Create a new lesson from an error and its solution
AI agents use create_lesson to create or update resources in Knowledge Graph Memory Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Knowledge Graph Memory Server environment.
This tool creates (writes) a new lesson record, which is a reversible operation that modifies data by adding an entry. It does not delete, execute arbitrary code, move funds, or cause irreversible changes. The blast radius is minimal since lesson creation is a data enrichment operation with no external side effects or destructive consequences.
From the tool's definition Tool description states 'Create a new lesson' which is a create operation that adds a new record to the knowledge graph's lesson management system.
Documented attack patterns abuse exactly the kind of access create_lesson gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Knowledge Graph Memory Server, and nothing reaches the server without passing your rules. This is the rule we recommend for create_lesson:
{
"version": "1",
"default": "deny",
"tools": {
"create_lesson": {
"limits": [
{
"counter": "create_lesson_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_lesson 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 lesson from an error and its solution. It is categorised as a Write tool in the Knowledge Graph Memory Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Knowledge Graph Memory Server MCP server in PolicyLayer and add a rule for create_lesson: 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 Knowledge Graph Memory Server. Nothing to install.
create_lesson 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 create_lesson 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 create_lesson. 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.
create_lesson is provided by the Knowledge Graph Memory Server MCP server (t1nker-1220/memories-with-lessons-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 13 Knowledge Graph Memory Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
13 Knowledge Graph Memory Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.