LabscoConnect MCP ↗
get-convex logo✓ Official★ 63

convex-deploy-guard

Makes your assistant name the Convex deployment it is about to touch, development, preview or production, before any command that affects one. Production changes need a fresh yes from you each time, and a read-only mode blocks all changes for the session.

by get-convexpart of get-convex/agent-skills

One of 30 skills in the get-convex/agent-skills package — works on its own, and pairs well with its siblings.

WHEN YOUR AGENT SHOULD USE IT

A QUICK BOUNDARY

USE FOR

  • See the target deployment named before every deploy or settings change.
  • Give an explicit yes for each production change in a session.
  • Let the assistant read production for an audit without being able to change it.
  • Lock a session to read-only when you say 'don't change anything'.
  • Work out why a deploy seemed to do nothing.

DO NOT USE FOR

  • Deploying the app: it guards other commands and deploys nothing itself.

Documents

This is the playbook your agent receives when the skill activates — you don't need to read it to use the skill, but it's here to audit before installing.

Deployment target guard

Deployments are not interchangeable, and most incidents start with a command aimed at the wrong one. Every Convex project has several (personal dev, preview, prod — often across multiple projects on one machine). This guard is the standing discipline: identify, announce, then act — and treat prod as consent-gated, per action, per session.

Workflow
  1. IDENTIFY before you act: read CONVEX_DEPLOYMENT in .env.local, convex.json, and whether CONVEX_DEPLOY_KEY is set; or call the official Convex MCP status tool. Classify the target: local-anonymous | dev | preview | prod. If two sources disagree, resolve before proceeding.
  2. ANNOUNCE in one line before any deployment-affecting command: target: dev (joyful-capybara-123, personal dev). Never run the command in the same breath as discovering the target — announce first.
  3. PROD needs a FRESH explicit yes: before npx convex deploy (when it resolves to prod), npx convex run --prod, env set on prod, snapshot import/export on prod, or starting the MCP with prod access — state exactly what will change on which deployment and get an explicit yes in THIS session. A yes given earlier, or for a different target, does not carry.
  4. MCP safety defaults: start the official MCP scoped non-prod (--deployment dev). The two prod flags are DIFFERENT risk levels — keep them split: a read-only prod audit (advisor/insights reading data/logs/insights) passes ONLY --cautiously-allow-production-pii (read tools); --dangerously-enable-production-deployments (which enables MUTATING prod tools) stays OFF unless the user explicitly asked to CHANGE prod this session. Never pair them by default — 'look at prod' must not silently grant 'mutate prod'.
  5. READ-ONLY session mode: when the user says 'read-only' / 'don't change anything', honor it absolutely for the rest of the session — no deploy, no env set/remove, no mutations via run, no imports; start the MCP with --disable-tools run,envSet,envRemove.
  6. Wrong-deployment diagnosis: when a deploy 'didn't change anything', do NOT re-deploy harder. Re-run step 1 — the deploy almost certainly landed on a different deployment than the one being observed.
  7. Ambiguity = stop: if you cannot determine which deployment a command will hit, find out (status tool; compare npx convex env list fingerprints) — never guess.
Rules
  • Classify and announce the target BEFORE every deployment-affecting command — identification and action are two separate steps.
  • Prod consent is per-action, per-target, per-session: state what changes where, get a fresh explicit yes.
  • Keep the two prod MCP flags split by risk: --cautiously-allow-production-pii (read-only) for an audit; --dangerously-enable-production-deployments (mutating) only when the user explicitly asks to change prod. Both are user-spoken-only; default every MCP start to a non-prod deployment selector.
  • Read-only mode, once requested, is absolute for the session — including 'harmless' mutations.
  • A deploy that seemed to do nothing means the WRONG deployment changed — diagnose the target, don't re-run.
  • This guard composes: ship, env, migrate, and seed run it as their step 0; it is not itself a deploy tool.

Installation

Copy & paste — that's it
npx skills add get-convex/agent-skills --skill "convex-deploy-guard" --full-depth

Run this in your project — your agent picks the skill up automatically.

License

Licensed under Apache-2.0— you can use, modify, and redistribute it under that license's terms.

View the full license file on GitHub →