Get Lenny Zeltser's scoring playbook so your AI can score a draft locally against a cybersecurity-writing rating sheet. THIS IS THE ONLY TOOL THAT PRODUCES NUMERIC SCORES — the writing-coach tools (get_security_writing_guidelines, ir_*, product_*) never score. Returns the rubric plus step-by-step...
Part of the Website Search server.
Free to start. No card required.
AI agents call rating_score_writing to retrieve information from Website Search without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though rating_score_writing only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"rating_score_writing": {}
}
}See the full Website Search policy for all 53 tools.
These attack patterns abuse exactly the kind of access rating_score_writing gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Get Lenny Zeltser's scoring playbook so your AI can score a draft locally against a cybersecurity-writing rating sheet. THIS IS THE ONLY TOOL THAT PRODUCES NUMERIC SCORES — the writing-coach tools (get_security_writing_guidelines, ir_*, product_*) never score. Returns the rubric plus step-by-step instructions for applying it. This server never requests your draft and instructs your AI to keep it local—rating sheets and scoring instructions flow to your AI.. It is categorised as a Read tool in the Website Search MCP Server, which means it retrieves data without modifying state.
Register the Website Search MCP server in PolicyLayer and add a rule for rating_score_writing: 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 Website Search. Nothing to install.
rating_score_writing is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the rating_score_writing 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 rating_score_writing. 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.
rating_score_writing is provided by the Website Search MCP server (https://website-mcp.zeltser.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 53 Website Search tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.