Agent Toolbox
Free, no-key MCP server: token estimates, JSON Schema conversion, MCP configs, tool search.
我該用這個嗎
品質與安全性
A
根據工具定義與協定合規性的自動化分析。
上下文成本
~249Token(工具定義)
~410 B典型回應大小
極小的注意力影響(128k 上下文的 0.19%)
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": {
"agenttoolbox": {
"url": "https://agenttoolbox.net/api/mcp"
}
}
}遠端端點
https://agenttoolbox.net/api/mcpstreamable-http它能做什麼
工具清單
工具(4)
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
⚪estimate_tokens(text, output_tokens)
Estimate tokens and USD cost of a text across current frontier models (list prices verified 2026-10-16).
輸入結構描述
{
"type": "object",
"properties": {
"text": {
"type": "string"
},
"output_tokens": {
"type": "number"
}
},
"required": [
"text"
]
}⚪convert_schema(name, description, schema)
Convert a JSON Schema into OpenAI, Anthropic and MCP tool definitions.
輸入結構描述
{
"type": "object",
"properties": {
"name": {
"type": "string"
},
"description": {
"type": "string"
},
"schema": {
"type": "object"
}
},
"required": [
"name",
"schema"
]
}⚪mcp_config(name, command, args, url, env)
Generate an mcpServers config block.
輸入結構描述
{
"type": "object",
"properties": {
"name": {
"type": "string"
},
"command": {
"type": "string"
},
"args": {
"type": "array",
"items": {
"type": "string"
}
},
"url": {
"type": "string"
},
"env": {
"type": "object"
}
},
"required": [
"name"
]
}🟢search_directory(query, category)
Search the Agent Toolbox directory of AI agent tools.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"category": {
"type": "string"
}
}
}社群
證據
近期觀測
已驗證未記錄版本4 個工具