Fetch citing cases for a cached citation from jade.io and store them locally.
AI agents use cache_cited_by to create or update resources in AusLaw MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AusLaw MCP environment.
The tool retrieves citing cases from jade.io (a read operation) but then stores/caches the results locally (a write operation). Since it persists data locally, Write is the most applicable category. The blast radius is low as it only stores legal citation metadata.
From the tool's definition fetch citing cases...and store them locally
Documented attack patterns abuse exactly the kind of access cache_cited_by gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AusLaw MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for cache_cited_by:
{
"version": "1",
"default": "deny",
"tools": {
"cache_cited_by": {
"limits": [
{
"counter": "cache_cited_by_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} cache_cited_by 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.
Fetch citing cases for a cached citation from jade.io and store them locally. It is categorised as a Write tool in the AusLaw MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AusLaw MCP server in PolicyLayer and add a rule for cache_cited_by: 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 AusLaw MCP. Nothing to install.
cache_cited_by 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 cache_cited_by 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 cache_cited_by. 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.
cache_cited_by is provided by the AusLaw MCP server (russellbrenner/auslaw-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AusLaw MCP, 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.
18 AusLaw MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.