AI agents call get_health to retrieve information from Musashi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
get_health is a diagnostic read operation that retrieves status information about API availability and data freshness. It has no side effects, does not execute arbitrary code, does not modify data, and does not involve financial transactions. The blast radius of misuse is minimal—an attacker could learn service uptime or data latency but cannot manipulate markets, execute trades, or cause irreversible harm.
From the tool's definition Tool name and description indicate it 'Check[s] the health and availability' of an API and data sources. This is a query/monitoring operation with no data modification, execution, or financial impact.
Attacks that exploit this kind of access
Check the health and availability of the Musashi API and its data sources (Polymarket, Kalshi). Use this when the user asks if the service is working or data is fresh. It is categorised as a Read tool in the Musashi MCP Server, which means it retrieves data without modifying state.
Register the Musashi MCP server in PolicyLayer and add a rule for get_health: 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 Musashi. Nothing to install.
get_health 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_health 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_health. 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_health is provided by the Musashi MCP server (musashibot/musashi-mcp). 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 →