compass
AI agents call compass to retrieve information from Tool Compass without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The primary tool appears to be a semantic navigator that retrieves information about MCP tools without modifying them. No modification, deletion, code execution, or financial effects are suggested. Classified as Read due to query-like intent. Confidence is moderate (0.6) because the tool description is empty, creating uncertainty about actual implementation details.
From the tool's definition Tool name 'compass' with empty description. Context from sibling tools ('compass_analytics', 'compass_audit', 'compass_categories', 'compass_chains', 'compass_status', 'compass_sync') suggests this is a navigation/discovery tool.
Attacks that exploit this kind of access
compass. It is categorised as a Read tool in the Tool Compass MCP Server, which means it retrieves data without modifying state.
Register the Tool Compass MCP server in PolicyLayer and add a rule for compass: 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 Tool Compass. Nothing to install.
compass 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 compass 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 compass. 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.
compass is provided by the Tool Compass MCP server (mcp-tool-shop-org/tool-compass). 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 →