call_webmcp_tool
Invoke a WebMCP tool on a connected origin. The tool is executed in the browser page context via page.evaluate(). Args are validated for suspicious patterns and results are scanned for anomalies. Use list_webmcp_tools to see available tools first.
This record as markdown: /tools/io-github-homenshum-nodebench/call-webmcp-tool.md
What call_webmcp_tool does on Nodebench
AI agents invoke call_webmcp_tool 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 call_webmcp_tool is rated High
This tool invokes arbitrary WebMCP tools in a browser context using page.evaluate(), which can execute JavaScript code and trigger external operations. While the description mentions argument validation and result scanning for anomalies, these are mitigations rather than categorical constraints.
From the tool's definition tool is executed in the browser page context via page.evaluate(); invoke, execute, and browser actions directly indicate Execute category
Attacks that exploit this kind of access
The rule that runs call_webmcp_tool 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 call_webmcp_tool, this is the rule to start with:
call_webmcp_tool 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 call_webmcp_tool call is checked against it from then on.
Questions about call_webmcp_tool
Invoke a WebMCP tool on a connected origin. The tool is executed in the browser page context via page.evaluate(). Args are validated for suspicious patterns and results are scanned for anomalies. Use list_webmcp_tools to see available tools first. 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 call_webmcp_tool: 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.
call_webmcp_tool 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 call_webmcp_tool 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 call_webmcp_tool. 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.
call_webmcp_tool 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