Low Risk

get_most_wanted

Get the list of most-wanted skills that haven't been built yet (Supply Loop). Agents can build these to fill community demand. / 미공급 수요 스킬 목록 (Most Wanted). 0건 검색 쿼리를 집계한 결과 — 여기 올라온 스킬을 만들어 업로드하면 즉시 다운로드 수요 있음. Args: days: 최근 N일 (기본 30, 최대 365) limit: 최대 반환 개수 (기본 20, 최대 100) type: 'keyword' | '...

Part of the AI Skill Store server.

get_most_wanted is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE AI SKILL STORE →

Free to start. No card required.

AI agents call get_most_wanted to retrieve information from AI Skill Store without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though get_most_wanted only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_most_wanted": {}
  }
}

See the full AI Skill Store policy for all 18 tools.

Get this rule live on your own AI Skill Store server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY AI SKILL STORE →

View all 18 tools →

These attack patterns abuse exactly the kind of access get_most_wanted gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so get_most_wanted only ever does what you allow.

SECURE AI SKILL STORE →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the get_most_wanted tool do? +

Get the list of most-wanted skills that haven't been built yet (Supply Loop). Agents can build these to fill community demand. / 미공급 수요 스킬 목록 (Most Wanted). 0건 검색 쿼리를 집계한 결과 — 여기 올라온 스킬을 만들어 업로드하면 즉시 다운로드 수요 있음. Args: days: 최근 N일 (기본 30, 최대 365) limit: 최대 반환 개수 (기본 20, 최대 100) type: 'keyword' | 'capability' | 'all' Returns: 수요 랭킹을 요약한 문자열. 각 항목: query, query_type, zero_result_count, last_seen.. It is categorised as a Read tool in the AI Skill Store MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_most_wanted? +

Register the AI Skill Store MCP server in PolicyLayer and add a rule for get_most_wanted: 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 AI Skill Store. Nothing to install.

What risk level is get_most_wanted? +

get_most_wanted is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_most_wanted? +

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

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

get_most_wanted is provided by the AI Skill Store MCP server (garasegae/aiskillstore). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every AI Skill Store tool call.

Deterministic rules across all 18 AI Skill Store tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.