AI agents call search to retrieve information from Jobs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries data by keyword across multiple fields without creating, modifying, deleting, or executing external operations. The search functionality is a standard Read operation that returns filtered query results with no irreversible effects or code execution. Low severity because misuse would only expose information already in the database, not compromise data integrity or trigger external actions.
From the tool's definition Tool performs a search operation across MongoDB healthcare jobs collection fields (client name, location, title, description, and notes) and returns matching results.
Attacks that exploit this kind of access
Search care jobs by a keyword across client name, location, title, description, and notes. It is categorised as a Read tool in the Jobs MCP Server, which means it retrieves data without modifying state.
Register the Jobs MCP server in PolicyLayer and add a rule for search: 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 Jobs. Nothing to install.
search 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 search 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 search. 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.
search is provided by the Jobs MCP server (xhrusvin/jobs-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 →