Read multiple notes at once. Accepts a glob pattern or comma-separated paths. Examples:
AI agents call multi_get to retrieve information from Grove without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data from the Obsidian vault with no side effects. It reads multiple notes in batch but does not create, modify, delete, or execute code. The glob pattern and path matching are purely for data selection, not transformation. Severity is low because read-only access to user's own notes has minimal blast radius even if misused.
From the tool's definition Tool name is 'multi_get' and description states 'Read multiple notes at once.' The function accepts 'a glob pattern or comma-separated paths' to retrieve data without modification.
Documented attack patterns abuse exactly the kind of access multi_get gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Grove, and nothing reaches the server without passing your rules. This is the rule we recommend for multi_get:
{
"version": "1",
"default": "deny",
"tools": {
"multi_get": {}
}
}multi_get 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.
Read multiple notes at once. Accepts a glob pattern or comma-separated paths. Examples:. It is categorised as a Read tool in the Grove MCP Server, which means it retrieves data without modifying state.
Register the Grove MCP server in PolicyLayer and add a rule for multi_get: 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 Grove. Nothing to install.
multi_get 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 multi_get 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 multi_get. 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.
multi_get is provided by the Grove MCP server (jmilinovich/grove). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Grove, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 Grove tools catalogued and risk-classified — across an index of 43,000+ MCP servers.