Cursor Integration

Cursor has first-class support for the Model Context Protocol (MCP). By connecting Kiomon, Cursor’s Composer and Chat can instantly query the documentation, GitHub issues, PRs, and notes you’ve been reading and saving — then write new learnings back as reviewable memory drafts.

Configure the MCP server

1. Open Cursor Settings (⌘ + , on Mac, Ctrl + , on Windows).
2. Navigate to the Features tab.
3. Scroll to the MCP section.
4. Click + Add New MCP Server and configure:
   • Name: kiomon
   • Type: command
   • Command: npx -y @kiomon/mcp-server
   • Environment variables:
     • KIOMON_TOKEN — your API key (Settings → API Keys in the dashboard)
     • KIOMON_URL — https://api.kiomon.com (or your own deployment’s URL)
5. Click Save. Cursor starts the server in the background.

Alternatively, add the same definition to your project’s .cursor/mcp.json, or run the one-line installer from the dashboard’s Settings → Agents & MCP tab (macOS: curl -sL https://kiomon.com/install.sh | bash -s -- --token=<key>).

Verify the connection

• In Settings → Features → MCP, the kiomon server should show a green check.
• Expand it to see the 8 registered tools: list_workspaces, get_workspace_context, search_memory, get_memory, explore_memory_graph, reflect_session, draft_memory, manage_memory.
• Cursor may ask you to trust the project before it can start the server.

Using it in Chat / Composer

Once connected, Cursor’s agent can retrieve context you’ve browsed. Try asking:

“Based on the Stripe documentation I was just reading, how do I create a checkout session?”

“Search my Kiomon library for what I saved about Cloudflare Workers.”

Cursor routes the request through the MCP server, queries your knowledge base (hybrid search), and returns the exact references you were looking at — with sources.

End-of-session reflection

Kiomon shines when you let Cursor recap. After a long task:

“Reflect on this session and save what you learned about our deploy process as memories for approval.”

Cursor drafts the learnings (facts, routines, moments) to your Review Inbox. Approve them in the dashboard and they become permanent, searchable memories with derived_from links back to the docs they came from.

Tips

• Let it orient: at the start of a workspace-heavy task, Cursor’s get_workspace_context loads your pinned memories and routines — the more you pin, the better its behavior.
• Save what you read: using the extension while you browse means Cursor answers from your research, not the open web.
• Staged follow-ups: RAG answers prefer already-cited documents, so drill into a topic with follow-up questions rather than re-asking from scratch.