Get current FSD and naming project rules.
AI agents call get_rules to retrieve information from Mcp React Frontend without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns configuration/rule data from the project. It has no side effects—it does not create, modify, execute, delete, or move data. The description explicitly indicates a retrieval operation ('Get current'). The blast radius of misuse is minimal; an agent accessing rules cannot cause damage beyond reading configuration information.
From the tool's definition get_rules retrieves current FSD and naming project rules with no modification or execution capability indicated.
Attacks that exploit this kind of access
Get current FSD and naming project rules. It is categorised as a Read tool in the Mcp React Frontend MCP Server, which means it retrieves data without modifying state.
Register the Mcp React Frontend MCP server in PolicyLayer and add a rule for get_rules: 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 Mcp React Frontend. Nothing to install.
get_rules is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_rules 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 get_rules. 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.
get_rules is provided by the Mcp React Frontend MCP server (kdf25/mcp-react-frontend). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →