Parse a resume file to extract information
AI agents call parseResume to retrieve information from MCP Resume & Email Assistant without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Parsing a resume is a read/extraction operation: it takes an input file and returns structured information. No data is created, modified, or deleted. However, severity is medium because resume files contain sensitive PII (name, address, employment history, etc.), so misuse could lead to privacy exposure.
From the tool's definition 'Parse a resume file to extract information' — the tool reads and processes a file to extract data, with no indication of writing, executing, or destructive operations.
Attacks that exploit this kind of access
Parse a resume file to extract information. It is categorised as a Read tool in the MCP Resume & Email Assistant MCP Server, which means it retrieves data without modifying state.
Register the MCP Resume & Email Assistant MCP server in PolicyLayer and add a rule for parseResume: 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 Resume & Email Assistant. Nothing to install.
parseResume 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 parseResume 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 parseResume. 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.
parseResume is provided by the MCP Resume & Email Assistant MCP server (thambimuthuanush24/mcp-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 →