add_resource · Lingua MCP: Risk & Policy

WHAT IT DOES

What add_resource does on LinguaMCP

AI agents use add_resource to create or update resources in LinguaMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your LinguaMCP environment.

WHY IT NEEDS A POLICY

Why add_resource needs a policy

This tool creates or modifies lesson metadata by adding a reference to an external resource. It is a Write operation because it creates new data in the system without destructive, financial, or code-execution implications. Severity is low because adding a resource link has minimal blast radius—the worst case is spam or irrelevant resources cluttering the curriculum, which can be removed.

From the tool's definition Tool name 'add_resource' and description 'Add an external resource' indicate creation of new data (a resource link). The action is reversible via the sibling tool 'remove_lesson' or implied delete capability.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_resource Rate-limited

add_resource stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "add_resource": {
      "limits": [
        {
          "counter": "add_resource_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches LinguaMCP, so you can run agents against it safely.

FAQ

Questions about add_resource

What does the add_resource tool do? +

Add an external resource (YouTube, article, podcast) linked to a lesson. It is categorised as a Write tool in the LinguaMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_resource? +

Register the Lingua MCP server in PolicyLayer and add a rule for add_resource: 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 LinguaMCP. Nothing to install.

What risk level is add_resource? +

add_resource is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit add_resource? +

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

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

add_resource is provided by the Lingua MCP server (marsmanleo/linguamcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.