Velog 포스트를 키워드로 검색합니다. username을 지정하면 특정 유저의 포스트만 검색합니다.
AI agents call velog_search_posts to retrieve information from Velog without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries post data without side effects. It does not create, modify, delete, or execute any operations. Even though it can filter by username, it is fundamentally a search/query operation with no ability to alter data. Therefore, it falls under the Read category with low severity.
From the tool's definition Tool description indicates it 'searches Velog posts by keyword' and optionally filters by username. The verb 'search' and the retrieval-only nature (no modification, creation, or deletion) clearly indicate read-only functionality.
Documented attack patterns abuse exactly the kind of access velog_search_posts 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_search_posts:
{
"version": "1",
"default": "deny",
"tools": {
"velog_search_posts": {}
}
}velog_search_posts is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Velog 포스트를 키워드로 검색합니다. username을 지정하면 특정 유저의 포스트만 검색합니다. It is categorised as a Read tool in the Velog MCP Server, which means it retrieves data without modifying state.
Register the Velog MCP server in PolicyLayer and add a rule for velog_search_posts: 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_search_posts is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the velog_search_posts 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_search_posts. 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_search_posts 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.