webcontext_scrape
Fetch one URL as clean Markdown Fetch one URL and return clean, main-content Markdown plus normalized metadata, links, and images. Backed by a privately deployed webclaw-server instance; upstream implementation details are never exposed. HTTP: GET /v1/webcontext/scrape
This record as markdown: /tools/com-replynodes-mcp/webcontext-scrape.md
What webcontext_scrape does on ReplyNodes
AI agents call webcontext_scrape to retrieve information from ReplyNodes without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
url | string | Yes | Target URL to fetch. Rejected if it is malformed, uses a disallowed scheme, or resolves to a private/loopback/link-local/cloud-metadata address. |
exclude_selectors | string | — | Comma-separated CSS selectors to exclude (e.g. "nav,.sidebar,footer"). |
include_selectors | string | — | Comma-separated CSS selectors to include (e.g. "article,.content"). |
Parameters from the server's own tool schema.
Why webcontext_scrape is rated Low
Tool fetches and returns web content without modifying, deleting, or executing code on target systems.
From the tool's definition Fetch one URL as clean Markdown; retrieves main-content, metadata, links, images.
Risk signalsAccepts URL/endpoint input (url)
Attacks that exploit this kind of access
The rule that runs webcontext_scrape safely
PolicyLayer is an MCP gateway: it sits between your AI agents and ReplyNodes, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For webcontext_scrape, this is the rule to start with:
webcontext_scrape is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect ReplyNodes, apply this rule, and every webcontext_scrape call is checked against it from then on.
Questions about webcontext_scrape
Fetch one URL as clean Markdown Fetch one URL and return clean, main-content Markdown plus normalized metadata, links, and images. Backed by a privately deployed webclaw-server instance; upstream implementation details are never exposed. HTTP: GET /v1/webcontext/scrape. It is categorised as a Read tool in the ReplyNodes MCP Server, which means it retrieves data without modifying state.
webcontext_scrape accepts 3 parameters: url, exclude_selectors, include_selectors. Required: url. The full parameter table on this page comes from the server's own tool schema.
Register the ReplyNodes MCP server in PolicyLayer and add a rule for webcontext_scrape: 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 ReplyNodes. Nothing to install.
webcontext_scrape is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the webcontext_scrape 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 webcontext_scrape. 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.
webcontext_scrape is provided by the ReplyNodes MCP server (https://mcp.replynodes.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on ReplyNodes, and thousands of servers like it.
This server
Across the catalogue