从项目内容推断数据库。默认仅返回 { db }；当 include_evidence=true 时返回经过脱敏的证据统计（不含文件路径/内容）。
AI agents call infer_database to retrieve information from Yooztech Mcp Mysql without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and infers information about databases from project context without querying data, modifying databases, executing code, or causing destructive actions. The mechanism is analysis-based inference rather than direct database access.
From the tool's definition Tool performs inference from project context to identify databases, returning only database metadata ({ db }) or anonymized evidence statistics. No data retrieval, modification, deletion, or external execution occurs.
Attacks that exploit this kind of access
从项目内容推断数据库。默认仅返回 { db }；当 include_evidence=true 时返回经过脱敏的证据统计（不含文件路径/内容）。. It is categorised as a Read tool in the Yooztech Mcp Mysql MCP Server, which means it retrieves data without modifying state.
Register the Yooztech Mcp Mysql MCP server in PolicyLayer and add a rule for infer_database: 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 Yooztech Mcp Mysql. Nothing to install.
infer_database 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 infer_database 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 infer_database. 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.
infer_database is provided by the Yooztech Mcp Mysql MCP server (yooztech/mcp_mysql). 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 →