brief_add_link · Llama MCP: Risk & Policy

WHAT IT DOES

What brief_add_link does on Llama

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

WHY IT NEEDS A POLICY

Why brief_add_link needs a policy

This tool adds (creates) a link block to a deal brief, which is a reversible modification of data. It does not delete, execute arbitrary code, move money, or perform irreversible actions.

From the tool's definition Tool name 'brief_add_link' and description 'Prepend a link block to a deal brief' indicates the tool creates or modifies data by adding a new link block to an existing brief.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

brief_add_link Rate-limited

brief_add_link 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": {
    "brief_add_link": {
      "limits": [
        {
          "counter": "brief_add_link_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 Llama, so you can run agents against it safely.

FAQ

Questions about brief_add_link

What does the brief_add_link tool do? +

Prepend a link block to a deal brief. Server fetches og:image + title via /api/link-preview. It is categorised as a Write tool in the Llama MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on brief_add_link? +

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

What risk level is brief_add_link? +

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

Can I rate-limit brief_add_link? +

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

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

brief_add_link is provided by the Llama MCP server (llama-ventures/llama-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.