AI agents call get_job_search_filters to retrieve information from Handshake without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to fetch filter metadata or configuration options for job searches (e.g., job type, location, salary range filters). It retrieves data without modifying, executing code, or causing side effects. The 'get_' prefix is consistent with Read category operations.
From the tool's definition Tool name 'get_job_search_filters' indicates retrieval of filter options for job search queries. No description provided, but context from sibling tools (search_jobs, get_job_details) suggests this retrieves metadata or options used to construct searches.
Attacks that exploit this kind of access
get_job_search_filters. It is categorised as a Read tool in the Handshake MCP Server, which means it retrieves data without modifying state.
Register the Handshake MCP server in PolicyLayer and add a rule for get_job_search_filters: 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 Handshake. Nothing to install.
get_job_search_filters 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_job_search_filters 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_job_search_filters. 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_job_search_filters is provided by the Handshake MCP server (sudhxnva/handshake-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 →