show_file

THE RISK

Low Risk

Why show_file needs a policy

This tool retrieves and displays file data without creating, modifying, deleting, or executing code. It is a read-only operation with no side effects. Severity is low because file reading has minimal blast radius unless the system exposes highly sensitive credentials or source code, which would be a deployment/configuration issue rather than a tool design issue.

From the tool's definition Tool name 'show_file' and description 'Displays content of a file' indicate retrieval of file contents without modification or execution. The line range specification is for querying purposes only.

Documented attack patterns abuse exactly the kind of access show_file gives an agent:

POLICY

How to control show_file

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Tools, and nothing reaches the server without passing your rules. This is the rule we recommend for show_file:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "show_file": {}
  }
}

show_file is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register MCP Tools — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More MCP Tools tools

Execute execute_shell_command Executes a command with support for both secure list mode and shell operator mode. Write edit_file Atomically edits a file using string replacements and/or line operations with simplified f Write write_file Writes content to a file, creating directories if necessary. Read fetch_page Fetches web page text via Chromium PDF conversion and marker text extraction. Read search_in_file Searches for regex patterns in a file, returning matches with optional context.

All 6 MCP Tools tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about show_file

What does the show_file tool do? +

Displays content of a file with flexible line range specification. It is categorised as a Read tool in the MCP Tools MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on show_file? +

Register the MCP Tools MCP server in PolicyLayer and add a rule for show_file: 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 MCP Tools. Nothing to install.

What risk level is show_file? +

show_file is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit show_file? +

Yes. Add a rate_limit block to the show_file 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.

How do I block show_file completely? +

Set action: deny in the PolicyLayer policy for show_file. 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.

What MCP server provides show_file? +

show_file is provided by the MCP Tools MCP server (zbigniewtomanek/my-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP Tools tool call.

Start from MCP Tools, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →