start_publishing_webserver · SEED MCP: Risk & Policy

WHAT IT DOES

What start_publishing_webserver does on SEED MCP

AI agents invoke start_publishing_webserver to trigger actions in SEED 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.

WHY IT NEEDS A POLICY

Why start_publishing_webserver needs a policy

Starting a web server is an Execute action—it triggers an external operation (server startup) whose effects depend on system configuration and arguments. It's not a simple data retrieval (Read), nor is it creating/modifying data reversibly (Write), nor is it destructive. The high severity reflects that misconfiguring or unexpectedly starting a production publishing webserver could disrupt services.

From the tool's definition Tool name 'start_publishing_webserver' indicates it starts/triggers a web server process. Sibling tools include 'get_publishing_webserver_status' and 'show_seed_publishing_interface', suggesting this controls server infrastructure.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_publishing_webserver Rate-limited

start_publishing_webserver 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": {
    "start_publishing_webserver": {
      "limits": [
        {
          "counter": "start_publishing_webserver_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 SEED MCP, so you can run agents against it safely.

FAQ

Questions about start_publishing_webserver

What does the start_publishing_webserver tool do? +

start_publishing_webserver. It is categorised as a Execute tool in the SEED 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 start_publishing_webserver? +

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

What risk level is start_publishing_webserver? +

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

Can I rate-limit start_publishing_webserver? +

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

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

start_publishing_webserver is provided by the SEED MCP server (sancovp/seed-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.