natural_language_query · MCP Beancount Tool MCP

WHAT IT DOES

What natural_language_query does on MCP Beancount Tool

AI agents invoke natural_language_query to trigger actions in MCP Beancount Tool. 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 natural_language_query needs a policy

The server description mentions 'answering natural-language questions via BeanQuery', suggesting this tool translates natural language into BeanQuery statements and executes them. BeanQuery can read data but may also support destructive operations. Given sibling tools include insert and remove transaction capabilities, and the tool executes arbitrary queries, Execute is the most appropriate category.

From the tool's definition Tool name 'natural_language_query' on a server that exposes 'query' (BeanQuery execution), 'insert_transaction', and 'remove_transaction' tools — description is empty and uninformative.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

natural_language_query Rate-limited

natural_language_query 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": {
    "natural_language_query": {
      "limits": [
        {
          "counter": "natural_language_query_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 MCP Beancount Tool, so you can run agents against it safely.

FAQ

Questions about natural_language_query

What does the natural_language_query tool do? +

natural_language_query. It is categorised as a Execute tool in the MCP Beancount Tool MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on natural_language_query? +

Register the MCP Beancount Tool MCP server in PolicyLayer and add a rule for natural_language_query: 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 MCP Beancount Tool. Nothing to install.

What risk level is natural_language_query? +

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

Can I rate-limit natural_language_query? +

Yes. Add a rate_limit block to the natural_language_query 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 natural_language_query completely? +

Set action: deny in the PolicyLayer policy for natural_language_query. 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 natural_language_query? +

natural_language_query is provided by the MCP Beancount Tool MCP server (onesvat/mcp-beancount). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.