查询当前测试进度。需要传入测试会话状态。
AI agents call get_progress to retrieve information from MBTI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves progress information from an MBTI test session. It performs a read-only operation to check status, similar to 'get' or 'fetch' operations. No data is created, modified, deleted, or executed. The blast radius is minimal as it only accesses existing session state information for the requesting user.
From the tool's definition Tool name 'get_progress' combined with description '查询当前测试进度' (query current test progress) indicates retrieval of existing test session state data without modification or side effects.
Attacks that exploit this kind of access
查询当前测试进度。需要传入测试会话状态。. It is categorised as a Read tool in the MBTI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MBTI MCP Server MCP server in PolicyLayer and add a rule for get_progress: 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 MBTI MCP Server. Nothing to install.
get_progress 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_progress 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_progress. 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_progress is provided by the MBTI MCP Server MCP server (wenyili/mbti-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 →