update_article
Update fields on an existing article. Only the fields you pass are changed; omitted fields stay as-is. Common patterns: flip status from draft → published, reschedule a scheduled post, replace the featured image, edit the content. Editing content replaces the WHOLE markdown body — read the articl...
This record as markdown: /tools/a3plus-mcp/update-article.md
What update_article does on A3plus
AI agents call update_article to permanently remove resources in A3plus, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
| Parameter | Type | Required | Description |
|---|---|---|---|
slug | string | — | ⚠️ DO NOT send this when editing a published article. Changing the slug 404s the old URL with no 301 redirect — Google index and rankings are lost, not transfer |
tags | array | — | |
title | string | — | |
ctaUrl | string | — | |
siteId | string | Yes | The A3Plus site ID. |
status | string | — | Same semantics as create_article. |
content | string | — | Replacement markdown body. |
excerpt | string | — | |
articleId | string | Yes | The article ObjectId. |
publishedAt | string | — | ISO 8601, required when status=scheduled. |
inlineImages | array | — | Optional images to weave into the article body (max 20). Same semantics as create_article: url already in content → replaced in-place; else inserted at `positio |
targetKeyword | string | — |
Parameters from the server's own tool schema.
Why update_article is rated Critical
An AI agent that decides to call update_article doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from A3plus is gone. There is no undo for destructive operations.
Risk signalsAccepts URL/endpoint input (inlineImages[].url) · Accepts raw HTML/template content (content) · High parameter count (18 properties)
Attacks that exploit this kind of access
The rule that runs update_article safely
PolicyLayer is an MCP gateway: it sits between your AI agents and A3plus, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For update_article, this is the rule to start with:
update_article is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect A3plus, apply this rule, and every update_article call is checked against it from then on.
Questions about update_article
Update fields on an existing article. Only the fields you pass are changed; omitted fields stay as-is. Common patterns: flip status from draft → published, reschedule a scheduled post, replace the featured image, edit the content. Editing content replaces the WHOLE markdown body — read the article first (get_article) and send the full text back, not just the part you changed. On articles that have a structured block body the blocks are re-derived from your markdown, so complex blocks (tables, callouts) may come back simplified; use get_article with includeBlocks:true first if you need to know what is there. When rewriting a title or meta description, pass ONLY those fields — never slug. The URL is fixed at creation and independent of the title; changing it de-indexes the page permanently. It is categorised as a Destructive tool in the A3plus MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
update_article accepts 12 parameters: slug, tags, title, ctaUrl, siteId, status, content, excerpt, articleId, publishedAt, inlineImages, targetKeyword. Required: siteId, articleId. The full parameter table on this page comes from the server's own tool schema.
Register the A3plus MCP server in PolicyLayer and add a rule for update_article: 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 A3plus. Nothing to install.
update_article is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the update_article 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 update_article. 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.
update_article is provided by the A3plus MCP server (a3plus-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on A3plus, and thousands of servers like it.
Across the catalogue