The eResource Scheduler MCP server lets you work with your eRS data from the ChatGPT desktop app. Setup takes about 5 minutes: an eRS admin enables the MCP server once, then each user adds eRS as an MCP server in their own ChatGPT desktop app.
Before You Start
You will need:
- An eRS administrator to turn on the MCP server (Part A). This is done once per account.
- Your own eRS login. ChatGPT signs in as you, so it can only see and do what your eRS access rights allow.
- The ChatGPT desktop app, with access to Plugins in Settings to add an MCP server.
Watch the Video
Prefer to watch? This 2-minute video walks through the full setup in the ChatGPT desktop app. Prefer written steps? Follow Part A and Part B below.
Part A: Enable the MCP Server in eResource Scheduler (Admin, One Time)
Skip to Part B if your admin has already enabled it and shared the endpoint URL.
Step 1. Open Administration
Log in to eResource Scheduler. Click your name in the top-right corner, then click Administration.
Step 2. Turn on the MCP Server
In the left menu, under INTEGRATION, click MCP Server. Switch the toggle at the top right from Disabled to Enabled. By enabling it, you agree to the MCP Server terms in the Terms of Service.
Step 3. Copy the endpoint URL
Once enabled, the page shows the Endpoint URL: https://app.eresourcescheduler.cloud/mcp. Click the copy icon next to it. Share this URL with anyone in your team who will connect the ChatGPT desktop app.
Part B: Add eResource Scheduler to the ChatGPT Desktop App (Each User)
Step 1. Add an MCP server
Open the ChatGPT desktop app and go to Settings. Click Plugins, then click Add and select Add MCP server.
Step 2. Enter the eRS details
Name it eResource Scheduler MCP and select Streamable HTTP as the type. Enter the server URL https://app.eresourcescheduler.cloud/mcp and click Save. The other fields are optional and can be left as they are.
Step 3. Authenticate
Go to the MCPs tab. Next to eresource_scheduler_mcp, click Authenticate.
Step 4. Sign in to eRS and confirm the connection
The eRS login page opens in your browser. Enter your eRS Login ID and password and click Login, or click Single Sign On if your company uses SSO.
Back in ChatGPT, check that eresource_scheduler_mcp is switched on in the MCPs list.
Start Using eRS in ChatGPT
Open a new chat and ask about your schedule in plain language. Mentioning "eResource Scheduler" in your first request helps ChatGPT pick the right plugin. Some prompts to try:
- "Using eResource Scheduler, show me who is booked on Project B next week."
- "What is the team's utilization this month by primary role?"
- "Which resources are free for 3 days next week?"
- "Book Grace Jonas on Project D at 50% from 5 to 9 October."
- "List timesheets waiting for my approval."
Learn More
Once connected, use these guides to see what you can ask:
- Ask AI Assistant About Your Reports
- Ask AI Assistant About Your Resources
- Ask AI Assistant About Your Projects
- Ask AI Assistant About Your Schedule
- Ask AI Assistant About Rates
- Ask AI Assistant About Your Timesheets
- eRS MCP Server: Tools & Prompting Guide
Troubleshooting
| Issue | What to check |
|---|---|
| Authentication failed | Confirm sign-in used an active eRS account, and that the OAuth flow completed fully in the browser without being closed early. |
| Connection failed | Confirm the endpoint URL is exactly https://app.eresourcescheduler.cloud/mcp, including the /mcp path, and that the client supports remote Streamable HTTPS servers. |
| Tools not appearing | Restart the AI client after saving the configuration. Some clients only load MCP tools on startup. |
| Assistant says it can't perform an action | Check the eRS role's permissions for that entity. The MCP server only allows what the account is permitted to do in eRS. |
| Assistant says MCP is disabled | Check with the eRS admin on whether MCP has been enabled. |
Note: Admin-related settings, such as Resource, Project, Booking, Requirement, and Timesheet profiles, along with calendar changes and user rights, can take up to 10 minutes to reflect through the eRS MCP Server. eRS also doesn't control how a connected AI client stores or uses retrieved data, so it's worth checking that client's own data retention and training settings wherever this matters to the organization.