get_action

THE RISK

Low Risk

Why get_action needs a policy

The tool retrieves and inspects metadata about a GPU draw call event from an already-captured RenderDoc frame. It performs a query operation that returns data for analysis purposes. There is no indication of code execution, data modification, deletion, or external side effects. The action is purely informational, examining existing frame capture data.

From the tool's definition Tool name 'get_action' and description 'Get detailed information about a specific action/draw call' indicate retrieval of frame capture analysis data without modification or side effects.

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

POLICY

How to control get_action

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

policy.json

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

get_action 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 Renderdoc — 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 Renderdoc tools

Execute open_capture Open a RenderDoc capture (.rdc) file for analysis. Automatically closes any previ Execute set_event Navigate the replay to a specific event ID. This must be called before inspecting Write close_capture Close the currently open capture file and free resources. Write export_draw_textures Batch export all textures bound to a draw call's pixel shader. Args: Write export_mesh Export mesh data from a draw call as OBJ format. Uses post-vertex-shader data to Write save_render_target Save the current render target(s) at a specific event. Args: event_id Write save_texture Save a texture resource to an image file. Args: resource_id: The text Read analyze_bandwidth analyze_bandwidth

All 42 Renderdoc 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 get_action

What does the get_action tool do? +

Get detailed information about a specific action/draw call. Args: event_id: The event ID of the action to inspect. It is categorised as a Read tool in the Renderdoc MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_action? +

Register the Renderdoc MCP server in PolicyLayer and add a rule for get_action: 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 Renderdoc. Nothing to install.

What risk level is get_action? +

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

Can I rate-limit get_action? +

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

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

get_action is provided by the Renderdoc MCP server (linkingooo/renderdoc-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Renderdoc tool call.

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

CHECK YOUR STACK →