Skip to main content

How to Connect eRS to Your AI Assistant

  • Updated
Table of Contents

MCP stands for Model Context Protocol, an open standard that lets AI assistants talk to external tools securely. The eRS MCP Server is eRS's implementation of that standard: a thin layer that translates a natural-language request into an eRS action and returns the result. It does not replace the eRS web application or store data separately.

The eRS MCP Server connects eResource Scheduler to AI assistants like Claude, ChatGPT, Microsoft Copilot Studio, Cursor, and more. Once connected, an AI assistant can search resources, check availability, log timesheets, or run a utilization report directly from a chat window, without opening eRS.

Two things determine what the assistant can do: 

  • The tools registered on the eRS MCP Server.
  • The permissions on the authenticated eRS account. 

If an action isn't possible in eRS, it isn't possible through the assistant either.

Before You Start

Before setting up the integration, make sure the following are in place:

  • An active eRS account with a role that has access to the required data
  • MCP enabled for that eRS account by an eRS admin (see Admin Setup below)
  • An MCP-compatible AI assistant or development tool (Claude Desktop, Microsoft Copilot Studio, Cursor, ChatGPT, Google Antigravity, or any client that supports remote Streamable HTTPS and OAuth)
  • The eRS MCP Server endpoint URL: https://app.eresourcescheduler.cloud/mcp

Important: eRS passwords, API keys, and access tokens should never be pasted into a client configuration file. Authentication happens through eRS OAuth in the browser, not through pasted credentials.

Admin Setup

An eRS admin needs to enable MCP before anyone in the organization can connect an AI assistant.

  1. Click the profile icon in the top-right corner and select Administration.

    1.png
  2. Under Integration, select MCP Server.
  3. Toggle Enabled to turn on the MCP Server.

  4. Use the MCP URL to get MCP connected on supported AI clients.

    2 (1).png

Connecting An AI Assistant 

Setup always comes down to two steps. Add the eRS MCP link to the assistant's settings, then sign in with an eRS account.


Claude

To set up the eRS MCP Server in Claude:

  1. Open Claude and click on the + button in the chatbox. 
  2. Click on Add Connector > Add custom connector.
    claude 1.png
  3. Add the name for the connector and use the eRS MCP Server URL.
  4. Click Continue and keep the Authentication & OAuth Client settings to default only.
    claude2.1.png

  5. Click Add.

    claude 3.png
  6. Complete the eRS authentication flow when prompted.

  7. Once authenticated, the eRS MCP connector is available in Claude.

    claude 4.png

 

ChatGPT

ChatGPT Desktop

To set up the eRS MCP Server in ChatGPT Desktop: 

  1. Open Settings in ChatGPT.
  2. Go to Plugins.
  3. Click Add > Add MCP server.
    gpt 1.png
     
  4. Name it "eResource Scheduler" and select Streamable HTTP as the transport type.
  5. Enter the MCP Server URL: https://app.eresourcescheduler.cloud/mcp and click Save (other fields are optional and can be left as they are).
    gpt 2.png
     
  6. Go to the MCPs tab and click Authenticate.

  7. Complete the eRS authentication flow.

    gpt 3.png
  8. Confirm the eRS MCP server is active.

ChatGPT Web 

To set up the eRS MCP Server in ChatGPT Web: 

  1. Go to Settings > Security and Login, enable Developer Mode, then close Settings.

    cw1.1.png

  2. Click Plugins, then click the '+' button. Next, click on Create app. 

    02.jpg

  3. Click on Create MCP App. 

    chatgpt 03.jpg
  4. Enter the tool name and the MCP server URL in the Connection field, agree to the security notice, and click Create.

    04.jpg
     
  5. Click "Sign in with eResource Scheduler" and complete the authentication.

    05.jpg
     
  6. eRS MCP is now connected.

    06.jpg
     
  7. To start using it, open a new chat, click '+', and select eResource Scheduler from the list.

    07.jpg


Microsoft Copilot Studio

To set up the eRS MCP Server in Microsoft Copilot Studio:

Prerequisites: 

  • A Microsoft Copilot Studio account
  • Generative orchestration enabled in the agent

Microsoft Copilot Studio (Standard Agent)

Note: These steps are based on the new-experience toggle being off. For the new UI, jump to Microsoft Copilot Studio (New UI) below.

  1. Open Microsoft Copilot Studio and click on Create blank agent. 

    mco1.png

  2. Wait for the agent to finish provisioning (status shows "Ready"), then go to the Tools tab.

    mco3.png

  3. Click Add tool > Add new MCP. 

    mco4.png

  4. Enter the server name and server URL, and set Authentication to OAuth 2.0 with dynamic discovery and click Create. 

    mco5.1.png

  5. Click the "No connection" dropdown and create a new connection. Next, click on "Add".

    mco6.1.png
  6. Test the connection in the testing pane on the right by entering a query, for example: "List Project Apollo's details."
  7. Click Open connection manager and create a connection. Once the connection is created, click "Retry." The agent should now be able to retrieve eRS information.
    mco7.png

  8. Publish the agent and share it with your team to make it available across the organization, including Teams, Microsoft 365 Copilot, and other Copilot surfaces. 

    mco8.png

Microsoft Copilot Studio (New UI)

To set up the eRS MCP Server in Microsoft Copilot Studio using the new UI:

  1. Go to Agents > Create your first agent or Create agent.

    nui1.png

  2. Enter the title and description, then click Tools.

    nui2.png

  3. Click Add > Model Context Protocol (MCP).

    nui3.png

  4. Enter the name, description, and URL. Select OAuth 2.0 as the authentication type and Dynamic (with discovery) as the configuration type, then click Add. 

    nui4.png

  5. Click the "Not connected" dropdown and select Create new connection.

    nui5.png

  6. Click Create and confirm the connection shows as connected.

    nui6.png

  7. Go to Preview and test it with a sample prompt, for example: "List Project Apollo's details."

    nui7.png
  8. Add the channels to publish to, such as Teams and Microsoft 365.

  9. Publish the agent and share it with your team to make it available across the organization, including Teams, Microsoft 365 Copilot, and other Copilot surfaces. 

    08 & 09.png


Cursor

To set up the eRS MCP Server in Cursor:

  1. Open Cursor > Settings > Customize.

    cursor 1.png

  2. Click the MCPs tab > New button, then add the URL and save it. 

    {
  "mcpServers": {
    "eResource Scheduler MCP": {
      "url": "https://app.eresourcescheduler.cloud/mcp"
    }
  }
}
    cursor 2.png

    Once saved, the entry looks like this:

    cw3.png

  3. Find the eResource Scheduler and click Authenticate.

    cursor4.1.png
  4. Complete the eResource Scheduler authentication flow in the browser.
  5. Confirm the eResource Scheduler shows as connected.
    cursor 5.1.png

 

GitHub Copilot

To set up the eRS MCP Server in GitHub Copilot: 

  1. Open Settings.

  2. Select Customize, then Go to Customize.

    git1.png
  3. Select Add.
  4. Select MCP server.
    git2.png
  5. Enter the server name and select HTTP as the type.
  6. Add the following URL: https://app.eresourcescheduler.cloud/mcp and click on 'Add server'.
    git3.1.png

  7. Go to the MCP tab in Customize, find it under Installed, and complete the authentication process.

    git4.png

  8. Confirm the authentication process is complete.

    git5.png

 

Google Antigravity

To set up the eRS MCP Server in Google Antigravity: 

  1. Open Settings and go to Customizations.
  2. Select MCP Server, then open the MCP configuration file.
    gravity 1.png
  3. Add this configuration below:
{
  "mcpServers": {
    "eResource-Scheduler": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://app.eresourcescheduler.cloud/mcp"
      ]
    }
  }
}
  1. Save the configuration and authenticate with eRS when prompted.

  2. Confirm the eRS MCP Server is authenticated. The eRS tools should now be visible.

    gravity 2.png

Other MCP-Compatible Clients

Most MCP-compatible assistants and dev tools can connect to eRS using standard settings:

  • Transport: Streamable HTTP
  • Server URL: https://app.eresourcescheduler.cloud/mcp
  • Authentication: OAuth

If the client requires mcp-remote, use:

  • Command: npx
  • Arguments: -y mcp-remote https://app.eresourcescheduler.cloud/mcp
  • Environment: None

For the full list of available tools and prompting best practices, see 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.