser opens the OpenLM sign-in page. After you sign in with your credentials, the connector establishes a secure session and scopes all queries to your organization's data.

Which URL do I use: US or EU?​

Use the URL that corresponds to the region where your OpenLM tenant is hosted. If you are unsure, contact your OpenLM administrator. The URLs are:

  • Prod US: https://cloud-us.openlm.com/mcp
  • Prod EU: https://cloud-eu.openlm.com/mcp

Can multiple people in my organization connect simultaneously?​

Yes. Each user authenticates independently with their own OpenLM credentials. All queries are scoped to your organization's tenant data, so multiple team members can use the OpenLM MCP Connector concurrently without conflicts.

Troubleshooting​

The following sections list fixes for common connection problems.

Why can't I add the OpenLM MCP Connector in my AI client?​

Check the following:

  • Verify that you have a paid subscription to your AI platform. Free plans don't support custom MCP connectors.
  • In ChatGPT, turn on Developer Mode in Settings before you create an app.
  • In Claude.ai, the Add custom connector option might be deactivated if your organization has restricted it. Contact your administrator.

Why does authentication fail or the sign-in page not appear?​

Check the following:

  • Allow pop-ups and redirects in your browser. The OAuth flow opens an OpenLM sign-in page in a new browser window or tab.
  • Clear your browser cookies and cache, then try the authentication process again.
  • Verify that you are using the correct OpenLM MCP Connector URL for your region (Prod US or Prod EU).
  • If you are behind a corporate firewall or VPN, confirm that access to the OpenLM MCP Connector URL is not blocked.
  • In Cline, if the sign-in page does not open after you save cline_mcp_settings.json, select Retry Connection on the MCP Servers panel.
  • In Codex, save the server configuration and restart the application, then select Authenticate to start the OAuth flow.

Why does the OpenLM MCP Connector return no data?​

Check the following:

  • Confirm that your OpenLM Platform account has the appropriate permissions to access reporting data.
  • Verify that your tenant has data available for the time range you are querying.
  • Try a query such as "Show me all active licenses" to verify basic connectivity.
  • If you use a development or QA URL, confirm that the environment has test data loaded.

Why are the tools not available in the chat?​

Check the following for your AI client:

  • In Grok, select the + icon in the chat window, select Connectors, and toggle the OpenLM MCP Connector on. The tools are available only after you turn on the connector in the chat.
  • In GitHub Copilot, set the chat mode to Agent. Tools work only in Agent mode. Also select the tools icon in the chat box and check that the tools of the OpenLM MCP Connector are toggled on.
  • In Microsoft Copilot Studio, check that the Enabled toggle of the MCP tool is set to On and that you added the tool to your agent.
  • In Claude.ai, select Connectors in the chat input area and select the OpenLM MCP Connector before you enter your question.
  • In Google Antigravity, check the OpenLM entry in mcp_config.json for a disabledTools array. The model can't call any tool listed there. Remove the tool from the array to make it available again.

Why does the connection time out?​

Check the following:

  • For Gemini CLI, increase the timeout value in your settings.json configuration. The default timeout of 30000 ms (30 seconds) might not be enough for complex queries.
  • For other clients, verify that your internet connection is stable and that the OpenLM MCP Connector URL is reachable.
  • Large queries or reports might take longer to process. Try narrowing the date range or simplifying your query.

Why does the AI client show incorrect or unexpected results?​

Check the following:

  • The AI model interprets your data and might occasionally misrepresent it. Cross-check results against your OpenLM dashboard.
  • Try rephrasing your query with more specific details, such as exact date ranges, product names, or departments.
  • Start a new conversation and try the same query again. Context from earlier in a conversation can sometimes influence results.

Why are charts or dashboards not generated?​

Check the following:

  • Visual output, including charts and HTML dashboards, requires a higher-tier AI subscription such as Claude Pro or ChatGPT Plus.
  • Request visual output in your prompt, for example Create a bar chart showing license usage by department.
  • If you use a lower-tier plan, the AI returns text-based summaries and tables instead of visual content.

Why does the npx command fail or mcp-remote not appear?​

Check the following:

  • Verify that you have Node.js and npm installed on your system. The npx command is included starting with npm 5.2.
  • Check that you have internet access so that npx can download the mcp-remote package.
  • Try running npm cache clean --force, then retry the npx command.
  • If you configured more than one MCP server through mcp-remote, verify that each one uses a different local callback port. The port is the number that follows the URL in the args array, such as 9877 for Windsurf and Gemini CLI or 9880 for Google Antigravity. Two servers sharing a port can't both complete the OAuth callback.

Get help​

If you can't resolve your issue with the preceding steps, contact the OpenLM Data Engineering team for assistance. Include the following information:

  • The AI client and version you are using
  • The OpenLM MCP Connector URL you are connecting to
  • The exact error message or unexpected behavior
  • Screenshots, if available

The documentation team might draft this page using a large language model. A technical writer reviews every page and verifies it against the product before publishing it. A human makes the final decision.