unifi_execute

Execute a UniFi tool by name. Use unifi_tool_index to discover available tools first.

SERVERUniFi Access MCP SOURCEpypi:unifi-protect-mcp

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/io-github-sirkirby-unifi-access-mcp/unifi-execute.md

WHAT IT DOES

What unifi_execute does on UniFi Access MCP

AI agents invoke unifi_execute to trigger actions in UniFi Access MCP. 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 unifi_execute is rated High

This is a meta-tool that executes other UniFi tools by name. The 'Execute' category applies because it runs operations whose effects depend on which tool name is passed as an argument. In the context of a physical access control system (doors, credentials, visitors), this could trigger actions like unlocking doors, creating unauthorized credentials, or deleting visitor records.

From the tool's definition Tool name 'unifi_execute' combined with description 'Execute a UniFi tool by name' directly indicates code/command execution. The phrase 'Execute a UniFi tool' is the key indicator.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs unifi_execute safely

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

unifi_execute Rate-limited

unifi_execute 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": {
    "unifi_execute": {
      "limits": [
        {
          "counter": "unifi_execute_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 UniFi Access MCP, apply this rule, and every unifi_execute call is checked against it from then on.

FAQ

Questions about unifi_execute

What does the unifi_execute tool do? +

Execute a UniFi tool by name. Use unifi_tool_index to discover available tools first. It is categorised as a Execute tool in the UniFi Access MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on unifi_execute? +

Register the UniFi Access MCP server in PolicyLayer and add a rule for unifi_execute: 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 UniFi Access MCP. Nothing to install.

What risk level is unifi_execute? +

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

Can I rate-limit unifi_execute? +

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

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

unifi_execute is provided by the UniFi Access MCP server (pypi:unifi-protect-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on UniFi Access, and thousands of servers like it.

This server

All 272 UniFi Access tools → High-risk tools on this server →

Across the catalogue

claude_execute on Claude Bridge →execute_test_case on Percepta MCP Server → All high-risk MCP tools → The MCP Attack Database →

Guides

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