Phased code-review recipe — which tools to run, in what order, what to flag. Pure plan, no side effects. Execute phases sequentially; each action carries
AI agents call chiasmus_review to retrieve information from Chiasmus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool description explicitly states 'Pure plan, no side effects' and describes a phased code-review recipe that specifies which tools to run and in what order. It generates a plan/recipe rather than executing anything, making it a Read/informational tool with low blast radius.
From the tool's definition Pure plan, no side effects
Documented attack patterns abuse exactly the kind of access chiasmus_review gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Chiasmus, and nothing reaches the server without passing your rules. This is the rule we recommend for chiasmus_review:
{
"version": "1",
"default": "deny",
"tools": {
"chiasmus_review": {}
}
}chiasmus_review 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.
Phased code-review recipe — which tools to run, in what order, what to flag. Pure plan, no side effects. Execute phases sequentially; each action carries. It is categorised as a Read tool in the Chiasmus MCP Server, which means it retrieves data without modifying state.
Register the Chiasmus MCP server in PolicyLayer and add a rule for chiasmus_review: 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 Chiasmus. Nothing to install.
chiasmus_review 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 chiasmus_review 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 chiasmus_review. 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.
chiasmus_review is provided by the Chiasmus MCP server (yogthos/chiasmus). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 11 Chiasmus tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
11 Chiasmus tools catalogued and risk-classified — across an index of 42,500+ MCP servers.