Velog 포스트 초안을 세션 메모리에 저장합니다. 발행 전 사용자가 검토할 수 있도록 draft_id를 반환합니다.
AI agents use velog_draft_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.
The tool creates and stores draft content (Write category) but does not publish or delete irreversibly. It is explicitly part of a human-in-the-loop workflow where users review before publication.
From the tool's definition Tool description states it 'saves Velog post draft to session memory' and 'returns draft_id for user review before publishing.' This is creating/storing content in a draft state, a reversible modification.
Documented attack patterns abuse exactly the kind of access velog_draft_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_draft_post:
{
"version": "1",
"default": "deny",
"tools": {
"velog_draft_post": {
"limits": [
{
"counter": "velog_draft_post_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}velog_draft_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 포스트 초안을 세션 메모리에 저장합니다. 발행 전 사용자가 검토할 수 있도록 draft_id를 반환합니다. 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_draft_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_draft_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_draft_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_draft_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_draft_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.