Fetch the raw HTML source code and page information of a webpage.
AI agents call get_webpage_source to retrieve information from Spider MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves webpage source code without side effects, modification, or execution of code. It is a passive data retrieval operation similar to viewing page source in a browser. No data is created, deleted, modified, or executed—only read. Low severity because HTML source code is typically public and the operation has minimal blast radius.
From the tool's definition Tool fetches 'raw HTML source code and page information' with no modification capability. The verb 'Fetch' and description emphasize data retrieval only.
Attacks that exploit this kind of access
Fetch the raw HTML source code and page information of a webpage. It is categorised as a Read tool in the Spider MCP MCP Server, which means it retrieves data without modifying state.
Register the Spider MCP server in PolicyLayer and add a rule for get_webpage_source: 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 Spider MCP. Nothing to install.
get_webpage_source 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 get_webpage_source 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 get_webpage_source. 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.
get_webpage_source is provided by the Spider MCP server (yc9yc/spider-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →