Extract reusable template from verified solution → add to skill library. Generalizes concrete spec into parameterized template. Stored as candidate → promoted after 3+ successful reuses. Needs API key. Flow: chiasmus_verify → chiasmus_learn → template appears in chiasmus_skills.
AI agents use chiasmus_learn 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.
The tool creates and stores new templates in a skill library, which is a reversible modification of data. This is a Write operation rather than Read (it modifies state) or Execute (it doesn't run external code or commands based on user input—it processes verified solutions). The reversibility (templates can be removed or updated) and controlled nature (promotion requires 3+ reuses) prevent it from being Destructive.
From the tool's definition 'Extract reusable template from verified solution → add to skill library' and 'Stored as candidate → promoted after 3+ successful reuses' indicate the tool creates and modifies data (templates) in a persistent skill library.
Documented attack patterns abuse exactly the kind of access chiasmus_learn 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_learn:
{
"version": "1",
"default": "deny",
"tools": {
"chiasmus_learn": {
"limits": [
{
"counter": "chiasmus_learn_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}chiasmus_learn 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.
Extract reusable template from verified solution → add to skill library. Generalizes concrete spec into parameterized template. Stored as candidate → promoted after 3+ successful reuses. Needs API key. Flow: chiasmus_verify → chiasmus_learn → template appears in chiasmus_skills. 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_learn: 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_learn 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_learn 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_learn. 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_learn 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.