High Risk →

affinity_start_app

Start Affinity Designer application / Affinity Designerアプリケーションを開始

How to control affinity_start_app ↓

What affinity_start_app does on MCP Affinity Designer Server

AI agents invoke affinity_start_app to trigger actions in MCP Affinity Designer 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.

High Risk

Why affinity_start_app needs a policy

Starting an application is an Execute action: it triggers an external process whose downstream effects are determined by what the agent does with the running application (as evidenced by sibling tools like affinity_apply_effect, affinity_delete_layer, affinity_close_document).

From the tool's definition Tool description states 'Start Affinity Designer application' — this launches an external application, which is an external operation whose effects depend on system state and subsequent user/agent actions.

Documented attack patterns abuse exactly the kind of access affinity_start_app gives an agent:

How to control affinity_start_app

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Affinity Designer Server, and nothing reaches the server without passing your rules. This is the rule we recommend for affinity_start_app:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "affinity_start_app": {
      "limits": [
        {
          "counter": "affinity_start_app_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

affinity_start_app 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.

  1. Create a free account and register MCP Affinity Designer Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RATE-LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about affinity_start_app

What does the affinity_start_app tool do? +

Start Affinity Designer application / Affinity Designerアプリケーションを開始. It is categorised as a Execute tool in the MCP Affinity Designer 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 affinity_start_app? +

Register the MCP Affinity Designer Server MCP server in PolicyLayer and add a rule for affinity_start_app: 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 Affinity Designer Server. Nothing to install.

What risk level is affinity_start_app? +

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

Can I rate-limit affinity_start_app? +

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

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

affinity_start_app is provided by the MCP Affinity Designer Server MCP server (szgk/mcp-affinity-designer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP Affinity Designer Server tool call.

Start from MCP Affinity Designer Server, 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.

28 MCP Affinity Designer Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.