agent_web_reader
Paid (x402, $0.002 USDC on Base). Fetch any http(s) URL and return clean readable text, title/description/canonical, and outbound links as JSON — the data an agent ingests on each step of a crawl/RAG loop.
This record as markdown: /tools/dev-charliemorrison-agent-web-reader/agent-web-reader.md
What agent_web_reader does on Agent Web Reader
AI agents call agent_web_reader to retrieve information from Agent Web Reader 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 | Absolute http(s) URL to fetch and extract (e.g. 'https://example.com/article') |
x402_payment | string | — | Base64 X-PAYMENT header from your x402 wallet (omit to get the payment challenge) |
Parameters from the server's own tool schema.
Why agent_web_reader is rated Low
This tool retrieves and reads web content, returning structured data for consumption. It has no side effects on the target systems or data stores. The financial component (paid service at $0.002 USDC per call) is a cost to the caller, not a financial transaction moving money between parties or committing obligations, so it does not qualify as Financial category.
From the tool's definition Tool description states it 'Fetch[es]...URL and return[s] clean readable text, title/description/canonical, and outbound links as JSON' — a retrieval operation with no modification or deletion of data.
Risk signalsAccepts URL/endpoint input (url)
Attacks that exploit this kind of access
The rule that runs agent_web_reader safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Agent Web Reader, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For agent_web_reader, this is the rule to start with:
agent_web_reader 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 Agent Web Reader, apply this rule, and every agent_web_reader call is checked against it from then on.
Questions about agent_web_reader
Paid (x402, $0.002 USDC on Base). Fetch any http(s) URL and return clean readable text, title/description/canonical, and outbound links as JSON — the data an agent ingests on each step of a crawl/RAG loop. It is categorised as a Read tool in the Agent Web Reader MCP Server, which means it retrieves data without modifying state.
agent_web_reader accepts 2 parameters: url, x402_payment. Required: url. The full parameter table on this page comes from the server's own tool schema.
Register the Agent Web Reader MCP server in PolicyLayer and add a rule for agent_web_reader: 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 Agent Web Reader. Nothing to install.
agent_web_reader 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 agent_web_reader 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 agent_web_reader. 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.
agent_web_reader is provided by the Agent Web Reader MCP server (https://x402.charliemorrison.dev/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Agent Web Reader, and thousands of servers like it.
This server
Across the catalogue