AI agents call lookup_fact to retrieve information from Grounded without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool is part of a server designed for querying and monitoring data across package registries and cloud services. Even without a description, contextual evidence from sibling tools and the server's stated purpose (technical lookups, monitoring) indicates this is a read-only data retrieval function. No creation, modification, deletion, execution, or financial operations are implied.
From the tool's definition Tool named 'lookup_fact' with empty description; sibling tools ('check_downloads', 'check_package_version', 'check_service_status') are all Read operations that retrieve data without side effects.
Attacks that exploit this kind of access
lookup_fact. It is categorised as a Read tool in the Grounded MCP Server, which means it retrieves data without modifying state.
Register the Grounded MCP server in PolicyLayer and add a rule for lookup_fact: 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 Grounded. Nothing to install.
lookup_fact 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 lookup_fact 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 lookup_fact. 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.
lookup_fact is provided by the Grounded MCP server (nghizas/grounded-mcp). 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 →