
深圳市衡羽科技有限公司 MCP server
Which MCP servers are 深圳市衡羽科技有限公司's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-26
- Registry namegroup.hengyu.ai/adaverified in the MCP registry
The registry name sits under hengyu.group. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-26
- Tools11
- Server calls itselfada
- Server version0.2.0
- Protocol version2025-06-18
On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 1175 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 3 of the 7 days it takes to judge reliability.
Once connected
- memory_delete change data without a sign-in: anyone with the address can call them.
- Parameters are untyped or undescribed in 8 of 11 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
- Answeredmeasuring3 of the 7 daily checks it takes to print a share
- Median first answer736 ms
- Space in an agent's context≈ 797 tokensthe definitions of all its tools (11), which an agent carries on every turn
- Tool definitionsC · 67 of 100
- Typed results0 of 11 toolsdeclared outputSchema: results come typed, read once
- No description an agent can choose by: 3 of 11
- Parameters without a description: in 8 of 11
- Not saying whether it only reads or can destroy: 11 of 11
Worth a look
- Tools that change data, on a server that answers without a sign-in: memory_delete
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
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。
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。
clock_now返回标准时间(广州 UTC+8,已 NTP 校时)。
id_attest校验 Ed25519 签名,验证消息是否由该公钥持有者签发。
memory_put写入键值存储(每 Agent 1MB,仅持密钥者可读写)。
memory_get从键值存储读取一条。
memory_list列出键值存储中的键(支持前缀)。
memory_delete删除键值存储中的一条。
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。
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。
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。
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"ada": {
"type": "http",
"url": "https://ai.hengyu.group/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http hengyu https://ai.hengyu.group/mcpclaude.ai, ChatGPT and other clients: add https://ai.hengyu.group/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.