get_model

THE RISK

Low Risk

Why get_model needs a policy

The tool retrieves or queries model information without side effects. This is a read-only operation typical of data retrieval endpoints. No data is created, modified, deleted, or executed. The low severity reflects minimal risk if misused by an AI agent, as it only exposes existing model metadata.

From the tool's definition Tool name is 'get_model' and description states 'Get model details' — a straightforward retrieval operation with no modification, deletion, or execution capability.

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

POLICY

How to control get_model

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

policy.json

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

get_model 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 WeKnora MCP Server — 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 WeKnora MCP Server tools

Destructive delete_chunk Delete a chunk Destructive delete_knowledge Delete knowledge Destructive delete_knowledge_base Delete a knowledge base Destructive delete_session Delete a session Execute chat Send a chat message to a session Write create_knowledge_base Create a new knowledge base Write create_knowledge_from_url Create knowledge from URL Write create_model Create a new model

All 21 WeKnora MCP Server 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 get_model

What does the get_model tool do? +

Get model details. It is categorised as a Read tool in the WeKnora MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_model? +

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

What risk level is get_model? +

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

Can I rate-limit get_model? +

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

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

get_model is provided by the WeKnora MCP Server MCP server (nannaolympicbroadcast/weknoramcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every WeKnora MCP Server tool call.

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

CHECK YOUR STACK →