propose_probe
Submit a standalone behavioral probe. Execute real application behavior, including a legitimate-use control. The same script is frozen and replayed after patching. Do not inspect source text or Git state to infer success. A setup error is inconclusive, never safe.
This record as markdown: /tools/0sec/propose-probe.md
What propose_probe does on 0sec
AI agents invoke propose_probe to trigger actions in 0sec. 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 propose_probe is rated High
Executes real application behavior with scripts whose effects depend on probe arguments and patching state.
From the tool's definition Execute real application behavior, execute script, replayed after patching
Attacks that exploit this kind of access
The rule that runs propose_probe safely
PolicyLayer is an MCP gateway: it sits between your AI agents and 0sec, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For propose_probe, this is the rule to start with:
propose_probe 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 0sec, apply this rule, and every propose_probe call is checked against it from then on.
Questions about propose_probe
Submit a standalone behavioral probe. Execute real application behavior, including a legitimate-use control. The same script is frozen and replayed after patching. Do not inspect source text or Git state to infer success. A setup error is inconclusive, never safe. It is categorised as a Execute tool in the 0sec MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the 0sec MCP server in PolicyLayer and add a rule for propose_probe: 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 0sec. Nothing to install.
propose_probe 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 propose_probe 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 propose_probe. 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.
propose_probe is provided by the 0sec MCP server (0sec-labs/0sec). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on 0sec, and thousands of servers like it.
This server
Across the catalogue