Universal search across multiple Passgage resources
AI agents call passgage_search to retrieve information from Passgage MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches existing data without modifying, deleting, or executing operations. Even though it can search 'multiple resources' across a workforce management system, the core function is retrieval. Confidence is high because the description clearly indicates a search/query operation.
From the tool's definition Tool name 'passgage_search' and description 'Universal search across multiple Passgage resources' indicate a query/retrieval operation with no side effects. The term 'search' is a classic read operation that retrieves existing data.
Attacks that exploit this kind of access
Universal search across multiple Passgage resources. It is categorised as a Read tool in the Passgage MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Passgage MCP Server MCP server in PolicyLayer and add a rule for passgage_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 Passgage MCP Server. Nothing to install.
passgage_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 passgage_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 passgage_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.
passgage_search is provided by the Passgage MCP Server MCP server (passgage/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 →