# 艾达 ADA (remote · ai.hengyu.group)

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

- Trust score: 68/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- remote · `ai.hengyu.group`: 68/100 (this document), [markdown](https://verifymcp.io/servers/group-hengyu-ai-ada/ai.md), [page](https://verifymcp.io/servers/group-hengyu-ai-ada/ai)

## Channel facts

- Endpoint: `https://ai.hengyu.group/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-18.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 11 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 873 tokens (~79/item across 11 items; 11 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 50/100
  - Stability observed for 15 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 73/100
  - 82% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 54% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "memory_delete" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the 艾达 ADA MCP server?

艾达 ADA is a hosted endpoint at https://ai.hengyu.group/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http group-hengyu-ai-ada 'https://ai.hengyu.group/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "group-hengyu-ai-ada": {
      "url": "https://ai.hengyu.group/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "group-hengyu-ai-ada": {
      "type": "http",
      "url": "https://ai.hengyu.group/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.group-hengyu-ai-ada]
url = "https://ai.hengyu.group/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "group-hengyu-ai-ada": {
      "type": "remote",
      "url": "https://ai.hengyu.group/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add group-hengyu-ai-ada --url 'https://ai.hengyu.group/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  group-hengyu-ai-ada:
    url: "https://ai.hengyu.group/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "group-hengyu-ai-ada": {
      "Transport": "http",
      "Url": "https://ai.hengyu.group/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add group-hengyu-ai-ada -t streamable-http -u 'https://ai.hengyu.group/mcp'
```

### Other

```json
{
  "mcpServers": {
    "group-hengyu-ai-ada": {
      "type": "http",
      "url": "https://ai.hengyu.group/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-18 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-16 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-12 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 30. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-10 (score 64, +1)

- [security] Tool “shelf_get” rewrote its description, which is the text the model reads
- [security] Tool “shelf_put” rewrote its description, which is the text the model reads

### 2026-10-08 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 17. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-06 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 10. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-04 (score 61, +2)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “clock_now” rewrote its description, which is the text the model reads
- [security] Tool “id_attest” rewrote its description, which is the text the model reads
- [security] Tool “memory_delete” rewrote its description, which is the text the model reads
- [security] Tool “memory_get” rewrote its description, which is the text the model reads
- [security] Tool “memory_list” rewrote its description, which is the text the model reads
- [security] Tool “memory_put” rewrote its description, which is the text the model reads
- [security] Tool “text_slice” rewrote its description, which is the text the model reads
- [security] Tool “web_read” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 61 → 80
- [functional improvement] Tool coverage: 75% → 82%
- [functional improvement] Tool coverage: 29% → 54%
- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 0.1.0 → 0.2.0
- [functional] New tool “shelf_find”
- [functional] New tool “shelf_get”
- [functional] New tool “shelf_put”
- [cosmetic] “memory_put” reworded the description of “agent_key”

## MCP tools (11)

### `web_read` (~81 tokens)

读取网页正文。全站共享缓存：命中缓存即时返回，节省 token。

Input parameters:

- `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
- `url` (string, required): http/https 网址

### `text_slice` (~81 tokens)

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。

Input parameters:

- `context` (integer)
- `max_lines` (integer)
- `query` (string)
- `text` (string): 原文（二选一）
- `url` (string): 或网址（二选一）

### `clock_now` (~30 tokens)

返回标准时间（广州 UTC+8，已 NTP 校时）。

Input parameters:

- `tz` (string)

### `id_attest` (~53 tokens)

校验 Ed25519 签名，验证消息是否由该公钥持有者签发。

Input parameters:

- `message` (string)
- `public_key` (string, required)
- `signature` (string, required)

### `memory_put` (~71 tokens)

写入键值存储（每 Agent 1MB，仅持密钥者可读写）。

Input parameters:

- `agent_key` (string): 在 /v1/register 申请的密钥；也可放在请求头 X-Agent-Key
- `key` (string, required)
- `value` (string, required)

### `memory_get` (~32 tokens)

从键值存储读取一条。

Input parameters:

- `agent_key` (string)
- `key` (string, required)

### `memory_list` (~38 tokens)

列出键值存储中的键（支持前缀）。

Input parameters:

- `agent_key` (string)
- `prefix` (string)

### `memory_delete` (~32 tokens)

删除键值存储中的一条。

Input parameters:

- `agent_key` (string)
- `key` (string, required)

### `shelf_find` (~89 tokens)

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。

Input parameters:

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

### `shelf_get` (~139 tokens)

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。

Input parameters:

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

### `shelf_put` (~143 tokens)

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。

Input parameters:

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

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/group-hengyu-ai-ada/ai#diagnostics

## Score history

- 2026-10-18: 68
- 2026-10-17: 67
- 2026-10-16: 67
- 2026-10-15: 66
- 2026-10-14: 66
- 2026-10-13: 65
- 2026-10-12: 65
- 2026-10-10: 64
- 2026-10-08: 63
- 2026-10-06: 62
- 2026-10-04: 61
- 2026-10-03: 59

## Common questions

### What is the 艾达 ADA MCP server?

艾达 ADA is an MCP server listed in the public MCP registry as group.hengyu.ai/ada. Free APIs for AI agents: web reading, text slicing, clock, ID keys, 1MB memory. No signup or fees. This page covers its hosted endpoint (https://ai.hengyu.group/mcp).

### Is the 艾达 ADA MCP server safe to use?

艾达 ADA scores 68 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the 艾达 ADA MCP server expose?

艾达 ADA exposes 11 tools: web_read, text_slice, clock_now, id_attest, memory_put, and 6 more. Their descriptions and schemas cost roughly 789 tokens of context every time the server is loaded.

### Does the 艾达 ADA MCP server require authentication?

No. We connected to 艾达 ADA without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the 艾达 ADA MCP server still maintained?

艾达 ADA is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://ai.hengyu.group/mcp
- Website: https://ai.hengyu.group/
- Changelog RSS feed: https://verifymcp.io/servers/group-hengyu-ai-ada/ai.xml
- Changelog JSON feed: https://verifymcp.io/servers/group-hengyu-ai-ada/ai.json
- HTML version of this page: https://verifymcp.io/servers/group-hengyu-ai-ada/ai