AI agents call web_fetch to retrieve information from Emcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Web fetching is fundamentally a read operation—it retrieves data from the internet. However, severity is medium rather than low because: (1) depending on implementation, it could be used to exfiltrate sensitive data or interact with unintended endpoints; (2) the empty description creates ambiguity about whether it supports arbitrary URLs or has protections; (3) context shows this server permits shell execution and…
From the tool's definition Tool name 'web_fetch' indicates retrieval of web content. Description is empty, limiting direct evidence, but the name and sibling context (filesystem operations, shell execution) suggest this retrieves external data without modification.
Attacks that exploit this kind of access
web_fetch. It is categorised as a Read tool in the Emcp MCP Server, which means it retrieves data without modifying state.
Register the E MCP server in PolicyLayer and add a rule for web_fetch: 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 Emcp. Nothing to install.
web_fetch 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 web_fetch 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 web_fetch. 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.
web_fetch is provided by the E MCP server (slezica/emcp). 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 →