Servers Playground How we check Add a server Log in

艾达 ADA

Working · 3.4 s

group.hengyu.ai/adav0.1.0 Domain verified

Free APIs for AI agents: web reading, text slicing, clock, ID keys, 1MB memory. No signup or fees.

AI & Agents Web Search

Website Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://ai.hengyu.group/mcp

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

clock_now

返回标准时间（广州 UTC+8，已 NTP 校时）。

tzstring

This tool isn't marked read-only, so it may change something on the server or in an account you connected.

I understand, run it anyway

Tools

艾达 ADA MCP server | mcptry

clock_now

返回标准时间（广州 UTC+8，已 NTP 校时）。

Argument	Type	Description
tz	string

Input schema (JSON)

{
  "type": "object",
  "required": [],
  "properties": {
    "tz": {
      "type": "string"
    }
  }
}

id_attest

校验 Ed25519 签名，验证消息是否由该公钥持有者签发。

Argument	Type	Description
message	string
signature*	string
public_key*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "public_key",
    "signature"
  ],
  "properties": {
    "message": {
      "type": "string"
    },
    "signature": {
      "type": "string"
    },
    "public_key": {
      "type": "string"
    }
  }
}

memory_delete

删除键值存储中的一条。

Argument	Type	Description
key*	string
agent_key	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "key"
  ],
  "properties": {
    "key": {
      "type": "string"
    },
    "agent_key": {
      "type": "string"
    }
  }
}

memory_get

从键值存储读取一条。

Argument	Type	Description
key*	string
agent_key	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "key"
  ],
  "properties": {
    "key": {
      "type": "string"
    },
    "agent_key": {
      "type": "string"
    }
  }
}

memory_list

列出键值存储中的键（支持前缀）。

Argument	Type	Description
prefix	string
agent_key	string

Input schema (JSON)

{
  "type": "object",
  "required": [],
  "properties": {
    "prefix": {
      "type": "string"
    },
    "agent_key": {
      "type": "string"
    }
  }
}

memory_put

写入键值存储（每 Agent 1MB，仅持密钥者可读写）。

Argument	Type	Description
key*	string
value*	string
agent_key	string	在 /v1/register 申请的密钥；也可放在请求头 X-Agent-Key

Input schema (JSON)

{
  "type": "object",
  "required": [
    "key",
    "value"
  ],
  "properties": {
    "key": {
      "type": "string"
    },
    "value": {
      "type": "string"
    },
    "agent_key": {
      "type": "string",
      "description": "在 /v1/register 申请的密钥；也可放在请求头 X-Agent-Key"
    }
  }
}

shelf_find

查公共仓库里有没有这一份：给关键词或网址，回谁什么时候放的。只回元数据，不计被取次数。

Argument	Type	Description
q	string	关键词或网址
kind	string	品类：webpage/transcript/pdf/translation/ocr，留空＝全部
limit	integer	最多回几条，默认 20

Input schema (JSON)

{
  "type": "object",
  "required": [],
  "properties": {
    "q": {
      "type": "string",
      "description": "关键词或网址"
    },
    "kind": {
      "type": "string",
      "description": "品类：webpage/transcript/pdf/translation/ocr，留空＝全部"
    },
    "limit": {
      "type": "integer",
      "description": "最多回几条，默认 20"
    }
  }
}

shelf_get

取公共仓库里的成品（带来源与时间）。库里没有且给了网址，会实时加工并写回库内。

Argument	Type	Description
q	string	或关键词
id	string	条目号（find 回的 id）
url	string	或网址：命中直接给，没命中就现加工
auto	boolean	true（默认）＝库里没有就现加工；false＝只取现成的
kind	string	品类，默认 webpage
max_chars	integer	最多回多少字，默认 120000

Input schema (JSON)

{
  "type": "object",
  "required": [],
  "properties": {
    "q": {
      "type": "string",
      "description": "或关键词"
    },
    "id": {
      "type": "string",
      "description": "条目号（find 回的 id）"
    },
    "url": {
      "type": "string",
      "description": "或网址：命中直接给，没命中就现加工"
    },
    "auto": {
      "type": "boolean",
      "description": "true（默认）＝库里没有就现加工；false＝只取现成的"
    },
    "kind": {
      "type": "string",
      "description": "品类，默认 webpage"
    },
    "max_chars": {
      "type": "integer",
      "description": "最多回多少字，默认 120000"
    }
  }
}

shelf_put

把加工好的成品放回公共仓库（免注册、免密钥，带一个 source 标识）。同一份全库只保留一条。

Argument	Type	Description
url	string	来源网址（网页正文必填）
kind	string	webpage/transcript/pdf/translation/ocr
lang	string
text*	string	加工好的文字内容
title	string
source*	string	自报标识，1-48 位字母数字开头，例 my-agent
ttl_hours	number	保质期小时数；不填＝长效

Input schema (JSON)

{
  "type": "object",
  "required": [
    "text",
    "source"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "来源网址（网页正文必填）"
    },
    "kind": {
      "type": "string",
      "description": "webpage/transcript/pdf/translation/ocr"
    },
    "lang": {
      "type": "string"
    },
    "text": {
      "type": "string",
      "description": "加工好的文字内容"
    },
    "title": {
      "type": "string"
    },
    "source": {
      "type": "string",
      "description": "自报标识，1-48 位字母数字开头，例 my-agent"
    },
    "ttl_hours": {
      "type": "number",
      "description": "保质期小时数；不填＝长效"
    }
  }
}

text_slice

长文本检索：传入原文或网址 + 关键词，仅返回带行号的相关行，节省 token。

Argument	Type	Description
url	string	或网址（二选一）
text	string	原文（二选一）
query	string
context	integer
max_lines	integer

Input schema (JSON)

{
  "type": "object",
  "required": [],
  "properties": {
    "url": {
      "type": "string",
      "description": "或网址（二选一）"
    },
    "text": {
      "type": "string",
      "description": "原文（二选一）"
    },
    "query": {
      "type": "string"
    },
    "context": {
      "type": "integer"
    },
    "max_lines": {
      "type": "integer"
    }
  }
}

web_read

读取网页正文。全站共享缓存：命中缓存即时返回，节省 token。

Argument	Type	Description
url*	string	http/https 网址
force	boolean	true = 不吃缓存，重新抓一遍
max_chars	integer	最多回多少字，默认 12000、上限 120000

Input schema (JSON)

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "http/https 网址"
    },
    "force": {
      "type": "boolean",
      "description": "true = 不吃缓存，重新抓一遍"
    },
    "max_chars": {
      "type": "integer",
      "description": "最多回多少字，默认 12000、上限 120000"
    }
  }
}