personal_match
AI agents call personal_match to retrieve information from Guokao MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to perform intelligent matching of civil service exam positions against personal qualifications. Matching and filtering are read operations that retrieve and return data without modifying, deleting, or executing external actions. The sibling tools are all read-oriented (filter, get, match). No side effects or state changes are implied.
From the tool's definition Tool name 'personal_match' combined with sibling tools 'filter_positions', 'get_position_detail', 'get_statistics', and 'match_by_major' all indicate query and retrieval operations.
Attacks that exploit this kind of access
personal_match. It is categorised as a Read tool in the Guokao MCP MCP Server, which means it retrieves data without modifying state.
Register the Guokao MCP server in PolicyLayer and add a rule for personal_match: 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 Guokao MCP. Nothing to install.
personal_match 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 personal_match 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 personal_match. 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.
personal_match is provided by the Guokao MCP server (mouseminar/guokao_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 →