run_tool

Run an AirMCP tool by name with JSON arguments. Use discover_tools first when the tool is not visible in tools/list.

SERVERAirMCP SOURCEairmcp

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/heznpc-airmcp/run-tool.md

WHAT IT DOES

What run_tool does on AirMCP

AI agents invoke run_tool to trigger actions in AirMCP. 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 run_tool is rated High

This is an Execute tool because it triggers external operations whose effects depend on arguments (the tool name and JSON parameters). The 'critical' severity reflects the extremely broad blast radius: an AI agent with access to run_tool could invoke any of 150+ tools, potentially including destructive actions (delete notes/reminders), financial operations (if any exist in the ecosystem), or sensitive reads (mail,…

From the tool's definition Tool description explicitly states 'Run an AirMCP tool by name with JSON arguments' — this is a meta-execution function that dynamically invokes other tools.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs run_tool safely

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

run_tool Rate-limited

run_tool 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": {
    "run_tool": {
      "limits": [
        {
          "counter": "run_tool_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 AirMCP, apply this rule, and every run_tool call is checked against it from then on.

FAQ

Questions about run_tool

What does the run_tool tool do? +

Run an AirMCP tool by name with JSON arguments. Use discover_tools first when the tool is not visible in tools/list. It is categorised as a Execute tool in the AirMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_tool? +

Register the Air MCP server in PolicyLayer and add a rule for run_tool: 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 AirMCP. Nothing to install.

What risk level is run_tool? +

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

Can I rate-limit run_tool? +

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

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

run_tool is provided by the Air MCP server (airmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Air, and thousands of servers like it.

This server

All 298 Air tools → High-risk tools on this server →

Across the catalogue

run on 0sec →shortcuts_run on Apple Apps MCP →run_emba_scan on EMBA-MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

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