connect_webmcp_origin
Connect to a WebMCP-enabled website via Playwright. Navigates to the URL, intercepts navigator.modelContext tool registrations, and makes discovered tools available for invocation via call_webmcp_tool. Requires Playwright (npm install playwright && npx playwright install chromium). Use check_webm...
This record as markdown: /tools/io-github-homenshum-nodebench/connect-webmcp-origin.md
What connect_webmcp_origin does on Nodebench
AI agents invoke connect_webmcp_origin to trigger actions in Nodebench. 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 connect_webmcp_origin is rated High
This tool launches a browser (Playwright/Chromium), navigates to arbitrary URLs, and intercepts/registers external tools for invocation. It triggers external browser operations whose effects depend on the URL argument, and opens the door to further tool invocations via call_webmcp_tool.
From the tool's definition Connect to a WebMCP-enabled website via Playwright. Navigates to the URL, intercepts navigator.modelContext tool registrations, and makes discovered tools available for invocation
Attacks that exploit this kind of access
The rule that runs connect_webmcp_origin safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For connect_webmcp_origin, this is the rule to start with:
connect_webmcp_origin 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Nodebench, apply this rule, and every connect_webmcp_origin call is checked against it from then on.
Questions about connect_webmcp_origin
Connect to a WebMCP-enabled website via Playwright. Navigates to the URL, intercepts navigator.modelContext tool registrations, and makes discovered tools available for invocation via call_webmcp_tool. Requires Playwright (npm install playwright && npx playwright install chromium). Use check_webmcp_setup to verify prerequisites. It is categorised as a Execute tool in the Nodebench MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Nodebench MCP server in PolicyLayer and add a rule for connect_webmcp_origin: 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 Nodebench. Nothing to install.
connect_webmcp_origin is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the connect_webmcp_origin 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.
Set action: deny in the PolicyLayer policy for connect_webmcp_origin. 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.
connect_webmcp_origin is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nodebench, and thousands of servers like it.
Across the catalogue