filter_positions
AI agents call filter_positions 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 retrieves or filters position data based on criteria without modifying, deleting, or executing external operations. The empty description is offset by strong contextual evidence from the server's stated purpose (intelligent querying and matching) and sibling tools that are clearly read-only. The typical blast radius of misused position filtering is minimal—it returns informational data about job openings.
From the tool's definition Tool name 'filter_positions' combined with sibling tools ('match_by_major', 'personal_match', 'get_position_detail', 'get_statistics') indicates data retrieval and querying operations. Server purpose is 'querying and matching' examination positions.
Attacks that exploit this kind of access
filter_positions. 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 filter_positions: 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.
filter_positions 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 filter_positions 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 filter_positions. 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.
filter_positions 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 →