AI agents call qf_tool_spec_get to retrieve information from Qingflow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns information about tool specifications, parameters, and examples. It is purely informational and read-only, with no capability to create, modify, execute, or delete data. The 'get' suffix and the language 'Return' confirm it is a query operation that retrieves existing metadata for agent prompt grounding purposes.
From the tool's definition Tool name 'qf_tool_spec_get' and description 'Return MCP tool parameter requirements, limits, aliases and minimal examples' indicates retrieval of metadata/documentation about tool specifications with no side effects.
Attacks that exploit this kind of access
Return MCP tool parameter requirements, limits, aliases and minimal examples for agent prompt grounding. It is categorised as a Read tool in the Qingflow MCP Server, which means it retrieves data without modifying state.
Register the Qingflow MCP server in PolicyLayer and add a rule for qf_tool_spec_get: 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 Qingflow. Nothing to install.
qf_tool_spec_get 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 qf_tool_spec_get 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 qf_tool_spec_get. 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.
qf_tool_spec_get is provided by the Qingflow MCP server (qingflow-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 →