AI agents use velog_like_post to create or update resources in Velog — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Velog environment.
This tool creates or modifies data (a like record) reversibly - users can unlike posts to undo the action. It is not destructive (likes can be removed), not financial, and not execute/code-running. The write category applies because it persistently changes application state in a reversible manner with minimal blast radius if misused.
From the tool's definition Tool name 'velog_like_post' and description 'Velog 포스트에 좋아요를 누릅니다' (likes a Velog post) indicates a write operation that modifies state by recording a like/upvote action on a post.
Documented attack patterns abuse exactly the kind of access velog_like_post gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Velog, and nothing reaches the server without passing your rules. This is the rule we recommend for velog_like_post:
{
"version": "1",
"default": "deny",
"tools": {
"velog_like_post": {
"limits": [
{
"counter": "velog_like_post_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}velog_like_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.
Free to start. No card required.
Velog 포스트에 좋아요를 누릅니다. It is categorised as a Write tool in the Velog MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Velog MCP server in PolicyLayer and add a rule for velog_like_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 Velog. Nothing to install.
velog_like_post 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 velog_like_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.
Set action: deny in the PolicyLayer policy for velog_like_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.
velog_like_post is provided by the Velog MCP server (seongwon030/velog_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Velog, 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.
29 Velog tools catalogued and risk-classified — across an index of 43,000+ MCP servers.