AI agents call getRpcHealth to retrieve information from Boosty MCP DeFi Platform without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool merely retrieves health status information about RPC endpoints—a diagnostic read operation with no side effects. It does not execute transactions, modify data, delete resources, or commit financial obligations. Despite the platform's capacity for real DeFi operations, this specific tool is a simple status check query.
From the tool's definition Tool name 'getRpcHealth' and description 'Get health status of all RPC endpoints' indicates a read-only query operation that retrieves status information without modifying, executing, or affecting any data or operations.
Documented attack patterns abuse exactly the kind of access getRpcHealth gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Boosty MCP DeFi Platform, and nothing reaches the server without passing your rules. This is the rule we recommend for getRpcHealth:
{
"version": "1",
"default": "deny",
"tools": {
"getRpcHealth": {}
}
}getRpcHealth is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get health status of all RPC endpoints. It is categorised as a Read tool in the Boosty MCP DeFi Platform MCP Server, which means it retrieves data without modifying state.
Register the Boosty MCP DeFi Platform MCP server in PolicyLayer and add a rule for getRpcHealth: 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 Boosty MCP DeFi Platform. Nothing to install.
getRpcHealth 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 getRpcHealth 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 getRpcHealth. 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.
getRpcHealth is provided by the Boosty MCP DeFi Platform MCP server (nirholas/boosty). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Boosty MCP DeFi Platform, 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.
80 Boosty MCP DeFi Platform tools catalogued and risk-classified — across an index of 43,000+ MCP servers.