AI agents call swarm_list_directory to retrieve information from Mcp Swarm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and displays directory/file structure information about a project. It performs a read-only query operation that does not modify, execute, or delete any data. Directory listing is a standard informational operation with minimal security risk unless the project contains highly sensitive path information, warranting low severity.
From the tool's definition Tool name is 'swarm_list_directory' and description translates to 'List project directory structure.' This is a directory listing operation with no side effects.
Attacks that exploit this kind of access
列出项目目录结构。. It is categorised as a Read tool in the Mcp Swarm MCP Server, which means it retrieves data without modifying state.
Register the Mcp Swarm MCP server in PolicyLayer and add a rule for swarm_list_directory: 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 Swarm. Nothing to install.
swarm_list_directory 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 swarm_list_directory 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 swarm_list_directory. 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.
swarm_list_directory is provided by the Mcp Swarm MCP server (moselu/mcp-swarm). 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 →