Build a signed graph-registry manifest for generated memory graph, code graph, indexes, metrics, audit, inbox, source packet IDs, packet hashes, and repo git state.
AI agents use kage_graph_registry 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 'builds' (creates/writes) a signed manifest artifact that consolidates multiple data sources. This is a write operation — it generates and stores a new manifest document. It is not purely reading existing data, nor does it delete anything or execute arbitrary code.
From the tool's definition Build a signed graph-registry manifest for generated memory graph, code graph, indexes, metrics, audit, inbox, source packet IDs, packet hashes, and repo git state.
Documented attack patterns abuse exactly the kind of access kage_graph_registry 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_graph_registry:
{
"version": "1",
"default": "deny",
"tools": {
"kage_graph_registry": {
"limits": [
{
"counter": "kage_graph_registry_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}kage_graph_registry 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.
Build a signed graph-registry manifest for generated memory graph, code graph, indexes, metrics, audit, inbox, source packet IDs, packet hashes, and repo git state. 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_graph_registry: 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_graph_registry 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_graph_registry 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_graph_registry. 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_graph_registry 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.