AI agents call list_libraries_tool to retrieve information from Openground without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve or enumerate libraries without side effects. Although the description is empty, the name and server purpose (documentation search) strongly suggest a read operation. The absence of language indicating creation, modification, deletion, execution, or financial activity, combined with sibling tools that are clearly read-only, supports the Read category.
From the tool's definition Tool name 'list_libraries_tool' indicates retrieval/enumeration of library information. Tool description is empty, but the naming pattern and context (on-device documentation search) suggest it lists available libraries without modifying them.
Documented attack patterns abuse exactly the kind of access list_libraries_tool gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Openground, and nothing reaches the server without passing your rules. This is the rule we recommend for list_libraries_tool:
{
"version": "1",
"default": "deny",
"tools": {
"list_libraries_tool": {}
}
}list_libraries_tool is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
list_libraries_tool. It is categorised as a Read tool in the Openground MCP Server, which means it retrieves data without modifying state.
Register the Openground MCP server in PolicyLayer and add a rule for list_libraries_tool: 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 Openground. Nothing to install.
list_libraries_tool 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 list_libraries_tool 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 list_libraries_tool. 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.
list_libraries_tool is provided by the Openground MCP server (poweroutlet2/openground). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 3 Openground tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
3 Openground tools catalogued and risk-classified — across an index of 42,500+ MCP servers.