add_keywords

Add keywords (supports hierarchical format: A > B > C).

SERVERLightroom Classic MCP SOURCE4xiomdev/lightroom-classic-mcp

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/4xiomdev-lightroom-classic-mcp/add-keywords.md

WHAT IT DOES

What add_keywords does on Lightroom Classic MCP

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

RISK

Why add_keywords is rated Medium

This tool creates or modifies keyword metadata on photos in a reversible manner. It does not execute code, delete data, move money, or trigger external operations—it simply adds organizational metadata. This is a classic Write operation.

From the tool's definition Tool name 'add_keywords' and description 'Add keywords' indicates creation/modification of metadata. The hierarchical format support (A > B > C) confirms it structures and persists keyword data in the Lightroom catalog.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs add_keywords safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Lightroom Classic MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For add_keywords, this is the rule to start with:

add_keywords Rate-limited

add_keywords 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_keywords": {
      "limits": [
        {
          "counter": "add_keywords_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Lightroom Classic MCP, apply this rule, and every add_keywords call is checked against it from then on.

FAQ

Questions about add_keywords

What does the add_keywords tool do? +

Add keywords (supports hierarchical format: A > B > C). It is categorised as a Write tool in the Lightroom Classic MCP 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_keywords? +

Register the Lightroom Classic MCP server in PolicyLayer and add a rule for add_keywords: 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 Lightroom Classic MCP. Nothing to install.

What risk level is add_keywords? +

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

Can I rate-limit add_keywords? +

Yes. Add a rate_limit block to the add_keywords 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_keywords completely? +

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

add_keywords is provided by the Lightroom Classic MCP server (4xiomdev/lightroom-classic-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Lightroom Classic, and thousands of servers like it.

This server

All 59 Lightroom Classic tools →

Across the catalogue

add-tag on Kanban MCP Server →kb_add on Persistent Kb → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →