// MCP TOOL REFERENCE

hub_execute

Execute a pre-configured hub tool for the current site. After navigating, the response will list available tool names and their arguments. Use this tool to run them.

ServerMoltBrowser MCP Server
CategoryExecute

How to control hub_execute ↓

WHAT IT DOES

What hub_execute does on MoltBrowser MCP Server

AI agents invoke hub_execute to trigger actions in MoltBrowser 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.

THE RISK

High Risk

Why hub_execute needs a policy

This tool executes arbitrary pre-configured browser automation tools selected from a community hub. While individual sibling tools are Read or Write operations, hub_execute acts as a dispatcher that runs these tools dynamically.

From the tool's definition Tool description states 'Execute a pre-configured hub tool' and 'Use this tool to run them' - the verb 'execute' combined with dynamic invocation of pre-configured tools from a community hub means the actual effects depend on which tool is selected and its…

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

POLICY

How to control hub_execute

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "hub_execute": {
      "limits": [
        {
          "counter": "hub_execute_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

hub_execute 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.

Create a free account and register MoltBrowser 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.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More MoltBrowser MCP Server tools

Destructive contribute_delete-tool Delete a specific tool from a WebMCP Hub config. The config owner or the tool\ Execute click-compose-button Click the compose/new tweet button to open the tweet editor Execute click-post-button Click the Post button to submit the tweet Write contribute_vote-on-tool Upvote or downvote a tool within a WebMCP Hub config. Each user gets one vote per tool — v Write fill-search Fill the search input field with a query. After calling this, use browser_press_key({ key: Write fill-tweet-text Fill the tweet text area with content Read get-article Get the main article text Read get-posts Get all visible posts on the page

All 9 MoltBrowser MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in MoltBrowser MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about hub_execute

What does the hub_execute tool do? +

Execute a pre-configured hub tool for the current site. After navigating, the response will list available tool names and their arguments. Use this tool to run them. It is categorised as a Execute tool in the MoltBrowser 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 hub_execute? +

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

What risk level is hub_execute? +

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

Can I rate-limit hub_execute? +

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

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

hub_execute is provided by the MoltBrowser MCP Server MCP server (joakim-sael/moltbrowser). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MoltBrowser MCP Server tool call.

Start from MoltBrowser 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 →

Free to start. No card required.

9 MoltBrowser MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.