Brakes for your AI agents: every tool call is checked against your rules, held for human approval when risky, and recorded in a tamper-evident audit trail. Works with Claude Code and any MCP app.
Brakes for your AI agents. Every action an agent takes (running a command, editing a file, sending an email, issuing a refund, changing a database) goes through Squidbrake first. It is checked against your rules, held for a person when it's risky, recorded in a tamper-evident audit trail, and can be stopped instantly.
Free and open source (Apache 2.0). Runs on your laptop or your own server; your data never leaves it.
- Rules, not vibes: rules.yaml says what runs by itself, what's blocked, and what waits for a person. No LLM in the decision path. - Human approval: risky actions wait in the dashboard, on your phone (one-tap links, push via ntfy) or in Slack. The approver sees what led to it, e.g. the email the agent just read. - Reads what a command really does: ls && rm -rf ~/, bash -c "...", rmdir /s /q d:\ or curl ... sh are split and read before they run. Wiping a disk or home folder is blocked; git push --force, terraform destroy, kubectl delete or cloud deletes wait for a person; commands that only look (ls, git status) run without asking. - Catches prompt injection without a model: if an agent sends data to an address that only a web page, email or issue mentioned (not you, not your own systems), it's held and the approver is told where the address came from. - Judges by history: blocks a retry of something a person rejected, catches look-alike domains (acrne-corp.com pretending to be acme.com), flags duplicate refunds, and lets you write sequence rules ("deleting a database right after its backups were turned off") that say which earlier step caused them. - Works w
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/batrapulkit--squidbrake.html)
Reuse Agent Skills across DeepSeek Harness and MCP. Check local SKILL.md files in the browser or CI, with parser diagnostics, file hashes and clear exit codes. Try the Hugging Face playground.
Shalimov04/mcp-airlockStateless governance proxy for MCP (2026-07-28): policy, dry-run, human confirmation, audit, tracing
CTRLRun/ctrlrunThe execution safety layer for AI agents.
agent-chaperone/agent-chaperoneScreens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.
Winterrks/telepathyAllow your coding agents to self discover and collaborate with eachother (Claude Code, Codex, open code and other 9 supported)
Masikomoore/agent-memoryOne memory for every AI agent — self-hosted long-term memory over MCP/REST for Claude Code, Codex, Cursor, Gemini CLI, VS Code, OpenClaw, and more.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.