--- title: "Setting up MCP clients for the Docebo MCP server" slug: "setting-up-mcp-clients-for-the-docebo-mcp-server" updated: 2026-10-30T13:23:01Z published: 2026-10-30T13:23:01Z canonical: "developer.docebo.com/setting-up-mcp-clients-for-the-docebo-mcp-server" --- > ## Documentation Index > Fetch the complete documentation index at: https://developer.docebo.com/llms.txt > Use this file to discover all available pages before exploring further. # Setting up MCP clients for the Docebo MCP server ## Introduction The administrator of your external AI assistant must connect the Docebo MCP server. The steps below describe the setup process for the most common clients. Note that these interfaces change frequently. If the steps no longer match your client's current interface, refer to the client's official documentation, linked in each section below. Before proceeding: - Ensure that an OAuth2 application has been configured. See [Configuring OAuth interactive authentication for the Docebo MCP server](/v1/docs/configuring-oauth-interactive-authentication-for-the-docebo-mcp-server). - Ensure that the MCP server is enabled. See [Configuring Docebo MCP servers](/v1/docs/configuring-docebo-mcp-servers). - Copy the MCP server URL from the *Docebo MCP server* page. ## Connecting your MCP client ### ChatGPT For the official documentation, see [ChatGPT plugins (opens in a new tab)](https://help.openai.com/en/articles/11487775-connectors-in-chatgpt). 1. Log into ChatGPT with administrative or workspace owner privileges. 2. Open **Plugins**, click **Add** and select **Add custom MCP server**. 3. Configure the connection with the following details: - **Name:** Docebo (You can choose a name that best fits your organization. This name will be visible to final users, so we suggest using the same name they are used to seeing for your Docebo platform.) - **Description (optional):** a short description of what the plugin does. - **Connection:** select *Server URL* and enter the MCP Server URL: `https://[docebo-instance-name]/mcp/servers/[server-path]/http` - **Authentication:** OAuth 4. Expand **Advanced OAuth settings** and set: - **Registration method:** *User-Defined OAuth Client* - **Callback URL:** ChatGPT shows the Callback URL here. Copy it, go to your Docebo OAuth2 application, paste it into the *Redirect URIs* field, and save. - **OAuth client ID:** paste the Client ID from your OAuth2 application - **OAuth client secret:** paste the Client Secret from your OAuth2 application - **Token endpoint auth method:** select `client_secret_post`. - **Scopes:** disable the `api` scope - **OAuth endpoints:** - **Auth URL:** `https://[docebo-instance-name]/oauth2/authorize` - **Token URL:** `https://[docebo-instance-name]/oauth2/token` - **Registration URL:** leave this field empty - **Authorization server base:** `https://[docebo-instance-name]` - **Resource:** `https://[docebo-instance-name]` 5. Select **I understand and want to continue**. 6. Click **Create as a plugin**. 7. Enable the plugin for the target users. ### Claude For the official documentation, see [Claude (opens in a new tab)](https://support.claude.com/en/articles/11175166-getting-started-with-custom-connectors-using-remote-mcp). 1. Log into Claude with administrative privileges. 2. Navigate to **Organizational Settings > Connectors**. 3. Click **Add custom connector** at the bottom of the page. 4. Configure the connection: - **Name:** Docebo (You can choose a name that best fits your organization. This name will be visible to final users, so we suggest using the same name they are used to seeing for your Docebo platform.) - **Remote MCP Server URL:** `https://[docebo-instance-name]/mcp/servers/[server-path]/http` - **Client ID:** paste the Client ID from your OAuth2 application - **Client Secret:** paste the Client Secret from your OAuth2 application 5. Click **Add**. 6. Enable the connector for the target users. ### Microsoft Copilot (via Copilot Studio) For the official documentation, see [Microsoft Copilot Studio (opens in a new tab)](https://learn.microsoft.com/en-us/microsoft-copilot-studio/mcp-add-existing-server-to-agent). 1. Log into Microsoft Copilot Studio as an administrator or environment maker. 2. Select your desired agent, then navigate to the **Tools** section. 3. Click **Add a tool**, then select the **Model Context Protocol** filter tab. 4. Click **New tool** to add a new MCP server. 5. Provide the following details: - **Server Name:** Docebo (You can choose a name that best fits your organization. This name will be visible to final users, so we suggest using the same name they are used to seeing for your Docebo platform.) - **Server URL:** `https://[docebo-instance-name]/mcp/servers/[server-path]/http` - **Authentication:** select *OAuth 2.0*, type *Manual* - **Client ID:** paste the Client ID from your OAuth2 application - **Client Secret:** paste the Client Secret from your OAuth2 application - **Authorization URL:** `https://[docebo-instance-name]/oauth2/authorize` - **Token URL template:** `https://[docebo-instance-name]/oauth2/token` - **Refresh URL:** `https://[docebo-instance-name]/oauth2/token` - **Scopes:** (Leave this field empty) 6. Click **Create**. 7. Copilot Studio will generate a *Redirect URI*. Copy this URL, return to your Docebo OAuth2 app settings, paste it into the *Redirect URIs* field, and save. 8. Enable the connector for the target users. ### Gemini Enterprise The values below are always required. For the full step-by-step instructions, refer to Google's [Set up a custom MCP server documentation (opens in a new tab)](https://docs.cloud.google.com/gemini/enterprise/docs/connectors/custom-mcp-server/set-up-custom-mcp-server). When prompted, provide the following details: - **MCP Server URL:** `https://[docebo-instance-name]/mcp/servers/[server-path]/http` - **Authorization URL:** `https://[docebo-instance-name]/oauth2/authorize` - **Token URL:** `https://[docebo-instance-name]/oauth2/token` - **Client ID:** paste the Client ID from your OAuth2 application - **Client Secret:** paste the Client Secret from your OAuth2 application Once the data store is created, enable the Docebo tools for the target users as described in Google's documentation. ### Slack (Slackbot) Slack requires a Slack app to connect an MCP server. For the full step-by-step instructions, refer to Slack's [Connecting an MCP server to the Slackbot MCP Client documentation (opens in a new tab)](https://docs.slack.dev/ai/slackbot-mcp-client/). When prompted, provide the following details: - **MCP Server URL:** `https://[docebo-instance-name]/mcp/servers/[server-path]/http` - **Authorization URL:** `https://[docebo-instance-name]/oauth2/authorize` - **Token URL:** `https://[docebo-instance-name]/oauth2/token` - **Client ID:** paste the Client ID from your OAuth2 application - **Client Secret:** paste the Client Secret from your OAuth2 application Once the Slack app is configured and installed, users connect Docebo from Slackbot as described in Slack's documentation. ## Refreshing MCP server tools MCP clients store the list of tools when the connector is created. Refresh the tools in your client when: - A Docebo Superadmin added or removed tools on the custom MCP server in the MCP configurator. See [Configuring Docebo MCP servers](/v1/docs/configuring-docebo-mcp-servers). - An existing tool's inputs or outputs changed, for example after a Docebo release. Most clients provide a *Refresh* option for the administrator who created the connector. The location and label vary by client, so see your client's official documentation, linked in each section above.