fetch_tool

THE RISK

Low Risk

Why fetch_tool needs a policy

This tool retrieves existing tool metadata and source code without modifying, executing, or deleting anything. It is a straightforward query operation with no side effects. Severity is low because fetching tool code is informational and read-only, with minimal risk of misuse causing damage.

From the tool's definition Tool name 'fetch_tool' combined with description 'Fetch a tool, including its source code' indicates data retrieval. The verb 'fetch' and the absence of modification language confirm read-only behavior.

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

POLICY

How to control fetch_tool

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

policy.json

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

fetch_tool 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 Riza — 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 Riza tools

Execute execute_code Execute arbitrary Typescript or Python code. Execute execute_tool Executes a tool. This tool will be used to execute a self-written tool. Write create_tool Create a new tool. This tool will be used to create new tools. You can use the tools you h Write edit_tool Edit a tool, including its source code. Omit properties that you do not want to change. Read list_tools Lists the tool definitions of all self-written tools available for use. These tools can be

All 6 Riza 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 fetch_tool

What does the fetch_tool tool do? +

Fetch a tool, including its source code. It is categorised as a Read tool in the Riza MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on fetch_tool? +

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

What risk level is fetch_tool? +

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

Can I rate-limit fetch_tool? +

Yes. Add a rate_limit block to the fetch_tool 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 fetch_tool completely? +

Set action: deny in the PolicyLayer policy for fetch_tool. 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 fetch_tool? +

fetch_tool is provided by the Riza MCP server (riza-io/riza-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Riza tool call.

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

CHECK YOUR STACK →