runway_getTask

THE RISK

Low Risk

Why runway_getTask needs a policy

This tool retrieves task status and details from the Runway API without creating, modifying, deleting, or executing operations. It is a simple data query operation with no side effects or blast radius if misused by an AI agent.

From the tool's definition Tool name 'runway_getTask' and description 'Get the details of a task' indicate a retrieval operation with no modification or execution of external processes.

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

POLICY

How to control runway_getTask

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "runway_getTask": {}
  }
}

runway_getTask is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Runway API MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Runway API MCP Server tools

Destructive runway_cancelTask Deletes or cancels a given task. Execute runway_editVideo Edit a video using Runway Aleph. promptText is a prompt for the video. videoUri takes in a Execute runway_generateVideo Generate a video from an image and a text prompt. Accepted ratios are 1280:720, 720:1280, Write runway_generateImage Generate an image from a text prompt and optional reference images. Available ratios are 1 Write runway_upscaleVideo Upscale a video to a higher resolution. videoUri takes in a url of a video or a data uri o Read runway_getOrg Returns details like credit balance, usage details, and organization information.

All 7 Runway API MCP Server tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about runway_getTask

What does the runway_getTask tool do? +

Get the details of a task, if the task status is. It is categorised as a Read tool in the Runway API MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on runway_getTask? +

Register the Runway API MCP Server MCP server in PolicyLayer and add a rule for runway_getTask: 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 Runway API MCP Server. Nothing to install.

What risk level is runway_getTask? +

runway_getTask is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit runway_getTask? +

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

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

runway_getTask is provided by the Runway API MCP Server MCP server (runwayml/runway-api-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Runway API MCP Server tool call.

Start from Runway API MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →