What does connecting Claude Desktop actually do?
Connect your existing agent to the same private workspace you use in the Montage app. The remote server handles research and workspace tools; your client handles its own conversation and authentication controls. Start with the setup specific to your client, then prove access with a real, read-only tool response.
https://app.montages.co/mcpUse a remote custom connector
In a Claude account and client version that offers remote custom connectors, add Montage using its HTTPS server URL. Remote connector availability and administration depend on the Claude plan and organization. Do not paste this remote URL into a local stdio command field: those are different transports.
Complete Montage consent in the browser
Follow the connector’s authentication prompt. Sign in to Montage if necessary, confirm the agent name and selected account, and review permissions before approving. An existing Montage session can remove the extra sign-in step, but opening the settings panel alone never connects the account.
Enable the connector for the conversation
Return to Claude and make the connector available to the conversation using the client’s current tool controls. Ask it to call signals_status and describe real workspace coverage. If a workspace policy blocks custom connectors, an administrator must make that decision; Montage cannot bypass it.
Keep the boundaries clear.
- No API key to copy for normal OAuth-capable clients.
- The agent uses your workspace’s plan, limits and research credit.
- Client support and UI labels vary; do not promise an app-store integration.
Start with a read-only check: ask your agent to report actual source coverage before collecting records or exporting an audience.
Primary references
Documentation reviewed 2026-11-13. Product capabilities, client availability and plans can change. Third-party marks identify their products, not an affiliation.