openehr_query_adhoc

A execute tool on the openEHR MCP server.

SERVERopenEHR MCP Server SOURCEdeak-ai/openehr-mcp-server

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/deak-ai-openehr-mcp-server/openehr-query-adhoc.md

WHAT IT DOES

What openehr_query_adhoc does on openEHR MCP Server

AI agents invoke openehr_query_adhoc to trigger actions in openEHR MCP Server. 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.

RISK

Why openehr_query_adhoc is rated High

Ad-hoc query execution typically allows arbitrary query strings to be submitted at runtime. In the context of this openEHR server, this maps to AQL (Archetype Query Language) execution, which can read or potentially modify data depending on query content. Since the description is empty, confidence is reduced, but 'adhoc' queries are canonically Execute-category — running arbitrary code/queries against a system.

From the tool's definition Tool name 'openehr_query_adhoc' — 'adhoc' strongly implies execution of arbitrary/user-supplied AQL queries against the openEHR server; server description mentions 'executing AQL queries'

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs openehr_query_adhoc safely

PolicyLayer is an MCP gateway: it sits between your AI agents and openEHR MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For openehr_query_adhoc, this is the rule to start with:

openehr_query_adhoc Rate-limited

openehr_query_adhoc 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": {
    "openehr_query_adhoc": {
      "limits": [
        {
          "counter": "openehr_query_adhoc_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect openEHR MCP Server, apply this rule, and every openehr_query_adhoc call is checked against it from then on.

FAQ

Questions about openehr_query_adhoc

What does the openehr_query_adhoc tool do? +

openehr_query_adhoc is a execute tool on the openEHR MCP Server MCP server. It is categorised as a Execute tool in the openEHR MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on openehr_query_adhoc? +

Register the openEHR MCP Server MCP server in PolicyLayer and add a rule for openehr_query_adhoc: 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 openEHR MCP Server. Nothing to install.

What risk level is openehr_query_adhoc? +

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

Can I rate-limit openehr_query_adhoc? +

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

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

openehr_query_adhoc is provided by the openEHR MCP Server MCP server (deak-ai/openehr-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on openEHR MCP Server, and thousands of servers like it.

This server

All 13 openEHR MCP Server tools → High-risk tools on this server →

Across the catalogue

aroflo_query_zone on AroFlo MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →