根据关键词、职位、技能、经验等条件搜索和排序简历。
AI agents call search_resumes to retrieve information from Resume Filter 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 searches through resume data to return filtered results. It performs no data modification, deletion, or execution of external operations. The medium severity reflects that resumes contain personally identifiable information (PII) and sensitive employment data; unauthorized search access could expose confidential candidate information, though the tool itself is a safe Read operation.
From the tool's definition Tool description indicates 'search and rank resumes' based on 'keywords, position, skills, experience' — purely retrieval and filtering operations with no modification or deletion.
Attacks that exploit this kind of access
根据关键词、职位、技能、经验等条件搜索和排序简历。. It is categorised as a Read tool in the Resume Filter MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Resume Filter MCP Server MCP server in PolicyLayer and add a rule for search_resumes: 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 Resume Filter MCP Server. Nothing to install.
search_resumes 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 search_resumes 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 search_resumes. 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.
search_resumes is provided by the Resume Filter MCP Server MCP server (xinmu-wyb/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 →