Get total count of skills in the database.
AI agents call count_skills to retrieve information from Hivemind MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple data retrieval operation—fetching a count metric from the database. It does not create, modify, delete, or execute any operations; it purely retrieves existing information. The blast radius of misuse is minimal, as an AI agent obtaining a count of skills poses no security or operational risk.
From the tool's definition Tool name 'count_skills' and description 'Get total count of skills in the database' indicate a retrieval operation that queries aggregate data without modification or side effects.
Attacks that exploit this kind of access
Get total count of skills in the database. It is categorised as a Read tool in the Hivemind MCP MCP Server, which means it retrieves data without modifying state.
Register the Hivemind MCP server in PolicyLayer and add a rule for count_skills: 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 Hivemind MCP. Nothing to install.
count_skills 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 count_skills 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 count_skills. 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.
count_skills is provided by the Hivemind MCP server (kevthetech143/hivemind-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 →