lbm_update_project · LLM Brand Monitor MCP: Risk & Policy

WHAT IT DOES

What lbm_update_project does on LLM Brand Monitor

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

WHY IT NEEDS A POLICY

Why lbm_update_project needs a policy

This tool creates or modifies data in a reversible manner (Write category), not reading, executing code, deleting, or moving money. The severity is medium because misconfiguration of monitoring settings or project names could impact brand monitoring accuracy or visibility, but changes are easily correctable and do not destroy data or trigger external operations beyond configuration updates.

From the tool's definition Tool description states 'To update project name, models, or auto monitoring settings' — this modifies existing project configuration data. The phrase 'Only provided fields are updated' confirms reversible partial updates to project metadata.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

lbm_update_project Rate-limited

lbm_update_project 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": {
    "lbm_update_project": {
      "limits": [
        {
          "counter": "lbm_update_project_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 LLM Brand Monitor, so you can run agents against it safely.

FAQ

Questions about lbm_update_project

What does the lbm_update_project tool do? +

WHEN TO USE: To update project name, models, or auto monitoring settings. Only provided fields are updated. It is categorised as a Write tool in the LLM Brand Monitor MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on lbm_update_project? +

Register the LLM Brand Monitor MCP server in PolicyLayer and add a rule for lbm_update_project: 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 LLM Brand Monitor. Nothing to install.

What risk level is lbm_update_project? +

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

Can I rate-limit lbm_update_project? +

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

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

lbm_update_project is provided by the LLM Brand Monitor MCP server (@serpstat/llm-brand-monitor-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.