Skip to content

MCP servers › hk.liki › liki

MCP server · registry snapshot 2026-11-15 · last tested 2026-11-15

liki MCP server

Registry name hk.liki/liki

Liki — Professional AI Astrologer — the publisher's title

by liki.hk · domain (the registry's namespace rule)Website ↗

Professional AI Astrologer for BaZi, Zi Wei Dou Shu, I Ching, Feng Shui and naming. Free at liki.hk — the publisher's description

1 of 2 record checks metRead-only · tools listed 2026-11-15version 2026.11.15.1streamable HTTP24 tools

Summary

hk.liki/liki is a remote MCP server listed in the official MCP registry at version 2026.11.15.1, under the namespace of the domain liki.hk. On 2026-11-15 ProtocolProbe connected to it in read-only mode and read its inventory: 24 tools, 0 resources and 0 prompts.

Record checks

1 of 2 record checks met · 7 do not apply

  • met: Registry entry is active and says how to run it
  • not met: Source repository link opens
  • not applicable: Repository is not archived
  • not applicable: Code pushed to the repository in the 90 days before our check
  • not applicable: Repository publishes a security policy (SECURITY.md)
  • not applicable: Package names its licence with a standard (SPDX) identifier
  • not applicable: The version the registry lists can be installed and is not withdrawn
  • not applicable: npm package carries build provenance (attestation)
  • not applicable: No known critical or high advisory in the package or its dependencies
  • Not ranked by downloads: a remote server publishes no download figure
  • Not ranked by stars: no public GitHub repository

From public records, not a safety rating. Each check with its reason

Operate this server? Correct a fact · README badge · Run the checks yourself · Claim it

Key facts

Runs
remote (hosted by the publisher)
Transport
streamable HTTP
Your own values
none declared (not a guarantee)
Sign-in
none needed to open a session
Tools
24
Last tested
2026-11-15

Tool list size

Claude's token counter refused this tool list as listed, unchanged (tool "subject_candidates" (no. 2): input_schema: input_schema does not support oneOf, allOf, or anyOf at the top level)

Tried on Claude Opus 5.5 on 2026-11-15, from the tool list we read on 2026-11-15 (24 tools). How it is counted

How a client gets in

Connects without signing in

Read from the server's public metadata on 2026-11-15 (mcp.tokflux.com), in our read-only connection; no tool was called. It may have changed since. How it is read

Tool list at the three APIs

Not sent yet for this version (2026.11.15.1).

Add to your client

How fresh this is

Live-tested
yes, a real session (not a text-only review)
Last tested
2026-11-15
Mode
read-only (no tool calls)
Latest version
2026.11.15.1, published 2026-11-14 (registry, as of the 2026-11-15 snapshot)
First listed version
2026-11-10 (earliest version still in the registry; older removed versions would be earlier)
Version history
2 versions listed, 2026-11-10 to 2026-11-14; 2 in the 90 days before the 2026-11-15 snapshot; 1 marked deprecated.
Most recent 2 versions
  • 2026.11.15.1 · 2026-11-14
  • 2026.11.09.1 · 2026-11-10 · deprecated
(versions still listed in the registry only)
Registry data
snapshot 2026-11-15
Package and repository
checked 2026-11-15
Engine
mcp-runtime-engine@0.1.0 · sdk@1.32.0

Dead or stale signals

None found in the records we hold

Looked for and not found: deprecated in the registry. Does not apply: listed version cannot be installed or is withdrawn; repository link does not open; repository archived; no push in over 365 days. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.

Changes since the last refresh

Version 2026.11.09.1 (published 2026-11-10) → 2026.11.15.1 (published 2026-11-14), between the registry lists of 2026-11-14 and 2026-11-15.

No release note: the registry entry links no GitHub repository.

Source: the official MCP Registry list on 2026-11-14 and on 2026-11-15; release notes from the GitHub Releases API, checked 2026-11-15.

What it is

What does this server offer?

Observed inventory
24tools
0resources
0prompts

None of its 24 tools are described as changing anything. For 24 the reading was uncertain, so no mark is shown.

  • “按 IANA 时区返回服务端当前标准时间(无 DST);空值、无效或未知 timezone 直接报错。所有「现在/今天/当前年份」运算以本返回值为唯一时间基准。用户出生时间不走本工具:民用/农历/时辰/日界模糊时先用 subject_candidates;地点或时区未知先用 city_info;黄历择日用 huangli_days。”

    Publisher declares: read-only yes · idempotent yes

    1 input, 1 required
    • timezonestringrequired“IANA timezone, e.g.”
  • subject_candidateson 1 other server

    “把民用时间事实归一化为 canonical subject 候选:接受公历/农历壁钟、时辰或同日区间;longitude_range 可选,表示地点边界不确定性。返回候选列表,input 候选恒定第一,边界派生候选按时间排序,每个候选附 reasons;longitude_range 省略时只用精确 longitude,非法时间、时区或范围直接报错。时间明确时直接组装下游 subject;模糊或…”

    Publisher declares: read-only yes · idempotent yes

    Takes no inputs.

  • “根据城市名返回城市信息候选(内置表,不访问外链):每项含名称、行政区、层级、经纬度、IANA 时区与可选经度范围;locale 只本地化名称展示,不改变匹配集合。长度 1 可直接使用;多于 1(同名区县等)必须由用户确认,不得静默取第一个。未命中时请询问附近大城市,或让用户直接提供经纬度和时区。”

    Publisher declares: read-only yes · idempotent yes

    2 inputs, 1 required
    • citystringrequired“城市名称(中英文均可);同名区县请用省/市限定(如 北京朝阳区)。”
    • localestring“可选显示语言:zh-Hans、zh-Hant 或 en;省略时返回内置表原文。”
  • huangli_dayson 1 other server

    “黄历择日查日。用户询问某事项宜忌日期、某日吉凶或黄历宜忌事实时调用;从 standard_time 起返回连续 count 天,指定 event 时逐日附适配结论与判定依据,范围内无适配日也不报错。命理合参(八字/紫微本命、流年)不走本工具,改用对应排盘与查询工具。”

    Publisher declares: read-only yes · idempotent yes

    3 inputs, 3 required
    • countintegerrequired“黄历查询天数,最多30。”
    • eventstringrequired“事项类型。”
    • standard_timestringrequired“查询起始日标准时间(无 DST),RFC3339 带 offset。”
  • “排八字本命盘并返回确定性结构事实。subject 可由用户明确事实组装,也可取自用户确认后的 subject_candidates 候选;时间模糊或多候选时先归一化并确认。需要四柱、大运、十神、藏干、神煞、刑冲合会、扶抑/调候或格局证据时调用。只要原始本命盘,不用八字紫微合参断语;后者用 natal_query,紫微宫位细节用 ziwei_chart。”

    Publisher declares: read-only yes · idempotent yes

    1 input, 1 required
    • subjectobjectrequired“schema 合法的出生主体;可来自用户明确事实或用户确认后的 subject_candidates 候选。”
  • “紫微斗数排本命盘并返回确定性宫位事实。subject 可由用户明确事实组装,也可取自用户确认后的 subject_candidates 候选;时间模糊或多候选时先归一化并确认。需要十二宫主星、亮度、四化、杂曜、长生博士十二神、小限或大限时调用。两人合盘用 ziwei_bond,流盘用 ziwei_liupan,八字紫微断语合参用 natal_query。”

    Publisher declares: read-only yes · idempotent yes

    1 input, 1 required
    • subjectobjectrequired“已归一化的出生主体。”
  • “八字流盘:按 scope 返回 liu_nian/liu_yue/liu_ri/liu_shi/xiao_yun 对应领域数组,字段见 output schema。按粒度选择:逐年用 liu_nian,逐月用 liu_yue,具体日期用 liu_ri,具体时辰用 liu_shi,童年或小运趋势用 xiao_yun。count=1 单层,count>1 连续批量;liu_ri/liu_shi 必须…”

    Publisher declares: read-only yes · idempotent yes

    Takes no inputs.

  • ziwei_liupanon 1 other server

    “紫微流盘:按 scope 返回 liu_nian/liu_yue/liu_ri/liu_shi 对应的领域数组,字段见 output schema。count=1(默认)单层,count>1 连续批量;standard_time 为当地标准时间,liu_shi 必须带经度。只返回确定性流盘事实,不做断语;本命盘用 ziwei_chart,八字紫微逐年合参断语用 natal_liunian_que…”

    Publisher declares: read-only yes · idempotent yes

    Takes no inputs.

  • “八字合盘返回确定性关系事实,不做合婚评级。a/b 必须来自用户确认事实或 subject_candidates 归一化候选;非法、不完整或未确认的模糊 subject 直接报错。用户询问合婚、合作、亲子等关系并需要八字侧证据时调用;需要紫微宫位主星对照用 ziwei_bond,两者常配合使用。”

    Publisher declares: read-only yes · idempotent yes

    2 inputs, 2 required
    • arequired“甲方:已归一化的出生主体。”
    • brequired“乙方:已归一化的出生主体。”
  • “紫微合盘原始事实。a/b 必须是用户确认事实或 subject_candidates 归一化后的主体,不得手造模糊时间。用户询问两人关系并需要紫微侧证据时调用;八字干支与十神视角改用 bazi_bond,两者常配合使用。并排返回双方命宫、夫妻宫、子女宫主星;不做跨盘投射和合婚评级。”

    Publisher declares: read-only yes · idempotent yes

    2 inputs, 2 required
    • arequired“甲方:已归一化的出生主体。”
    • brequired“乙方:已归一化的出生主体。”
  • bazhai_charton 1 other server

    “八宅排盘:由已校准 subject 推导出生年与性别,排命卦、四吉四凶方与出生年紫白飞星。subject 必须来自用户确认事实或 subject_candidates;时间或性别非法时返回错误,不猜测出生时辰。住宅风水评估、命卦方位吉凶类问题调用;门/主/灶配合改用 bazhai_layout。八宅不与八字四柱合参。”

    Publisher declares: read-only yes · idempotent yes

    1 input, 1 required
    • subjectobjectrequired“八宅命卦主体。”
  • bazhai_layouton 1 other server

    “八宅门主灶配合:评估命卦与门/主/灶卦的游年九星、方向与吉凶。门/主/灶卦必须来自建筑方位或用户确认事实,本工具不反推方位。已由 bazhai_chart 得到命卦后调用;输出是八宅学派确定性参考判断,不是施工或安全建议;玄空飞星用 xuankong 工具。”

    Publisher declares: read-only yes · idempotent yes

    4 inputs, 4 required
    • door_guarequired“门卦。”
    • master_guarequired“主卧卦。”
    • ming_guarequired“命卦。”
    • stove_guarequired“灶卦。”
Show 12 more tools
  • xuankong_charton 1 other server

    “玄空飞星起盘:按宅体事实日期(建成、入住或改宅)与二十四山坐向,排九宫飞星盘。评估阳宅固定风水格局时调用;流年飞星变化改用 xuankong_liunian。注意起盘日期不是命主出生时间。”

    Publisher declares: read-only yes · idempotent yes

    3 inputs, 3 required
    • standard_timestringrequired“宅运起盘地标准日期时间(无 DST),RFC3339 带 offset。”
    • xiang_shanintegerrequired“朝向;必须与坐山相对。”
    • zuo_shanintegerrequired“坐山,二十四山 index。”
  • xuankong_liunianon 1 other server

    “玄空流年飞星:在宅运盘上叠加指定年份,返回流年飞星盘;count=1(默认)单年,count>1 连续批量。评估阳宅某一年风水变化时调用;固定格局用 xuankong_chart,尚未起宅运盘的也先调用 xuankong_chart。”

    Publisher declares: read-only yes · idempotent yes

    4 inputs, 3 required
    • countnull or integer“连续查询年数。”
    • standard_timestringrequired“流年选择地标准时间(无 DST),RFC3339 带 offset。”
    • xiang_shanintegerrequired“朝向;必须与坐山相对。”
    • zuo_shanintegerrequired“坐山,二十四山 index。”
  • bazi_yongshenon 1 other server

    “schema 合法的已归一化出生主体 → 确定性唯一用神裁决。subject 可由用户明确事实组装,也可取自用户确认后的 subject_candidates;时间模糊或多候选时先归一化并确认。返回 status、selected_yongshen、conflicts、命中规则、格局上下文与裁决证据;conflicts 非空或 status 需复核时不静默改选。只要原始八字盘时用 bazi_ch…”

    Publisher declares: read-only yes · idempotent yes

    1 input, 1 required
    • subjectobjectrequired“已考时归一化的出生主体。”
  • “schema 合法的出生主体 + 人生问题 → 八字与紫微本命合参断语。subject 可由用户明确事实组装,也可取自用户确认后的 subject_candidates 候选;时间模糊或多候选时先归一化并确认。只要原始本命盘时改用 bazi_chart / ziwei_chart;逐年流年断语用 natal_liunian_query。因子计算由服务端内部完成,不对外返回。”

    Publisher declares: read-only yes · idempotent yes

    2 inputs, 2 required
    • subjectobjectrequired“已考时归一化的出生主体。”
    • life_topicsarrayrequired“人生问题域。”
  • natal_liunian_queryon 1 other server

    “schema 合法出生主体 + start_year/year_count/life_topics → 八字与紫微逐年流年合参断语。subject 必须来自用户确认事实或 subject_candidates;时间模糊先归一化确认。服务端内部计算因子;失败年保留结构化 error,不中断整批。只要单个原始流盘用 bazi_liupan / ziwei_liupan;本命断语用 natal_que…”

    Publisher declares: read-only yes · idempotent yes

    4 inputs, 4 required
    • subjectobjectrequired“已考时归一化的出生主体。”
    • start_yearintegerrequired“起始流年年号。”
    • year_countintegerrequired“连续查询年数。”
    • life_topicsarrayrequired“人生问题域(同 natal_query)。”
  • naming_surnameon 1 other server

    “按发音匹配候选姓氏:源姓必须是 Latin 拼音/英文拼写,匹配前会 trim、lowercase 并折叠常见拉丁变体;按 pinyin_exact / romanization_exact / phonetic_close 排序,无匹配时按百家姓顺序回退。max_candidates 是硬上限。仅处理姓氏;取字池用 naming_pick,整名评估用 naming_check。”

    Publisher declares: read-only yes · idempotent yes

    2 inputs, 1 required
    • source_surnamestringrequired“源姓氏的拉丁拼音或英文拼写(如 zhang / chan / lee)。”
    • max_candidatesinteger“返回候选数上限。”
  • “按用/喜五行角色取字池:selected_yongshen 直接使用八字用神裁决返回;first_role 与 second_role 选择字位角色,second_role 省略表示单名;生成阶段不提供 ji 字池。字池产出后组合候选名用 naming_compose,组合前查单字事实用 naming_character。”

    Publisher declares: read-only yes · idempotent yes

    3 inputs, 1 required
    • selected_yongshenobjectrequired“八字用神裁决返回对象。”
    • first_rolestring“第一字位角色;只能是 yong 或 xi。”
    • second_rolenull or string“第二字位角色;省略表示单名,只能是 yong 或 xi。”
  • naming_characteron 1 other server

    “按精确单字查询起名字库事实:字频、五行、笔画、部首、拼音、声调。不做繁简/异体折叠,不接受多字或空白变体;未收录时 character 为 null。适用于核对单字属性;取字池用 naming_pick,组合候选名用 naming_compose,整名评估用 naming_check。”

    Publisher declares: read-only yes · idempotent yes

    1 input, 1 required
    • charstringrequired“要查询的单个汉字。”
  • naming_composeon 1 other server

    “将已收录且非禁用的字组合为候选名:单名=first_chars 单字,双名=first_chars×second_chars 两字组合;按 first_chars 顺序生成并在 max_names 处截断。输入字池须来自 naming_pick,重复字会被拒绝。组合后的候选名评估用 naming_check,单字事实查询用 naming_character。”

    Publisher declares: read-only yes · idempotent yes

    3 inputs, 1 required
    • first_charsarrayrequired“第一位可选字(1-256 个)。”
    • second_charsarray“第二位可选字(双名用,1-256 个);省略=单名。”
    • max_namesinteger“返回候选名上限。”
  • naming_checkon 2 other servers

    “独立评估整名,不生成候选名;生成用 naming_compose,取字池用 naming_pick。接受 1-200 个去重候选名,逐个返回 evaluations:invalid 不中断批量,以 valid=false 与结构化 errors 说明长度、字库、禁用/必含字或音律问题。selected_yongshen 直接使用八字裁决对象且仅接受 resolved/partial;省略时不做五…”

    Publisher declares: read-only yes · idempotent yes

    4 inputs, 1 required
    • given_namesarrayrequired“要评估的名字(单名或双名,1-2 字)。”
    • selected_yongshennull or object“八字用神裁决返回对象;省略时不做五行角色评估。”
    • forbidden_charsarray“用户明确避讳的单字;候选名命中任一字即为 invalid。”
    • required_charsarray“用户要求必含的单字;候选名必须包含全部字符。”
  • “一次完成六爻起卦、排盘和结构化解读,适用于以卦象断事的问询(吉凶、成败、得失)。casting=auto 时会新起一卦,同一事禁止自动重试或重复调用;后续追问基于本次 Reading 解释,卦象事实按 schema 原样使用。需要时空方位决策时改用 qimen_ask。”

    Publisher declares: read-only no · idempotent no

    6 inputs, 4 required
    • questionstringrequired“本次要判断的一个具体目标”
    • longitudenumberrequired“起卦地经度(-180..180);必须显式传入,不做默认(精度要求)。”
    • standard_timestringrequired“起卦地标准时间 RFC3339(无 DST),必填。”
    • castingobject“起卦方式;按 schema 选择 auto / coins / yaos,用户手动记录按原顺序组装。”
    • focusobjectrequired“占问焦点:matter 自动推导用神,或显式指定六亲用神。”
    • topicstring“可选专题视角;省略时与 matter 相同。”
  • “一次完成奇门起局、因子投影和结构化解读,适用于需要时空方位信息的决策类问题(出行、谈判、寻物、择时方位等)。longitude 必填,城市需先转换;subject 与金函玉镜不兼容,非法组合在解读前失败。同一事禁止重新排局,后续追问基于本次 Reading 解释;起卦问事(得卦象而非方位盘)改用 liuyao_ask。”

    Publisher declares: read-only yes · idempotent yes

    7 inputs, 4 required
    • questionstringrequired“本次要判断的一个具体目标”
    • standard_timestringrequired“起局地标准时间 RFC3339(无 DST);来自用户明确事实或既有工具结果,节气换局按此时刻判定。”
    • methodobjectrequired“奇门方法事实;用户未指定高级方法时按 schema 描述选择常规组合,不臆造高级参数。”
    • longitudenumberrequired“起局地经度(-180..180);必须显式传入,城市需先转换为经度。”
    • focusobject or null“普通事象或显式用神;quarter / specialized rule 可按规则省略。”
    • rulestring“可选专占规则;由因子契约校验适用盘型”
    • subjectnull or object“可选命主;提供时用于年命干落宫;金函玉镜不接受。”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-11-15.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).

Counted from the listing

Parameters with a description
100% of 57
Tools with a description
100% of 24
Typical description length
173 characters

The tool set

Counted from the listing

Tools
24
Size of the list
about 43,416 tokens for an agent to load (characters ÷ 4)
Naming
24 of 24 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 0 of 24 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the remote endpoint (Streamable HTTP)

We connected to this URL on 2026-11-15 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste:
https://mcp.tokflux.com/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "liki": {
      "url": "https://mcp.tokflux.com/mcp"
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "liki": {
      "type": "http",
      "url": "https://mcp.tokflux.com/mcp"
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"liki","type":"http","url":"https://mcp.tokflux.com/mcp"}'
Claude Code
claude mcp add --transport http liki https://mcp.tokflux.com/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
  "mcpServers": {
    "liki": {
      "type": "streamableHttp",
      "url": "https://mcp.tokflux.com/mcp",
      "disabled": false,
      "autoApprove": []
    }
  }
}
Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
  "mcpServers": {
    "liki": {
      "httpUrl": "https://mcp.tokflux.com/mcp"
    }
  }
}
OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.liki]
url = "https://mcp.tokflux.com/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
  "context_servers": {
    "liki": {
      "url": "https://mcp.tokflux.com/mcp"
    }
  }
}
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://mcp.tokflux.com/mcp --transport http
  • The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
  • Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
  • The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

What do the published files and outside lists say?

Read as text · nothing run · no tool called

Package files

  • MCP SDK in the package files. Not read yet: added with the next daily run.
  • Build workflow. Not read yet: added with the next daily run.

Outside lists

  • CVE records (NVD). No CVE record in the NVD feeds we read links this server's repository. Source: read 2026-11-15. This product uses the NVD API but is not endorsed or certified by the NVD.
  • GitHub advisories. No GitHub advisory names this entry's listed package. Source: read 2026-11-15. GitHub Advisory Database, CC BY 4.0
  • Docker MCP catalogue. Not in the Docker MCP catalogue on 2026-11-15. Source: read 2026-11-15.
  • Cline marketplace. Not in the Cline marketplace on 2026-11-15. Source: read 2026-11-15.

Own host

  • security.txt. No security.txt at https://mcp.tokflux.com/.well-known/ (HTTP 404, 2026-11-15). security.txt found at https://liki.hk/.well-known/security.txt (Contact given; expires 2027-10-24). Source: mcp.tokflux.com/.well-known/security.txt · read 2026-11-15.
  • A2A agent card. No A2A agent card at https://mcp.tokflux.com/.well-known/ (HTTP 404, 2026-11-15). No A2A agent card at https://liki.hk/.well-known/ (HTTP 404, 2026-11-15). Source: mcp.tokflux.com/.well-known/agent-card.json · read 2026-11-15.

Read as text from published files and outside lists. Nothing was installed or run, and no tool was called. A fact, not a rating. How each fact is read

Does the registry listing match what we found?

Feature #6

The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.

Registry saysWe foundResultSource · date
Remote endpoint mcp.tokflux.com/mcpSession openedmatchesour test · 2026-11-15
No credential declared as requiredOpened a session without any credentialmatchesour test · 2026-11-15

Same tools as other registry entries

Tool lists read · names compared

Its 24 tools have exactly the same names as the tools of 1 other registry entry (all published under the same registry namespace). Their tool descriptions are also word for word the same.

This can be one publisher's family of servers or one template reused under many names. It is a fact about the published tool lists, not a judgement of the publisher and not a safety finding; we compared tool names, not code.

Shared tool names (12 of 24 shown):

bazhai_chartbazhai_layoutbazi_bondbazi_chartbazi_liupanbazi_yongshencity_infohuangli_daysliuyao_asknaming_characternaming_checknaming_compose

The other entries

All groups of servers with identical tool lists

Source: our read-only reads of each server's tool list · 2026-11-12 to 2026-11-15. No tool was called.

Choosing

Record checks

Public records · not a safety rating

1 of 2 record checks met · 7 do not apply

  • Not ranked by downloads: a remote server publishes no download figure
  • Not ranked by stars: no public GitHub repository
  • MetRegistry entry is active and says how to run itActive, with a package or a remote address.
  • Not metSource repository link opensThe registry entry gives no repository link.What changes this check: This check opens the repository link in the registry entry. GitHub's documentation describes changing a repository's visibility in its Settings, under Danger Zone, Change visibility. GitHub: setting repository visibility
  • Does not applyRepository is not archivedNo public GitHub repository to read.
  • Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
  • Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
  • Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
  • Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
  • Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
  • Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-11-15. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral

Common questions about hk.liki/liki

Answered from the data above

Who publishes hk.liki/liki?

The registry ties the namespace hk.liki to the domain liki.hk; only its owner can publish under it. These are facts from the registry and GitHub, not a rating.

Does hk.liki/liki need an API key or sign-in?

It opened a session without any credential on 2026-11-15. The registry entry declares no required credential; no declaration is not a guarantee.

Has hk.liki/liki been security tested?

Partly. 2 of the 14 checks that apply to it were exercised. We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so). This is our choice, not a block by the server. ProtocolProbe publishes no security verdict for a named server.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Not probed (no operator permission)

We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so). This is our choice, not a block by the server. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-11-15
  1. Inventory: exercised
  2. Hidden instructions: exercised
  3. Real execution: not run · our policy
  4. Secret leak: not run · nothing to check it against
  5. Internal addresses: not run · our policy
  6. Unconfirmed changes: not run · our policy
  7. Bad input: not run · our policy
  8. Model requests: not run · nothing to check it against
  9. Sensitive questions: not run · nothing to check it against
  10. Folder boundary: not run · our policy
  11. Log leaks: not run · nothing to check it against
  12. Hidden content: not run · nothing to check it against
  13. Fake assistant turns: not applicable
  14. Token passthrough: not applicable
  15. Token audience: not applicable
  16. Sign-in redirect: not run · our policy
  17. Consent handling: not testable from outside
  18. Sign-in metadata: not applicable

2 exercised12 not run (reason given)4 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 14 checks that apply to it were exercised. We do not publish security-check outcomes for named servers. These 18 checks are separate from the record checks at the top of this page, which read public records only.

Exercised · 2
  • 1Inventory
    tool-list
    Reads the declared tools, resources and prompts.exercised
  • 2Hidden instructions
    description-poisoning
    Looks for hidden instructions in tool descriptions.exercised
Not run, with the reason · 12
  • 3Real execution
    real-execution
    Calls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 4Secret leak
    canary-leak
    Plants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 5Internal addresses
    ssrf
    Checks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 6Unconfirmed changes
    write-without-confirmation
    Checks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 7Bad input
    error-handling
    Sends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 8Model requests
    sampling
    Checks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 9Sensitive questions
    elicitation-sensitive-data
    Checks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 10Folder boundary
    root-boundary
    Checks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 11Log leaks
    logging-side-channel
    Checks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 12Hidden content
    audience-hiding
    Checks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against
  • 16Sign-in redirect
    open-redirect
    Checks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy
  • 17Consent handling
    confused-deputy
    Checks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
Does not apply to this server · 4
  • 13Fake assistant turns
    fake-assistant-turn
    Checks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
  • 14Token passthrough
    token-passthrough
    Checks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable
  • 15Token audience
    token-audience-validation
    Checks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable
  • 18Sign-in metadata
    oauth-url-scheme
    Checks the published sign-in metadata for unsafe URLs.No sign-in (OAuth) metadata is published, so there are no sign-in addresses to check.not applicable

Source: our own test, 2026-11-15, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

  1. 0 msStarted a read-only session with the server's remote endpoint
  2. 2,006 msConnected after 0 redirects. No credential was sent or needed.
  3. Read the inventory: 24 tools, 0 resources, 0 prompts.
  4. 9,192 msFinished: 2 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified
pending: added at the next monthly refresh
listed 2026-11-15; not classified yet
Pricing modelAI-classified
pending: added at the next monthly refresh
the website is not read yet
Programming language
does not apply
no existing GitHub repository (server declares no repository link, so there is nothing to fetch)
Hosting type
registry · 2026-11-15
MCP capability
tools
our test · 2026-11-15
Transport
streamable HTTP
registry · 2026-11-15
Required credentials
none declared
registry · 2026-11-15 · no declaration is not a guarantee
Package registry
does not apply
remote-only server: no package is shipped, so there is no package registry
Freshness
0–30 days
registry updatedAt · 2026-11-15
Lifecycle status
registry · 2026-11-15
License class
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Integrity hash
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Signature / provenance
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Dependency advisories
does not apply
ships no package, so there are no dependencies to audit
Popularity
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Publisher signals
not stated
no readable GitHub owner to describe
Maintenance
does not apply
server declares no repository link, so there is nothing to fetch
Environment
the publisher's infrastructure
where it runs, from the hosting type · 2026-11-15

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “hk.liki/liki: MCP server record.” Data checked 2026-11-15. https://protocolprobe.com/mcp/servers/hk.liki/liki

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

ProtocolProbe: 1 of 2 record checks met

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/hk.liki/liki)](https://protocolprobe.com/mcp/servers/hk.liki/liki)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here, except for a server whose operator has claimed it and given permission (that server's page says so).

Write to hello@protocolprobe.com · corrections log · methodology