AI agents call get_feed_accounts 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 and returns metadata about which accounts/sources are tracked by Musashi's feed system. It is purely informational retrieval with no capability to modify data, execute operations, delete records, or affect financial transactions. The action is read-only and poses minimal risk if misused by an AI agent.
From the tool's definition Tool name 'get_feed_accounts' with description 'List the accounts and sources that Musashi monitors' — retrieves and lists monitored data sources without modification or side effects.
Attacks that exploit this kind of access
List the accounts and sources that Musashi monitors for its feed. Use this when the user asks about data sources or which accounts are tracked. 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_accounts: 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_accounts 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_accounts 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_accounts. 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_accounts 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 →