Sally proposes concrete refactors with before/after code and explains why the original would haunt your 3am on-call rotation. Use when the user wants code improved, cleaned up, simplified, or modernized. Sends only the provided code to the Cynical Sally backend — never stored, never used for trai...
AI agents call sally_refactor 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 refactoring suggestions and explanations based on provided code input. It has no side effects—it does not modify, execute, or delete anything. The explicit statement that it is 'read-only' with suggestions returned as markdown and nothing applied to files confirms it is a Read category tool.
From the tool's definition Tool description explicitly states: 'Read-only: suggestions come back as markdown, nothing is applied to files.' The tool 'proposes concrete refactors' and 'explains' without modifying any persistent state.
Documented attack patterns abuse exactly the kind of access sally_refactor 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_refactor:
{
"version": "1",
"default": "deny",
"tools": {
"sally_refactor": {}
}
}sally_refactor 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.
Sally proposes concrete refactors with before/after code and explains why the original would haunt your 3am on-call rotation. Use when the user wants code improved, cleaned up, simplified, or modernized. Sends only the provided code to the Cynical Sally backend — never stored, never used for training. Read-only: suggestions come back as markdown, nothing is applied to files. Premium tool: one free use per month on the free tier, unlimited with Full Suite. 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_refactor: 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_refactor 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_refactor 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_refactor. 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_refactor 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.