add_image_caption

Add a caption to an image in the document.

SERVERDocx SOURCEandrew82106/llm_docx_agent_mcp

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade D, identity unverified Pull the record →

This record as markdown: /tools/andrew82106-llm-docx-agent-mcp/add-image-caption.md

WHAT IT DOES

What add_image_caption does on Docx

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

RISK

Why add_image_caption is rated Medium

Adding a caption to an image is a reversible write operation that modifies document content but does not delete data, execute code, or create financial obligations. The change can be undone by removing or editing the caption. Severity is low because caption modifications have minimal blast radius—they affect only document formatting/presentation, not core data integrity or external system state.

From the tool's definition Tool name is 'add_image_caption' and description states it 'Add[s] a caption to an image in the document.' This is a modification operation that adds metadata/formatting to an existing image.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs add_image_caption safely

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

add_image_caption Rate-limited

add_image_caption 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_image_caption": {
      "limits": [
        {
          "counter": "add_image_caption_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 Docx, apply this rule, and every add_image_caption call is checked against it from then on.

FAQ

Questions about add_image_caption

What does the add_image_caption tool do? +

Add a caption to an image in the document. It is categorised as a Write tool in the Docx 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_image_caption? +

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

What risk level is add_image_caption? +

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

Can I rate-limit add_image_caption? +

Yes. Add a rate_limit block to the add_image_caption 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_image_caption completely? +

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

add_image_caption is provided by the Docx MCP server (andrew82106/llm_docx_agent_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Docx, and thousands of servers like it.

This server

All 24 Docx tools →

Across the catalogue

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

Guides

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