AI agents call yapi_get_project to retrieve information from Mcp Yapi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves project metadata from the YApi API documentation platform without making any changes to data. It queries and returns static information (project name, description, members) with no side effects. This is a classic Read operation with low severity since it only accesses documentation metadata that is typically non-sensitive in nature.
From the tool's definition Tool description states '获取YApi项目的基本信息' (get basic information of YApi project), including project name, description, and members.
Attacks that exploit this kind of access
获取YApi项目的基本信息,包括项目名称、描述、成员等. It is categorised as a Read tool in the Mcp Yapi MCP Server, which means it retrieves data without modifying state.
Register the Mcp Yapi MCP server in PolicyLayer and add a rule for yapi_get_project: 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 Yapi. Nothing to install.
yapi_get_project 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 yapi_get_project 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 yapi_get_project. 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.
yapi_get_project is provided by the Mcp Yapi MCP server (tstonelee/mcp-yapi-server). 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 →