获取项目总数
AI agents call get_project_count to retrieve information from MCP Project Query Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a count metric from the project database. It performs no writes, deletions, code execution, or financial operations. The operation is read-only and has minimal blast radius if misused by an AI agent—it only exposes a numeric value representing the total number of projects.
From the tool's definition Tool name 'get_project_count' and description '获取项目总数' (get total project count) indicate a simple query operation that retrieves aggregate data without modification or side effects.
Attacks that exploit this kind of access
获取项目总数. It is categorised as a Read tool in the MCP Project Query Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Project Query Server MCP server in PolicyLayer and add a rule for get_project_count: 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 Project Query Server. Nothing to install.
get_project_count 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 get_project_count 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 get_project_count. 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.
get_project_count is provided by the MCP Project Query Server MCP server (sweetwisdom/mcp-demo). 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 →