Smart routing: given a message or task description, suggest which agent is
AI agents call suggest_route to retrieve information from Claude Team MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a recommendation/suggestion tool that reads task descriptions and returns routing suggestions. It performs analysis and returns information without side effects—no data is created, modified, deleted, or executed. The tool fits the 'Read' category as a query-like function. Severity is low because misuse (e.g., suggesting suboptimal agent assignments) causes no data loss, financial impact, or irreversible harm.
From the tool's definition Tool name 'suggest_route' with description indicating it 'suggest[s] which agent is' (action: suggest/recommend).
Attacks that exploit this kind of access
Smart routing: given a message or task description, suggest which agent is. It is categorised as a Read tool in the Claude Team MCP MCP Server, which means it retrieves data without modifying state.
Register the Claude Team MCP server in PolicyLayer and add a rule for suggest_route: 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 Claude Team MCP. Nothing to install.
suggest_route 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 suggest_route 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 suggest_route. 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.
suggest_route is provided by the Claude Team MCP server (lakshan12367/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 →