Get agent suggestions for a request
AI agents call suggest_agents to retrieve information from Worksona MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries information (agent suggestions) based on a user request. It has no side effects, does not modify data, execute commands, delete resources, or commit financial obligations. It is a straightforward read operation that returns information to inform the user's subsequent choices.
From the tool's definition Tool name 'suggest_agents' and description 'Get agent suggestions for a request' indicate a query/retrieval operation. The verb 'Get' and noun 'suggestions' denote reading data without modification or execution of external operations.
Attacks that exploit this kind of access
Get agent suggestions for a request. It is categorised as a Read tool in the Worksona MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Worksona MCP Server MCP server in PolicyLayer and add a rule for suggest_agents: 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 Worksona MCP Server. Nothing to install.
suggest_agents 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_agents 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_agents. 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_agents is provided by the Worksona MCP Server MCP server (worksona/-worksona-mcp-server). 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 →