Low Risk

recommend_template_for_content

recommend_template_for_content

How to control recommend_template_for_content ↓

What recommend_template_for_content does on Deckbuilder MCP Server

AI agents call recommend_template_for_content to retrieve information from Deckbuilder MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why recommend_template_for_content needs a policy

This tool retrieves or recommends templates based on analyzing provided content. It performs a query/recommendation operation with no side effects—no data is created, modified, deleted, or external operations triggered. The empty description lowers confidence slightly, but the name and server context clearly indicate a read-only recommendation function.

From the tool's definition Tool name 'recommend_template_for_content' and server description stating 'automatic template selection based on content analysis' indicate the tool analyzes content and returns recommendations without modifying data.

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

How to control recommend_template_for_content

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "recommend_template_for_content": {}
  }
}

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

  1. Create a free account and register Deckbuilder MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about recommend_template_for_content

What does the recommend_template_for_content tool do? +

recommend_template_for_content. It is categorised as a Read tool in the Deckbuilder MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on recommend_template_for_content? +

Register the Deckbuilder MCP Server MCP server in PolicyLayer and add a rule for recommend_template_for_content: 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 Deckbuilder MCP Server. Nothing to install.

What risk level is recommend_template_for_content? +

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

Can I rate-limit recommend_template_for_content? +

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

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

recommend_template_for_content is provided by the Deckbuilder MCP Server MCP server (teknologika/deckbuilder). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Deckbuilder MCP Server tool call.

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

Free to start. No card required.

6 Deckbuilder MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.