Create a new formalization template and add it to the skill library. The calling LLM designs the template — no API key needed. Describe your problem, then submit a template with a skeleton (formal spec with {{SLOT:name}} markers), slot definitions, and normalization recipes. After creation, the t...
AI agents use chiasmus_craft to create or update resources in Chiasmus — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Chiasmus environment.
This tool creates a new template and persistently adds it to the skill library, making it a Write operation. It is reversible in principle (the template could be removed) and does not execute code or delete data. The blast radius is medium because a malformed or malicious template could propagate through chiasmus_formalize and chiasmus_skills, affecting subsequent formal verification workflows.
From the tool's definition Create a new formalization template and add it to the skill library
Documented attack patterns abuse exactly the kind of access chiasmus_craft 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_craft:
{
"version": "1",
"default": "deny",
"tools": {
"chiasmus_craft": {
"limits": [
{
"counter": "chiasmus_craft_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}chiasmus_craft stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Create a new formalization template and add it to the skill library. The calling LLM designs the template — no API key needed. Describe your problem, then submit a template with a skeleton (formal spec with {{SLOT:name}} markers), slot definitions, and normalization recipes. After creation, the template appears in chiasmus_skills and chiasmus_formalize. Validation: checks slot/skeleton consistency, required fields, name uniqueness. Optional: set test=true with an example to run it through the solver. It is categorised as a Write tool in the Chiasmus MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Chiasmus MCP server in PolicyLayer and add a rule for chiasmus_craft: 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_craft is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the chiasmus_craft 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_craft. 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_craft 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.