LocalMark Agent Directory
Search reviewed public A2A Agent Cards and declared skills with read-only MCP tools.
我該用這個嗎
品質與安全性
B
發現項目(1)
- LOW在 list_agents 中
根據工具定義與協定合規性的自動化分析。
上下文成本
~269Token(工具定義)
~494 B典型回應大小
極小的注意力影響(128k 上下文的 0.21%)
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高,可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案:
{
"mcpServers": {
"agent-directory": {
"url": "https://localmark.ai/mcp"
}
}
}遠端端點
https://localmark.ai/mcpstreamable-http它能做什麼
工具清單
工具(3)
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢search_agents(query, limit)
Search public agent names, descriptions, and declared skills. Returns card and profile URLs, not task results.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"title": "Query",
"type": "string"
},
"limit": {
"default": 10,
"title": "Limit",
"type": "integer"
}
},
"required": [
"query"
],
"title": "search_agentsArguments"
}🟢list_agents(limit, offset)
Browse public agents with pagination.
輸入結構描述
{
"type": "object",
"properties": {
"limit": {
"default": 20,
"title": "Limit",
"type": "integer"
},
"offset": {
"default": 0,
"title": "Offset",
"type": "integer"
}
},
"title": "list_agentsArguments"
}🟢get_agent(agent_id)
Get one published agent's source, declared skills, and latest card check by LocalMark ID.
輸入結構描述
{
"type": "object",
"properties": {
"agent_id": {
"title": "Agent Id",
"type": "integer"
}
},
"required": [
"agent_id"
],
"title": "get_agentArguments"
}社群
證據
近期觀測
已驗證未記錄版本3 個工具