query_dataview · Obsidian MCP: Risk & Policy

WHAT IT DOES

What query_dataview does on Obsidian

AI agents invoke query_dataview to trigger actions in Obsidian. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why query_dataview needs a policy

This tool executes arbitrary query language statements (LIST/TABLE/TASK) against the vault. While the described query types are read-oriented, executing arbitrary DQL queries via a plugin represents an Execute-level action — the query engine runs code/logic against the vault's data.

From the tool's definition "Run a Dataview DQL query" — executes arbitrary DQL queries against the vault using the Dataview plugin

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

query_dataview Rate-limited

query_dataview stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "query_dataview": {
      "limits": [
        {
          "counter": "query_dataview_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Obsidian, so you can run agents against it safely.

FAQ

Questions about query_dataview

What does the query_dataview tool do? +

Run a Dataview DQL query (LIST / TABLE / TASK) against the vault. Requires the Dataview plugin installed in the vault. Powerful for structured questions like. It is categorised as a Execute tool in the Obsidian MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on query_dataview? +

Register the Obsidian MCP server in PolicyLayer and add a rule for query_dataview: 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 Obsidian. Nothing to install.

What risk level is query_dataview? +

query_dataview is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit query_dataview? +

Yes. Add a rate_limit block to the query_dataview 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.

How do I block query_dataview completely? +

Set action: deny in the PolicyLayer policy for query_dataview. 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.

What MCP server provides query_dataview? +

query_dataview is provided by the Obsidian MCP server (yanxue06/obsidian-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.