Get a brutally honest code review from Cynical Sally — a 0–10 score, real issues backed by evidence, and fixes you can actually use. Use this whenever the user wants code reviewed, critiqued, roasted, or asks
AI agents call sally_roast to retrieve information from Cynical Sally without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes code to produce a review report. It reads code input and returns textual analysis, suggestions, and scores. There are no side effects on the codebase itself — no execution, modification, deletion, or financial impact. The tool operates entirely in the read/analysis domain, making it a Read category tool with low severity.
From the tool's definition sally_roast provides a code review with scoring and analysis. The description states it delivers 'a 0–10 score, real issues backed by evidence, and fixes you can actually use' — all outputs that represent analysis and feedback, not modification, execution, or…
Documented attack patterns abuse exactly the kind of access sally_roast gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cynical Sally, and nothing reaches the server without passing your rules. This is the rule we recommend for sally_roast:
{
"version": "1",
"default": "deny",
"tools": {
"sally_roast": {}
}
}sally_roast is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get a brutally honest code review from Cynical Sally — a 0–10 score, real issues backed by evidence, and fixes you can actually use. Use this whenever the user wants code reviewed, critiqued, roasted, or asks. It is categorised as a Read tool in the Cynical Sally MCP Server, which means it retrieves data without modifying state.
Register the Cynical Sally MCP server in PolicyLayer and add a rule for sally_roast: 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 Cynical Sally. Nothing to install.
sally_roast 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 sally_roast 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 sally_roast. 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.
sally_roast is provided by the Cynical Sally MCP server (w1ckedxt/cynical-sally). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 Cynical Sally tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
8 Cynical Sally tools catalogued and risk-classified — across an index of 42,500+ MCP servers.