AI agents invoke start_realtime_assistance to trigger actions in Scrivener MCP Server. 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.
start_realtime_assistance 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.
Documented attack patterns abuse exactly the kind of access start_realtime_assistance gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Scrivener MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for start_realtime_assistance:
{
"version": "1",
"default": "deny",
"tools": {
"start_realtime_assistance": {
"limits": [
{
"counter": "start_realtime_assistance_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}start_realtime_assistance 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.
Free to start. No card required.
Start real-time writing assist. It is categorised as a Execute tool in the Scrivener MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Scrivener MCP Server MCP server in PolicyLayer and add a rule for start_realtime_assistance: 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 Scrivener MCP Server. Nothing to install.
start_realtime_assistance 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 start_realtime_assistance 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 start_realtime_assistance. 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.
start_realtime_assistance is provided by the Scrivener MCP Server MCP server (writerslogic/scrivener-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 62 Scrivener MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
62 Scrivener MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.