AI agents call resuml_jobs_score to retrieve information from Resuml without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and analyzes existing data (job description text and resume) to produce a scoring/ranking output. No data is created, modified, deleted, or irreversibly changed. No code execution or external operations are triggered based on dynamic arguments. The operation is a pure analytical read with no side effects.
From the tool's definition Tool 'Score a single JD body against the resume' and 'ranked ATS breakdown' — performs analysis and comparison of provided job description text against resume data without modifying either document.
Attacks that exploit this kind of access
Score a single JD body against the resume. Use when the agent already has the JD text (e.g. user pasted a URL elsewhere) and just wants the ranked ATS breakdown without a fresh search. It is categorised as a Read tool in the Resuml MCP Server, which means it retrieves data without modifying state.
Register the Resuml MCP server in PolicyLayer and add a rule for resuml_jobs_score: 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 Resuml. Nothing to install.
resuml_jobs_score 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 resuml_jobs_score 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 resuml_jobs_score. 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.
resuml_jobs_score is provided by the Resuml MCP server (resuml). 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 →