Capture an actual reusable learning from the current session as repo-local memory. Prefer this over diff proposal when the agent knows what was learned. Capture is rejected if every referenced path is missing from the repo; set allow_missing_paths to record anyway (e.g. a file you are about to cr...
AI agents use kage_learn to create or update resources in Kage — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kage environment.
kage_learn writes new learning records to version-controlled memory storage. This is a reversible Write operation—captured learnings can be reviewed and amended in PRs, and the git-tracked nature means changes are auditable.
From the tool's definition Tool description states 'Capture an actual reusable learning from the current session as repo-local memory' and mentions recording to memory that is 'stored as git-tracked JSON reviewed in PRs'. The tool creates or modifies persistent memory records.
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access kage_learn gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kage, and nothing reaches the server without passing your rules. This is the rule we recommend for kage_learn:
{
"version": "1",
"default": "deny",
"tools": {
"kage_learn": {
"limits": [
{
"counter": "kage_learn_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}kage_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.
Capture an actual reusable learning from the current session as repo-local memory. Prefer this over diff proposal when the agent knows what was learned. Capture is rejected if every referenced path is missing from the repo; set allow_missing_paths to record anyway (e.g. a file you are about to create). It is categorised as a Write tool in the Kage MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kage MCP server in PolicyLayer and add a rule for kage_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 Kage. Nothing to install.
kage_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 kage_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 kage_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.
kage_learn is provided by the Kage MCP server (@kage-core/kage-graph-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kage, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
62 Kage tools catalogued and risk-classified — across an index of 43,000+ MCP servers.