Replace the image on an EXISTING rich menu without recreating it — the richMenuId, tappable areas, and any per-user links are preserved. Downloads the image from a public HTTPS URL, validates format + size, then uploads to the api-data.line.me content endpoint (the domain switch that trips up mos...
AI agents use line_upload_rich_menu_image to create or update resources in Line Oa Mcp Ultimate — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Line Oa Mcp Ultimate environment.
This tool modifies an existing resource (a rich menu's image) but does not delete it or cause irreversible destruction. The operation is reversible—another image can be uploaded to replace it. It is not Execute because it does not run arbitrary code or scripts; it performs a bounded update operation. It is not Destructive because the rich menu structure, tappable areas, and links are preserved.
From the tool's definition The tool description states it 'Replace[s] the image on an EXISTING rich menu' and 'uploads to the api-data.line.me content endpoint'. This is a modification operation on existing data (the rich menu image).
Documented attack patterns abuse exactly the kind of access line_upload_rich_menu_image gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Line Oa Mcp Ultimate, and nothing reaches the server without passing your rules. This is the rule we recommend for line_upload_rich_menu_image:
{
"version": "1",
"default": "deny",
"tools": {
"line_upload_rich_menu_image": {
"limits": [
{
"counter": "line_upload_rich_menu_image_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}line_upload_rich_menu_image 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.
Free to start. No card required.
Replace the image on an EXISTING rich menu without recreating it — the richMenuId, tappable areas, and any per-user links are preserved. Downloads the image from a public HTTPS URL, validates format + size, then uploads to the api-data.line.me content endpoint (the domain switch that trips up most implementations). Args: - rich_menu_id: ID of the existing rich menu to update. - image_url: Public HTTPS URL of the new image. JPEG/PNG, ≤1MB. - oa: Optional OA id. Returns: { rich_menu_id: string, uploaded: true, bytes: number // size of the uploaded image } Image requirements (validated client-side before upload): - Format: JPEG or PNG - File size: ≤1MB Examples: -. It is categorised as a Write tool in the Line Oa Mcp Ultimate MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Line Oa Mcp Ultimate MCP server in PolicyLayer and add a rule for line_upload_rich_menu_image: 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 Line Oa Mcp Ultimate. Nothing to install.
line_upload_rich_menu_image is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the line_upload_rich_menu_image 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.
Set action: deny in the PolicyLayer policy for line_upload_rich_menu_image. 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.
line_upload_rich_menu_image is provided by the Line Oa Mcp Ultimate MCP server (wasintoh/line-oa-mcp-ultimate). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 34 Line Oa Mcp Ultimate tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
34 Line Oa Mcp Ultimate tools catalogued and risk-classified — across an index of 42,500+ MCP servers.