Viewing the response/invitation
AI agents call get-negotiation-item to retrieve information from HeadHunter API MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries existing negotiation data (responses/invitations) without creating, modifying, deleting, or executing any side effects. It is a pure read operation on recruitment platform data.
From the tool's definition Tool name and description: 'get-negotiation-item' with purpose 'Viewing the response/invitation' — explicitly a viewing/retrieval operation with no mutation.
Attacks that exploit this kind of access
Viewing the response/invitation. It is categorised as a Read tool in the HeadHunter API MCP Server MCP Server, which means it retrieves data without modifying state.
Register the HeadHunter API MCP Server MCP server in PolicyLayer and add a rule for get-negotiation-item: 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 HeadHunter API MCP Server. Nothing to install.
get-negotiation-item 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 get-negotiation-item 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 get-negotiation-item. 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.
get-negotiation-item is provided by the HeadHunter API MCP Server MCP server (sargonpiraev/hh-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 →