Add Hexum to Grok
Last updated 12 September 2026
Hexum does not replace Grok. Keep the editor. Get a key at the dashboard. Starter needs no card.
Add Hexum to Grok in 3 steps
- Open the dashboard, create a key. The secret is shown once.
- grok mcp add --transport http hexum https://hexum.dev/mcp --header "Authorization: Bearer hexum_live_…"
- Reload. The agent should see Hexum’s tools. Details live in the docs.
{
"mcpServers": {
"hexum": {
"serverUrl": "https://hexum.dev/mcp",
"headers": { "Authorization": "Bearer hexum_live_…" }
}
}
}If connect says AUTH, the key is missing, wrong, or revoked. If it says BILLING, the starter window is used or that bill is off — turn billing on at the dashboard. Other editors: add Hexum to every agent.
FAQ
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 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.
How do I add Hexum to Grok?
grok mcp add --transport http hexum https://hexum.dev/mcp --header "Authorization: Bearer hexum_live_…" Mint a key at /app. Starter works without a card until two million tokens this month.
How does Hexum cut what I pay the model?
Your agent stops dumping the whole repo into the prompt. Hexum sends this task, not every file. On the published card, MBPP context dropped 85.2% and the combined 24-task cut is 87.6%, with 24/24 tests still passing. Tokens are ceil(utf8_bytes/4), not a provider invoice. See /benchmarks.
Why did connect fail with BILLING or AUTH?
AUTH means the key is missing, wrong, or revoked. BILLING means that key’s plan is off, or the starter window is used. Turn Usage billing on at /app, or make a key on the plan that is on.
Does Hexum store my repo?
No. We do not keep the code your agent sends. We do not train on it. Policy: /zdr.