Bring your tickets, conversations and knowledge base into the AI assistant you already use.
A useful AI assistant needs the right context. With HEDESU MCP, your assistant can find relevant tickets, read discussions, consult your knowledge base and help you take the next step—all through a conversation.
Ask it to catch you up on a ticket, turn meeting notes into a new request, or prepare a help article from a resolved issue. HEDESU provides the information and supported actions; your assistant helps you work with them.
Model Context Protocol, or MCP, is a standard that lets AI assistants connect to other applications.
For HEDESU, it means your assistant can work with information your account is allowed to access, without you copying entire conversations or articles into a chat.
| Your goal | How your assistant can help |
|---|---|
| Understand a ticket | Read its details and discussion, then summarize the situation |
| Prepare a team handover | Identify decisions, unanswered questions and suggested next steps |
| Turn notes into work | Create a ticket with a clear title, description and supported fields |
| Keep colleagues informed | Add an internal note to a ticket |
| Find an answer | Search accessible tickets, contacts and knowledge base articles |
| Improve your documentation | Create drafts, update articles and organize KB categories |
You describe the outcome. Your assistant uses the available HEDESU tools to help get there.
You’ll need an active HEDESU staff account and an AI client that supports remote MCP connections with OAuth sign-in.
In HEDESU, open your Profile and go to AI connections. Copy the MCP URL shown there—it already contains the correct address for your organization.
Your MCP URL will look like this:
https://YOUR-HEDESU-DOMAIN/api/mcp
Keep the copied URL ready to paste into your AI assistant in the next step.
Open your assistant’s MCP or connector settings. Add a remote connection named HEDESU, then paste the URL.
If asked for a transport type, choose Streamable HTTP.
Follow the connection’s sign-in prompt. HEDESU opens in your browser so you can sign in and review the requested access.
Approve the connection to continue. Enter your password only on the HEDESU sign-in page—not in the AI conversation.
Check my HEDESU connection, show the spaces I can access, and explain what you can help me do.
Your assistant should identify the available spaces and capabilities. You’re ready to begin.
Add HEDESU through the MCP server settings, using your URL and the Streamable HTTP transport. Complete authentication when prompted.
If you use the Codex CLI, you can add the connection with:
codex mcp add hedesu --url https://YOUR-HEDESU-DOMAIN/api/mcp
If sign-in does not start automatically:
codex mcp login hedesu
Follow the browser authorization flow. See the official OpenAI MCP instructions for your client’s current settings.
Open Claude’s Connectors settings and add a custom remote connector. Name it HEDESU, enter your MCP URL and complete the sign-in flow.
Enable the connector in the conversation where you want to use it.
For managed Team or Enterprise accounts, an authorized administrator may need to add the connector before members can connect their own accounts. See Claude’s custom connector guide for the current steps.
Your assistant works within your HEDESU account’s permissions. Connecting it does not grant access to additional spaces, private tickets or restricted articles.
For tasks where you want to review changes first, say so:
Research this first and show me your recommendation. Wait for my approval before changing anything.
You can manage or disconnect your authorizations from AI connections in your HEDESU profile.