Search across all projects, tasks, documents, and conversations with intelligent ranking
AI agents call universal_search to retrieve information from Helios-9 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 and queries data across multiple resource types without creating, modifying, deleting, or executing operations. It is a classic Read operation with low blast radius—misuse would only expose information the agent can already access.
From the tool's definition Tool name 'universal_search' combined with description 'Search across all projects, tasks, documents, and conversations' indicates a read-only retrieval operation.
Attacks that exploit this kind of access
Search across all projects, tasks, documents, and conversations with intelligent ranking. It is categorised as a Read tool in the Helios-9 MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Helios-9 MCP Server MCP server in PolicyLayer and add a rule for universal_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 Helios-9 MCP Server. Nothing to install.
universal_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 universal_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 universal_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.
universal_search is provided by the Helios-9 MCP Server MCP server (jakedx6/helios9-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 →