AI agents call fs_read 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.
fs_read retrieves or queries filesystem data without side effects. It is analogous to operations like 'cat', 'stat', or similar read-only filesystem commands. No data is created, modified, or deleted. Confidence is high despite empty description because the tool name explicitly indicates a read operation and context from sibling tools confirms the semantic categorization.
From the tool's definition Tool name is 'fs_read' which indicates reading filesystem content. Sibling tools include destructive (fs_rm), write (fs_write, fs_mkdir), and execute (shell_run) operations, establishing a clear pattern where 'fs_read' fits the read category.
Attacks that exploit this kind of access
fs_read. 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 fs_read: 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.
fs_read 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 fs_read 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 fs_read. 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.
fs_read 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 →