Fetch any URL and return its readable text — the catch-all for sources without a
AI agents call fetch_text to retrieve information from Philosophy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves text content from URLs and returns it for reading. There are no side effects: it does not modify, delete, execute code, move money, or trigger external operations beyond fetching. The 'catch-all' nature suggests it complements other retrieval tools but remains fundamentally a data-fetching operation.
From the tool's definition Tool name 'fetch_text' and description 'Fetch any URL and return its readable text' indicate data retrieval with no modification or deletion.
Attacks that exploit this kind of access
Fetch any URL and return its readable text — the catch-all for sources without a. It is categorised as a Read tool in the Philosophy MCP Server, which means it retrieves data without modifying state.
Register the Philosophy MCP server in PolicyLayer and add a rule for fetch_text: 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 Philosophy. Nothing to install.
fetch_text 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 fetch_text 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 fetch_text. 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.
fetch_text is provided by the Philosophy MCP server (sea9401/philosophy-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 →