Circuit
Find and try paid AI agent skills for security, on-chain data, code, markets, research and news.
我该使用它吗
质量与安全性
发现(1)
- LOW在 get_skill 中
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中:
{
"mcpServers": {
"marketplace": {
"url": "https://www.circuit.family/mcp"
}
}
}远程端点
https://www.circuit.family/mcpstreamable-http它能做什么
工具清单
工具(4)
🟢find_skills(query, category, maxPrice, limit)
Search Circuit's paid AI agent skills by capability, e.g. 'phishing link', 'token price' or 'summarize a web page'. Returns each skill's id, price in USDG, summary and 30-day usage. Free.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "What the skill should do. Leave empty to list everything."
},
"category": {
"type": "string",
"description": "Optional category, e.g. Security, On-chain, Developer, Market Data, Research, News."
},
"maxPrice": {
"type": "number",
"description": "Optional highest price per call in USDG, e.g. 0.005."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 25,
"description": "Most results to return (default 10)."
}
},
"additionalProperties": false
}🟢get_skill(skill_id)
Full details for one skill: input and output schema, a real example, price, 30-day usage, uptime, rating and how to pay for it. Free.
输入模式
{
"type": "object",
"properties": {
"skill_id": {
"type": "string",
"description": "Skill id from find_skills, e.g. 'bastion/url-risk'."
}
},
"required": [
"skill_id"
],
"additionalProperties": false
}🟢try_skill(skill_id, input)
Run a skill once for free on a small input (text up to 500 characters). 3 free calls per day. Paid calls have no such limits.
输入模式
{
"type": "object",
"properties": {
"skill_id": {
"type": "string",
"description": "Skill id, e.g. 'ticker/token-price'."
},
"input": {
"type": "object",
"description": "Input matching the skill's input schema.",
"additionalProperties": true
}
},
"required": [
"skill_id",
"input"
],
"additionalProperties": false
}🟢list_recipes
Workflows that chain several skills (vet a token, install a dependency safely, screen untrusted input and more), with the cost of one run. Free.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}社区
证据