recommend
AI agents call recommend to retrieve information from Mcp Director without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the server description which explicitly separates 'recommending' from 'switching' behaviors, and the sibling tool 'apply_profile' handles the actual switching, 'recommend' most likely only reads the current state and returns a suggestion. However, the empty description lowers confidence significantly — it could potentially trigger a profile switch.
From the tool's definition Tool name 'recommend' and server description mentions 'recommending and switching between task-specific MCP profiles'. The recommend function likely analyzes current context and suggests a profile without applying changes.
Attacks that exploit this kind of access
recommend. It is categorised as a Read tool in the Mcp Director MCP Server, which means it retrieves data without modifying state.
Register the Mcp Director MCP server in PolicyLayer and add a rule for recommend: 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 Director. Nothing to install.
recommend 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 recommend 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 recommend. 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.
recommend is provided by the Mcp Director MCP server (yut0takagi/mcp-director). 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 →