This record as markdown: /tools/cowork-os/qa-check.md
What qa_check does on CoWork OS
AI agents invoke qa_check to trigger actions in CoWork OS. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why qa_check is rated High
The tool executes a QA check process on the current page, which constitutes running an automated operation. While it may primarily read/analyze, 'Run' implies active execution with potential side effects depending on what the QA check does (e.g., modifying state, triggering validators, or interacting with page elements).
From the tool's definition "Run a specific QA check on the current page" — 'Run' indicates execution of a process/script against live content
Attacks that exploit this kind of access
The rule that runs qa_check safely
PolicyLayer is an MCP gateway: it sits between your AI agents and CoWork OS, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For qa_check, this is the rule to start with:
qa_check stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect CoWork OS, apply this rule, and every qa_check call is checked against it from then on.
Questions about qa_check
Run a specific QA check on the current page. It is categorised as a Execute tool in the CoWork OS MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the CoWork OS MCP server in PolicyLayer and add a rule for qa_check: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches CoWork OS. Nothing to install.
qa_check is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the qa_check rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for qa_check. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
qa_check is provided by the CoWork OS MCP server (CoWork-OS/CoWork-OS). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on CoWork OS, and thousands of servers like it.
Across the catalogue