count_words

THE RISK

Low Risk

Why count_words needs a policy

This tool performs a statistical analysis on provided text and returns a result without modifying, deleting, executing code, or creating any state changes. It is a pure read operation with minimal blast radius if misused by an AI agent.

From the tool's definition Tool name 'count_words' and description 'Count words in text' indicate a data retrieval operation that analyzes input text and returns a count—a query with no side effects.

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

POLICY

How to control count_words

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

policy.json

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

count_words 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 Awesome-MCP-Scaffold — 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 Awesome-MCP-Scaffold tools

Execute divide Divide first number by second Execute subtract Subtract second number from first Write clean_text Clean and normalize text Write convert_case Convert text case Write create_directory Create a new directory Write generate_slug Generate URL-friendly slug from text Write replace_text Replace text with regex support Write write_json_file Write data to a JSON file

All 24 Awesome-MCP-Scaffold 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 count_words

What does the count_words tool do? +

Count words in text. It is categorised as a Read tool in the Awesome-MCP-Scaffold MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on count_words? +

Register the Awesome-MCP-Scaffold MCP server in PolicyLayer and add a rule for count_words: 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 Awesome-MCP-Scaffold. Nothing to install.

What risk level is count_words? +

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

Can I rate-limit count_words? +

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

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

count_words is provided by the Awesome-MCP-Scaffold MCP server (ww-ai-lab/awesome-mcp-scaffold). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Awesome-MCP-Scaffold tool call.

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

CHECK YOUR STACK →