Get the TOOT directory path for search and bash operations.
AI agents call get_toot_dir to retrieve information from TOOT (Train of Operadic Thought) MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool returns a directory path for use by other operations but does not itself execute commands, modify data, or perform side effects. It is purely informational — similar to querying a configuration value. The severity is low because disclosing a directory path carries minimal risk on its own; the actual risk depends on what downstream tools do with that path.
From the tool's definition Tool name and description indicate it 'Get[s] the TOOT directory path' — a retrieval operation with no modification or execution capability. The word 'get' and passive retrieval of a path string confirm read-only behavior.
Attacks that exploit this kind of access
Get the TOOT directory path for search and bash operations. It is categorised as a Read tool in the TOOT (Train of Operadic Thought) MCP MCP Server, which means it retrieves data without modifying state.
Register the TOOT (Train of Operadic Thought) MCP server in PolicyLayer and add a rule for get_toot_dir: 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 TOOT (Train of Operadic Thought) MCP. Nothing to install.
get_toot_dir 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_toot_dir 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_toot_dir. 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_toot_dir is provided by the TOOT (Train of Operadic Thought) MCP server (sancovp/toot-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 →