Vault health, recent changes, and diagnostics. Modes: health — doc count, last commit date history — recent git log (filter by since, path_prefix) diagnostics — orphan notes, broken [[links]], missing frontmatter, stale Inbox items graph — wikilink graph: most connected, bridges, clusters, orphan...
AI agents call vault_status 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.
vault_status is purely informational and observational. It gathers diagnostic data, analyzes metadata, and reports on vault structure and performance. No data is created, modified, deleted, or irreversibly changed. No external code is executed. This is a classic Read operation with minimal blast radius if misused—an AI might retrieve unwanted information about vault contents, but cannot alter or destroy data.
From the tool's definition Tool provides vault diagnostics, health checks, and analysis: 'health' returns doc count and metadata; 'history' reads git logs; 'diagnostics' reports on notes and links; 'graph' analyzes connections; 'digest' categorizes notes by lifecycle; 'discovery' lists…
Documented attack patterns abuse exactly the kind of access vault_status 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 vault_status:
{
"version": "1",
"default": "deny",
"tools": {
"vault_status": {}
}
}vault_status 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.
Vault health, recent changes, and diagnostics. Modes: health — doc count, last commit date history — recent git log (filter by since, path_prefix) diagnostics — orphan notes, broken [[links]], missing frontmatter, stale Inbox items graph — wikilink graph: most connected, bridges, clusters, orphans digest — garden lifecycle: seeds, sprouts, growing, mature, dormant, withering discovery — recent extractions, new concepts, surprising connections, queue depth perf — per-tool latency percentiles, write queue depth, discovery backlog. 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 vault_status: 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.
vault_status 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 vault_status 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 vault_status. 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.
vault_status 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.