AI agents call recommend_best_assignee to retrieve information from Jamot MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries existing data (user profiles, workload, task requirements) to generate a recommendation. It performs analysis and returns information without creating, modifying, deleting, executing external operations, or committing financial obligations.
From the tool's definition Tool name is 'recommend_best_assignee' and description indicates it 'Recommend[s] the best available person for a task based on' workload/profile analysis.
Attacks that exploit this kind of access
Recommend the best available person for a task based on:. It is categorised as a Read tool in the Jamot MCP MCP Server, which means it retrieves data without modifying state.
Register the Jamot MCP server in PolicyLayer and add a rule for recommend_best_assignee: 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 Jamot MCP. Nothing to install.
recommend_best_assignee 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_best_assignee 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_best_assignee. 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_best_assignee is provided by the Jamot MCP server (jamot-pro/jamot-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 →