Updates demo://status and notifies subscribers.
AI agents use publish_status to create or update resources in MCP from Scratch Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP from Scratch Server environment.
This tool modifies state (updates a status resource) and triggers notifications, making it a Write operation with cascading effects. It's not Destructive (updates are reversible), not Execute (no arbitrary code execution), and not Financial.
From the tool's definition Tool description states it 'Updates demo://status' — a modification operation. The 'notifies subscribers' aspect indicates side effects beyond simple data change, affecting downstream systems.
Documented attack patterns abuse exactly the kind of access publish_status gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP from Scratch Server, and nothing reaches the server without passing your rules. This is the rule we recommend for publish_status:
{
"version": "1",
"default": "deny",
"tools": {
"publish_status": {
"limits": [
{
"counter": "publish_status_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} publish_status stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Updates demo://status and notifies subscribers. It is categorised as a Write tool in the MCP from Scratch Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP from Scratch Server MCP server in PolicyLayer and add a rule for publish_status: 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 MCP from Scratch Server. Nothing to install.
publish_status is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the publish_status 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 publish_status. 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.
publish_status is provided by the MCP from Scratch Server MCP server (pguso/mcp-from-scratch). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP from Scratch Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
12 MCP from Scratch Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.