serve_presentation · Slidev MCP Server MCP: Risk & Policy

WHAT IT DOES

What serve_presentation does on Slidev MCP Server

AI agents invoke serve_presentation to trigger actions in Slidev MCP 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.

WHY IT NEEDS A POLICY

Why serve_presentation needs a policy

Starting a development server is an Execute action because it runs external processes and operations rather than just reading or writing data. While not immediately destructive or financial, an agent misusing this could bind to unexpected ports, interfere with system services, expose internal content to the network, or consume system resources.

From the tool's definition Tool starts a local development server process ('Start a local Slidev development server') which executes server operations and opens browser previews—this triggers external operations whose effects depend on arguments (server binding, port selection, network…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

serve_presentation Rate-limited

serve_presentation 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": {
    "serve_presentation": {
      "limits": [
        {
          "counter": "serve_presentation_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Slidev MCP Server, so you can run agents against it safely.

FAQ

Questions about serve_presentation

What does the serve_presentation tool do? +

Start a local Slidev development server to preview the presentation in browser. Essential for reviewing presentations. It is categorised as a Execute tool in the Slidev MCP 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 serve_presentation? +

Register the Slidev MCP Server MCP server in PolicyLayer and add a rule for serve_presentation: 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 Slidev MCP Server. Nothing to install.

What risk level is serve_presentation? +

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

Can I rate-limit serve_presentation? +

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

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

serve_presentation is provided by the Slidev MCP Server MCP server (raykuonz/slidev-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.