Create a repo-local Kage memory packet immediately. Org/global promotion still requires explicit human review. Capture is rejected if every referenced path is missing from the repo; set allow_missing_paths to record anyway.
AI agents use kage_capture 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_capture creates new memory packets in a git-tracked JSON store. This is a reversible write operation—packets can be deleted or modified. It does not execute arbitrary code, delete data irreversibly, or move money. The 'medium' severity reflects that a compromised agent could flood the repo with incorrect or malicious memory entries, requiring human PR review before promotion to org/global scope.
From the tool's definition Tool description states 'Create a repo-local Kage memory packet immediately', using the verb 'Create' which indicates data creation. The mention of 'allow_missing_paths to record anyway' confirms writing behavior.
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access kage_capture 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_capture:
{
"version": "1",
"default": "deny",
"tools": {
"kage_capture": {
"limits": [
{
"counter": "kage_capture_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}kage_capture 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 repo-local Kage memory packet immediately. Org/global promotion still requires explicit human review. Capture is rejected if every referenced path is missing from the repo; set allow_missing_paths to record anyway. 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_capture: 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_capture 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_capture 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_capture. 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_capture 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.