One install. Every agent.
Last updated 12 September 2026
Add Hexum to Cursor in 3 steps
- Open the dashboard and create a key. Starter needs no card.
- Paste this JSON into Cursor Settings → MCP, or use the command on Claude Code.
- Reload. The agent should see Hexum.
{
"mcpServers": {
"hexum": {
"serverUrl": "https://hexum.dev/mcp",
"headers": { "Authorization": "Bearer hexum_live_…" }
}
}
}Other editors
- Add Hexum to Cursor — Cursor Settings → MCP, or paste the JSON into ~/.cursor/mcp.json, then reload.
- Add Hexum to Claude Code — From a terminal in the project: claude mcp add --transport http hexum https://hexum.dev/mcp --header "Authorization: Bearer hexum_live_…"
- Add Hexum to Antigravity — Open MCP servers in Antigravity. Add a remote HTTP server with the mcpServers JSON, then reload.
- Add Hexum to Codex — codex mcp add hexum --url https://hexum.dev/mcp --header "Authorization: Bearer hexum_live_…" then codex mcp list.
- Add Hexum to Grok — grok mcp add --transport http hexum https://hexum.dev/mcp --header "Authorization: Bearer hexum_live_…"
Optional skill file: Hexum skill. Full detail: docs.
Get a keyFAQ
How do I add Hexum to Cursor?
Create a key at /app, paste the one-sentence prompt into Cursor, and let the agent write the MCP config. Starter works until two million tokens this month. Details: /cursor.
Does Hexum replace Cursor or Claude Code?
No. You keep Cursor, Claude Code, Antigravity, Codex, or Grok. Hexum is not an editor and not a model. You paste a key into the agent you already use.
What are the five Hexum products?
Hexum is an ecosystem: five products and twelve tools on one key. Efficient: don’t paste the whole repo. Arch: block a bad import. Review: architecture review on GitHub PRs. Control: when the agent loops, write the rule. Loop: only keep building if checks and tests pass.
What is Hexum?
Hexum is a developer ecosystem for coding agents in Cursor, Claude Code, and the rest. One API key. Five products and twelve tools today: spend less on each prompt, block bad imports, review pull requests, stop the agent looping, and only keep building when checks pass. We do not keep your code.
Does Hexum store my repo?
No. We do not keep the code your agent sends. We do not train on it. Policy: /zdr.