Create or update a branch review summary and repo-local change-memory packet from local git status and diff metadata. Org/global promotion still requires explicit human review.
AI agents use kage_propose_from_diff 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.
This tool writes new data structures (branch review summaries and change-memory packets) and modifies existing ones. However, the changes are: (1) reversible via git operations, (2) scoped to a local repository branch, and (3) explicitly require human review for org/global promotion, limiting blast radius. It does not execute arbitrary code, delete data irreversibly, or move money.
From the tool's definition kage_propose_from_diff creates or updates a branch review summary and repo-local change-memory packet from git diff metadata. The verbs 'create or update' indicate it modifies data.
Documented attack patterns abuse exactly the kind of access kage_propose_from_diff 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_propose_from_diff:
{
"version": "1",
"default": "deny",
"tools": {
"kage_propose_from_diff": {
"limits": [
{
"counter": "kage_propose_from_diff_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}kage_propose_from_diff 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 or update a branch review summary and repo-local change-memory packet from local git status and diff metadata. Org/global promotion still requires explicit human review. 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_propose_from_diff: 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_propose_from_diff 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_propose_from_diff 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_propose_from_diff. 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_propose_from_diff 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.