Store an automatic local observation event from an agent session. Observations are privacy-scanned, deduplicated, and never published automatically.
AI agents use kage_observe 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.
The tool stores (writes) observation data locally. While it is described as never published automatically and privacy-scanned, it still creates new records in the memory system. This is a Write operation.
From the tool's definition 'Store an automatic local observation event' — the tool writes/persists data (an observation) to the memory system. 'privacy-scanned, deduplicated, and never published automatically' confirms it creates/modifies stored records.
Documented attack patterns abuse exactly the kind of access kage_observe 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_observe:
{
"version": "1",
"default": "deny",
"tools": {
"kage_observe": {
"limits": [
{
"counter": "kage_observe_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}kage_observe 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.
Store an automatic local observation event from an agent session. Observations are privacy-scanned, deduplicated, and never published automatically. 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_observe: 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_observe 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_observe 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_observe. 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_observe 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.