site_run
Execute a plan that a human has approved. Runs only the legs carried in the signed plan. A plan can be run once — replay is blocked in the database, not in code. Every leg writes a receipt BEFORE its call, so a leg that never returns leaves a visible
This record as markdown: /tools/io-github-0nork-0nmcp/site-run.md
What site_run does on 0nmcp
AI agents invoke site_run to trigger actions in 0nmcp. 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 site_run is rated High
site_run triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs site_run safely
PolicyLayer is an MCP gateway: it sits between your AI agents and 0nmcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For site_run, this is the rule to start with:
site_run 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 0nmcp, apply this rule, and every site_run call is checked against it from then on.
Questions about site_run
Execute a plan that a human has approved. Runs only the legs carried in the signed plan. A plan can be run once — replay is blocked in the database, not in code. Every leg writes a receipt BEFORE its call, so a leg that never returns leaves a visible. It is categorised as a Execute tool in the 0nmcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the 0n MCP server in PolicyLayer and add a rule for site_run: 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 0nmcp. Nothing to install.
site_run 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 site_run 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 site_run. 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.
site_run is provided by the 0n MCP server (0nmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on 0n, and thousands of servers like it.
This server
Across the catalogue