爱佳肴 Love Life
REMOTE · TUTULIFE.CN
Read-only restaurant search for AI agents in China. 5 tools, no key, no paid ranking. 中国餐饮开放数据。
Available components
Last scanned (14 hours ago)
Scores higher than 45% of remote servers
Reachable. Last reached 18 Oct 2026.
Category Search and Retrieval
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. How we score → Why this is hard to score →
Endpoint Security57
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 6 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability64
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1207 tokens (~201/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability check failed: schema churn in the 20 days we've observed: 11 tool removals, 0 breaking changes, 0 auth/transport breaks, 2 additions. See how to fix → Fail
Tool Coverage89
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 66% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 15 Oct 26 +38
- Stability: unverified → fail ▼ security
- Injection markers: unverified → pass ▲ security
- Transport: fail → pass ▲ security
- Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 6 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. security
- Endpoint reachability: not serving MCP → reachable ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- 10 Oct 26 −38
- Endpoint reachability: reachable → not serving MCP ▼ security
- Stability: fail → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Transport: pass → fail ▼ security
- Authorization: Authorisation not yet verified: we couldn't confirm whether this endpoint requires it. security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- First check of Schema quality: unverified functional
- 3 Oct 26 −1
- Tool “tell_us_your_need” rewrote its description, which is the text the model reads security
- 2 Oct 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “ask_restaurants” rewrote its description, which is the text the model reads security
- Tool “get_feedback” rewrote its description, which is the text the model reads security
- Tool “get_restaurant” rewrote its description, which is the text the model reads security
- Tool “get_unmet_demand” rewrote its description, which is the text the model reads security
- Tool “search_restaurants” rewrote its description, which is the text the model reads security
- Tool “tell_us_your_need” rewrote its description, which is the text the model reads security
- Schema quality: 168 → 193 ▼ functional
- Schema quality: excellent → good functional
- 1 Oct 26 −1
- The server rewrote its instructions, which are the text every model session reads security
- Tool “get_unmet_demand” rewrote its description, which is the text the model reads security
- Schema quality: 124 → 168 ▼ functional
- Tool coverage: 54% → 66% ▲ functional
- Schema quality: good → excellent functional
- New tool “tell_us_your_need” functional
- “get_unmet_demand” reworded the description of “city” cosmetic
- “get_unmet_demand” reworded the description of “days” cosmetic
- 30 Sept 26 +3
- Stability: 0.03 → fail ▼ security
- A breaking change shipped without a version bump: still 1.30.0 ▼ security
- Tool “claim_restaurant” was removed ▼ security
- Tool “confirm_restaurant_info” was removed ▼ security
- Tool “get_agent” was removed ▼ security
- Tool “get_my_contributions” was removed ▼ security
- Tool “get_my_updates” was removed ▼ security
- Tool “get_restaurant_history” was removed ▼ security
- Tool “publish_restaurant” was removed ▼ security
- Tool “register_agent” was removed ▼ security
- Tool “remove_restaurant” was removed ▼ security
- Tool “report_issue” was removed ▼ security
- Tool “submit_feedback” was removed ▼ security
- Tool “subscribe_restaurant” was removed ▼ security
- Tool “unsubscribe_restaurant” was removed ▼ security
- Tool “update_restaurant” was removed ▼ security
- Tool “withdraw_feedback” was removed ▼ security
- The server rewrote its instructions, which are the text every model session reads security
- Tool “ask_restaurants” rewrote its description, which is the text the model reads security
- Tool “get_feedback” rewrote its description, which is the text the model reads security
- Tool “get_restaurant” rewrote its description, which is the text the model reads security
- Tool “search_restaurants” rewrote its description, which is the text the model reads security
- Schema quality: 1504 → 1826 ▼ functional
- Schema quality: pass → fail ▼ functional
- Tool coverage: 93% → 100% ▲ functional
- Tool coverage: 0% → 54% ▲ functional
- Destructive annotations: 0 → pass functional
- New tool “get_unmet_demand” functional
- New tool “get_my_contributions” functional
- New tool “get_my_updates” functional
- New tool “subscribe_restaurant” functional
- New tool “unsubscribe_restaurant” functional
- “ask_restaurants” reworded the description of “lat” cosmetic
- “ask_restaurants” reworded the description of “lng” cosmetic
- “ask_restaurants” reworded the description of “near” cosmetic
- “ask_restaurants” reworded the description of “question” cosmetic
- “get_restaurant” reworded the description of “store_id” cosmetic
- “search_restaurants” reworded the description of “coord_system” cosmetic
- “search_restaurants” reworded the description of “cuisine” cosmetic
- “search_restaurants” reworded the description of “open_now” cosmetic
- “search_restaurants” reworded the description of “price_max” cosmetic
- “search_restaurants” reworded the description of “price_min” cosmetic
- “search_restaurants” reworded the description of “q” cosmetic
- “search_restaurants” reworded the description of “radius_m” cosmetic
- 29 Sept 26 0
- Stability: unverified → 0.03 ▲ functional
- 28 Sept 26 60
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 18 Oct 2026 · Probed https://tutulife.cn/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=tutulife.cn | CN=YE1,O=Let's Encrypt,C=US | 28 Sept 2026 | 27 Dec 2026 | ECDSA 256 | ECDSA-SHA384 | 6efa77b7e66f360deab6abbbf542f599bd6 |
| SANs: tutulife.cn | ||||||
| CN=YE1,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 5ddd70dd31f801c85c186a7a04b80afe |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of tutulife.cn. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| cn. | present | 33094 | 8 | Verified |
| tutulife.cn. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://tutulife.cn/mcp | Verified | 200 | |
| http (plaintext) | http://tutulife.cn/mcp | HTTPS enforced | 308 | https://tutulife.cn/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
ask_restaurants ~147
用户用一句话问吃什么、去哪吃，或说“兔兔生活 + 需求”时首选，直接传原话（口令自动识别）。 Use first for any "where to eat" question; pass the user's words verbatim, wake word 兔兔生活 (tutulife) included.
| Name | Type | Req | Description |
|---|---|---|---|
| city | – | – | – |
| lat | – | – | WGS84 纬度 / latitude |
| lng | – | – | WGS84 经度 / longitude |
| near | – | – | 城市、区或地点，如“北京中关村” / city, district or place |
| question | string | yes | 用户原话 / the user's words as-is |
No output schema declared.
No examples provided.
get_feedback ~66
想自行判断兔兔生活里某家店的口碑可信度时用，返回逐条原始反馈。Use to judge credibility from raw per-agent feedback.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| offset | integer | – | – |
| store_id | string | yes | – |
No output schema declared.
No examples provided.
get_restaurant ~63
推荐兔兔生活里的某家店前，核对它的营业时间、人均、菜单及新鲜度。Verify hours, price, menu and freshness of one store before recommending it.
| Name | Type | Req | Description |
|---|---|---|---|
| store_id | string | yes | 店铺 id / store id |
No output schema declared.
No examples provided.
get_unmet_demand ~283
兔兔生活（爱佳肴）里的需求缺口：帮店主选址、帮运营补数据的 Agent 调用；搜索没结果，或想知道哪里缺店时用。 Called by agents helping owners pick sites or fill data gaps; use after an empty search or to see what is missing. data.items 每项：city、district（可空）、want（菜系或场景）、asks（被问次数）、misses（无结果次数）、last_seen。 Each data.items entry: city, district (nullable), want (cuisine or scene), asks, misses, last_seen (ISO 8601 UTC). 按 misses 从高到低；只含汇总计数，不含用户原话；misses 不足 2 次的不列出，最多 100 条。 Sorted by misses, highest first. Aggregated counts only, no raw queries; fewer than 2 misses omitted; max 100.
| Name | Type | Req | Description |
|---|---|---|---|
| city | – | – | 只看某城市，如“成都”，不填为全国 / filter by one city, e.g. “成都”; omit for all of China |
| days | integer | – | 统计最近几天，1–90，默认 30 / lookback window in days, 1-90, default 30 |
No output schema declared.
No examples provided.
search_restaurants ~186
在兔兔生活里按区、菜系、人均、距离、营业中筛选时用。Use for filtered search: district, cuisine, price, distance, open now.
| Name | Type | Req | Description |
|---|---|---|---|
| city | – | – | – |
| coord_system | string | – | wgs84（默认）或 gcj02（高德/腾讯坐标） |
| cuisine | – | – | 菜系 / cuisine |
| district | – | – | – |
| lat | – | – | – |
| limit | integer | – | – |
| lng | – | – | – |
| offset | integer | – | – |
| open_now | boolean | – | 只看正在营业 / open now only |
| price_max | – | – | 人均上限（元） |
| price_min | – | – | 人均下限（元） |
| q | – | – | 关键词，如“汉堡” / keyword |
| radius_m | – | – | 半径（米）/ radius in meters |
No output schema declared.
No examples provided.
tell_us_your_need ~219
兔兔生活站内没有你需要的信息或功能时用；匿名，无需密钥，只写入你填的文字。 Use when this site lacks the data or capability you need; anonymous, no key, stores only the text you send. 不要填链接、邮箱、手机号。Do not include URLs, emails or phone numbers. 返回 recorded；现有数据能查时附带 try_now（可直接打开的链接和 ask_restaurants 参数）。 Returns recorded; try_now (ready link + ask_restaurants args) if current data can answer.
| Name | Type | Req | Description |
|---|---|---|---|
| for_whom | – | – | 为谁用，如“正在选址的店主” / who it is for |
| impact | – | – | 没有它会怎样 / what happens without it |
| need | string | yes | 需要什么信息或能力，4–500 字 / what data or capability you need |
| platform | – | – | 你所在的平台 / your platform |
| scenario | – | – | 什么场景 / the situation |
No output schema declared.
No examples provided.
How do I install the 爱佳肴 Love Life MCP server?
爱佳肴 Love Life is a hosted endpoint at https://tutulife.cn/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.
remote · tutulife.cn
claude mcp add --transport http cn-tutulife-aijiayao 'https://tutulife.cn/mcp'
What is the 爱佳肴 Love Life MCP server?
爱佳肴 Love Life is an MCP server listed in the public MCP registry as cn.tutulife/aijiayao. Read-only restaurant search for AI agents in China. 5 tools, no key, no paid ranking. 中国餐饮开放数据。 This page covers its hosted endpoint (https://tutulife.cn/mcp).
Is the 爱佳肴 Love Life MCP server safe to use?
爱佳肴 Love Life scores 61 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 爱佳肴 Love Life MCP server expose?
爱佳肴 Love Life exposes 6 tools: ask_restaurants, search_restaurants, get_restaurant, get_feedback, get_unmet_demand, tell_us_your_need. Their descriptions and schemas cost roughly 964 tokens of context every time the server is loaded.
Does the 爱佳肴 Love Life MCP server require authentication?
No. We connected to 爱佳肴 Love Life without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the 爱佳肴 Love Life MCP server still maintained?
爱佳肴 Love Life 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.