Medium Risk

update_blog_post

기존 블로그 포스트를 수정합니다. 블로그 ID(blog_id), 제목(title), 내용(content), 공개 여부(is_public), 태그(tags)를 지정할 수 있습니다.

How to control update_blog_post ↓

What update_blog_post does on Wikidocs

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

Medium Risk

Why update_blog_post needs a policy

This tool creates or modifies data reversibly—it updates blog post attributes without deleting or destroying data. The ability to change visibility (is_public) and content has medium severity because an agent could modify blog posts without authorization, but changes are not permanent or irreversible. It does not execute code, move money, or irreversibly delete data.

From the tool's definition Tool description states it modifies an existing blog post ("기존 블로그 포스트를 수정합니다"), allowing updates to title, content, is_public status, and tags. The verb "update" and the ability to modify post visibility and content constitute reversible changes to data.

Documented attack patterns abuse exactly the kind of access update_blog_post gives an agent:

How to control update_blog_post

PolicyLayer is an MCP gateway — it sits between your AI agents and Wikidocs, and nothing reaches the server without passing your rules. This is the rule we recommend for update_blog_post:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "update_blog_post": {
      "limits": [
        {
          "counter": "update_blog_post_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

update_blog_post 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.

  1. Create a free account and register Wikidocs — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about update_blog_post

What does the update_blog_post tool do? +

기존 블로그 포스트를 수정합니다. 블로그 ID(blog_id), 제목(title), 내용(content), 공개 여부(is_public), 태그(tags)를 지정할 수 있습니다. It is categorised as a Write tool in the Wikidocs MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update_blog_post? +

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

What risk level is update_blog_post? +

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

Can I rate-limit update_blog_post? +

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

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

update_blog_post is provided by the Wikidocs MCP server (ychoi-kr/wikidocs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Wikidocs tool call.

Start from Wikidocs, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

17 Wikidocs tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.