butterbase
AI-native, open-source backend-as-a-service with a built-in Model Context Protocol server.
Examining code for the line that is wrong
What it does
AI-native, open-source backend-as-a-service with a built-in Model Context Protocol (MCP) server. Postgres data plane, auth, storage, serverless functions, AI gateway, RAG, realtime, and durable objects — all drivable by an AI agent via MCP tools.
What it can touch
Includes 1621 scripts
Your AI can run these when the skill is used — on your computer in a coding tool (which asks first unless you have told it not to), or in the AI’s own sandbox in Claude and ChatGPT.
How we know
Found in the skill’s folder: Examples/agents/approval-hitl/cancel_subscription.ts, Examples/agents/support-readonly/lookup_account.ts, Examples/grocery-list-2026-04-03/frontend/eslint.config.js, Examples/grocery-list-2026-04-03/frontend/src/App.tsx….
Asks for an API key or token
You will need an account with the service it talks to, and your own key. Keep keys in your settings or environment, never in a chat.
How we know
The SKILL.md names BUTTERBASE_API_KEY.
Mentions 2 outside web addresses
The instructions point your AI at these sites or APIs. Anything it sends there leaves your computer.
How we know
Web addresses in the SKILL.md, excluding GitHub and documentation sites: api.butterbase.ai, butterbase.ai.
Uses terminal commands
It shows your AI commands to run. In a coding agent that means your terminal; in a chat app it usually can’t.
How we know
The SKILL.md contains shell code blocks.
Its code sends data over the internet
A script in it uploads or posts data. That is normal for a skill that talks to a service — check that the address is the service you expect.
How we know
README.md line 195: “curl -X POST http://localhost:4000/init -H "Content-Type: application/json" -d '{"name": "my-app"}'”. Read 2026-10-04, commit b8623ec.
README.md, line 195 ↗Adds a connector (MCP server)
It sets up a separate program your AI can call. That program is not covered by this check.
How we know
An MCP configuration or "mcp add" command in its files. Read 2026-10-04, commit b8623ec.
6 smaller things worth knowing
Contains commands that delete or overwrite; Refers to a credentials file (SSH keys, cloud logins, tokens). Usually legitimate — listed so nothing is hidden.
How we know
Contains commands that delete or overwrite — db/control-plane/061_post_cutover_drop_runtime_tables.sql line 15; Contains commands that delete or overwrite — docker-compose.local.yml line 239; Contains commands that delete or overwrite — package.json line 14; Contains commands that delete or overwrite — services/agent-runtime/Dockerfile line 5; Refers to a credentials file (SSH keys, cloud logins, tokens) — services/agent-runtime/src/agent_runtime/safe_request.py line 30; Refers to a credentials file (SSH keys, cloud logins, tokens) — services/agent-runtime/tests/test_safe_request.py line 12. Read 2026-10-04, commit b8623ec.
db/control-plane/061_post_cutover_drop_runtime_tables.sql, line 15 ↗docker-compose.local.yml, line 239 ↗package.json, line 14 ↗services/agent-runtime/Dockerfile, line 5 ↗services/agent-runtime/src/agent_runtime/safe_request.py, line 30 ↗services/agent-runtime/tests/test_safe_request.py, line 12 ↗Partly checked
Launch7’s check could not read everything in this skill: 2 files too large to read; too many files to read them all. Nothing is known about the parts it skipped.
How we know
596 text files read; skipped files are listed by name only. Read 2026-10-04, commit b8623ec.
Recently maintained
Its repository has had changes recently.
How we know
Last push to butterbase-ai/butterbase: 2026-10-01 (3 days before the scan).
Read automatically from the skill’s own files on GitHub on 4 Oct 2026. Launch7 does not run or manually review skills: this lists what the check saw, and nothing here means “safe”. How we check
Add it to your AI
Partly. Upload it in Claude’s settings — the instructions work; the scripts need the full folder.
Built in your browser from the SKILL.md on GitHub — nothing passes through Launch7.
In Claude, open Customize → Skills, press +, then Create skill → Upload a skill, and choose the .zip.
Make sure code execution is switched on (Settings → Capabilities). Skills need it.
Start a new chat and ask for the job in your own words — Claude picks the skill up when it fits.
This skill ships 1621 scripts beside its instructions. The download here is the SKILL.md alone — enough for the instructions, not for the parts that run code. Use the command route, or take the full folder from the repository.
How Claude does this: support.claude.com · checked 28 Sep 2026 · “Supported” means documented by the vendor; Launch7 has not run it end to end