AI agents call get_feed_stats 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.
This tool queries market feed statistics and provides aggregated metrics (volume, urgency, top markets) without creating, modifying, executing, deleting, or moving money. It is a straightforward read operation on pre-computed or aggregated data, presenting minimal risk if called by an AI agent.
From the tool's definition Tool description states 'Get Musashi feed statistics including volume, urgency breakdown, and top-mentioned markets' – purely retrieves and aggregates data with 'no side effects'. The verb 'Get' and focus on statistics/overview confirms read-only behavior.
Attacks that exploit this kind of access
Get Musashi feed statistics including volume, urgency breakdown, and top-mentioned markets. Use this for an overview of feed activity rather than individual items. 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_feed_stats: 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_feed_stats 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_feed_stats 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_feed_stats. 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_feed_stats 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 →