Hosted MCP server/Productivity

Timeglass AI MCP server

Provider setup path

Timeglass AI MCP connects AI timesheets and searchable work history to an assistant. Users can review time entries, explore meeting and project context and update work records in plain language. Each connector has its own URL: create one in Settings > MCP Connector, choosing Whole workspace or a client, then copy that connector’s URL. A client connector is read-only; a whole-workspace connector can add, edit, hide or delete time entries and create or update projects. On desktop, the path is Settings > Help > MCP Connection.

OAuth Server not checked yet Reviewed 2026-11-16
About

Where it fits

Consultants and teams that want timesheets and work history available to an assistant.

  • Review time entries from connected timesheets.
  • Explore meeting and project context for a work record.
  • Update work records with a whole-workspace connector.

A remote MCP server advertises tools to your client. The provider controls the tools, the data they can reach, and the permissions they need. Read the provider's docs before you use it with private data.

Install

Create a Timeglass connector

Each connector has its own URL. A whole-workspace connector can add, edit, hide or delete time entries and create or update projects; a client connector is read-only. CSV import is limited to supported columns.

  1. Create the connector

    Open Settings > MCP Connector in Timeglass. Keep Whole workspace or add the client you want, then copy that connector’s URL.

  2. Add the URL to your client

    Paste the per-connector URL into the MCP client. On desktop, the path is Settings > Help > MCP Connection.

  3. Choose the scope

    Use a client connector for read-only access. Use whole-workspace only when the assistant should change time entries and projects.

This is a local install path. Install and run it first, then add the local command or URL to OpenCode, VS Code, or another compatible client. The provider controls the package, required keys, and runtime.

Troubleshooting

Common failure modes

These are the problems to check first. If the provider changes its endpoint or authentication flow, use its documentation as the source of truth.

  • The sign-in window closes without returning. Allow pop-ups and finish the provider login in the same browser.
  • The server connects but its tools are missing. Remove it, add it again, and approve the scopes the provider lists.
  • Your client does not support Streamable HTTP. Use a client that does, and confirm the provider's current endpoint and transport in its docs.
Safety

Before you connect

Remote means provider access
  • The provider can see the requests and data your agent sends through the server.
  • Review OAuth scopes and API-key permissions. Start read-only if the provider offers it.
  • Use project scope for repository-specific servers; use global scope for personal tools.
  • Remove the server and revoke its token when you stop using it.
Review path

Check the connection before a real task

These guides cover the decisions that a provider description cannot answer: endpoint ownership, scopes, tool access, and a read-only test.

Reference

Provider documentation

Setup requirements, available tools, and rate limits live with the provider. Use the source link as the authority for this server.

Timeglass AI documentationhttps://timeglass.ai/help/ai-assistant/connect-ai-assistant