Submit formal logic to solver. Returns verified result. SOLVERS: z3 — SMT-LIB format → SAT + model | UNSAT + unsatCore | error prolog — facts/rules + query goal → answers | error FORMAT (optional, prolog only): mermaid — parse Mermaid flowchart/stateDiagram → Prolog facts + reachability rules Z3 ...
AI agents invoke chiasmus_verify to trigger actions in Chiasmus. 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.
This tool executes formal logic queries against external solvers (Z3 SMT solver and SWI-Prolog). It runs arbitrary logic programs and SMT-LIB expressions through solver engines, which constitutes code/query execution.
From the tool's definition Submit formal logic to solver. Returns verified result. SOLVERS: z3 — SMT-LIB format → SAT + model | UNSAT + unsatCore | error; prolog — facts/rules + query goal → answers | error
Documented attack patterns abuse exactly the kind of access chiasmus_verify 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_verify:
{
"version": "1",
"default": "deny",
"tools": {
"chiasmus_verify": {
"limits": [
{
"counter": "chiasmus_verify_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}chiasmus_verify 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.
Submit formal logic to solver. Returns verified result. SOLVERS: z3 — SMT-LIB format → SAT + model | UNSAT + unsatCore | error prolog — facts/rules + query goal → answers | error FORMAT (optional, prolog only): mermaid — parse Mermaid flowchart/stateDiagram → Prolog facts + reachability rules Z3 RULES: ⚠ UNSAT results include unsatCore — use (assert (! expr :named label)) for readable conflict labels ⚠ No (check-sat)/(get-model) — added automatically ⚠ Use (= flag (or ...)) NOT (=> ... flag) — implication → trivially SAT ⚠ No (define-fun) with args — breaks model extraction. Use (declare-const) + (assert (=)) instead PROLOG RULES: ⚠ All clauses end with period ⚠ No recursive reachability on cyclic graphs without tabling → infinite loop. Add. It is categorised as a Execute tool in the Chiasmus MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Chiasmus MCP server in PolicyLayer and add a rule for chiasmus_verify: 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_verify 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 chiasmus_verify 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_verify. 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_verify 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.