AI agents invoke query_base to trigger actions in Obsidian Mcp Pro. 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.
The description says 'Run a Base file', indicating this tool executes a file (likely a Dataview or similar query base file in Obsidian). Execution of arbitrary files/queries carries significant risk as an AI agent could run unintended code or queries. Categorized as Execute due to the 'run' action.
From the tool's definition "Run a Base file" — the tool explicitly runs/executes a file
Documented attack patterns abuse exactly the kind of access query_base gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Obsidian Mcp Pro, and nothing reaches the server without passing your rules. This is the rule we recommend for query_base:
{
"version": "1",
"default": "deny",
"tools": {
"query_base": {
"limits": [
{
"counter": "query_base_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} query_base 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.
Free to start. No card required.
Run a Base file. It is categorised as a Execute tool in the Obsidian Mcp Pro MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Obsidian Mcp Pro MCP server in PolicyLayer and add a rule for query_base: 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 Mcp Pro. Nothing to install.
query_base is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the query_base 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 query_base. 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.
query_base is provided by the Obsidian Mcp Pro MCP server (rps321321/obsidian-mcp-pro). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Obsidian Mcp Pro, 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.
41 Obsidian Mcp Pro tools catalogued and risk-classified — across an index of 43,000+ MCP servers.