Return agent-owned memory reconciliation work when source files linked to existing memory changed. Agents must update, supersede, or mark stale memory before final handoff.
AI agents use kage_memory_reconcile 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 performs reconciliation of agent-owned memory by updating, superseding, or marking entries stale when linked source files change. These are reversible modifications to stored memory records (git-tracked JSON), placing it in the Write category. It is not purely destructive since entries can be updated or superseded rather than deleted, and the git-tracked nature implies reversibility.
From the tool's definition 'update, supersede, or mark stale memory' — the tool modifies existing memory entries based on changed source files
Documented attack patterns abuse exactly the kind of access kage_memory_reconcile 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_memory_reconcile:
{
"version": "1",
"default": "deny",
"tools": {
"kage_memory_reconcile": {
"limits": [
{
"counter": "kage_memory_reconcile_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}kage_memory_reconcile 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.
Return agent-owned memory reconciliation work when source files linked to existing memory changed. Agents must update, supersede, or mark stale memory before final handoff. 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_memory_reconcile: 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_memory_reconcile 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_memory_reconcile 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_memory_reconcile. 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_memory_reconcile 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.