AI agents call view_position to retrieve information from Hiring without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads and returns job description data. It does not create, modify, delete, or execute any operations. The blast radius of misuse is minimal—an agent could retrieve position details it shouldn't access, but this causes no irreversible harm. Classified as Read with low severity.
From the tool's definition Tool name 'view_position' and description 'Returns the full job description' indicate data retrieval with no side effects. The action is querying/fetching existing job posting information.
Attacks that exploit this kind of access
Returns the full job description for a position. Pass the posting_id from browse_positions. It is categorised as a Read tool in the Hiring MCP Server, which means it retrieves data without modifying state.
Register the Hiring MCP server in PolicyLayer and add a rule for view_position: 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 Hiring. Nothing to install.
view_position 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 view_position 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 view_position. 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.
view_position is provided by the Hiring MCP server (meetvaghani12/hiring_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 →