MCP servers › com.mianlingai › mianling
MCP server · registry snapshot 2026-11-18 · last tested 2026-11-18
mianling MCP server
Registry name com.mianlingai/mianling
面灵AI 面试助手 — the publisher's title
by mianlingai.com · domain (the registry's namespace rule)Website ↗
面灵AI:查面试与笔试记录和报告、管理简历、搜索校招岗位与面试题、跟进网申进度,OAuth 授权访问个人账户 — the publisher's description
Summary
com.mianlingai/mianling is a remote MCP server listed in the official MCP registry at version 1.0.0, under the namespace of the domain mianlingai.com. On 2026-11-18 ProtocolProbe connected to it in read-only mode and read its inventory: 148 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- not applicable: The version the registry lists can be installed and is not withdrawn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
- 148
- Last tested
- 2026-11-18
Tool list size
41,537 tokens on Claude Opus 5.5
Added to every request that loads this server's tools (148 tools). Counted with Anthropic's token counter on 2026-11-18, from the tool list we read on 2026-11-18. Median across 28,560 counted servers: 2,657 tokens. How it is counted
How a client gets in
Connects without signing in
Read from the server's public metadata on 2026-11-18 (api.mianlingai.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 (1.0.0).
Observed fact
This server accepted a session without any credential and lists 55 tools whose name or declaration suggests they change data (redeem_credits, activate_subscription_card, refund_subscription_card, create_payment_order, update_feedback_notify_email and 50 more). That is our reading of the names; we did not call them. Source: our connection, 2026-11-18.
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-11-18
- Mode
- read-only (no tool calls)
- Latest version
- 1.0.0, published 2026-11-17 (registry, as of the 2026-11-18 snapshot)
- First listed version
- 2026-11-17 (earliest version still in the registry; older removed versions would be earlier)
- Registry data
- snapshot 2026-11-18
- Package and repository
- checked 2026-11-18
- 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
New in the registry: not in the list of 2026-11-17, listed on 2026-11-18 with version 1.0.0 (published 2026-11-17).
Source: the official MCP Registry list on 2026-11-17 and on 2026-11-18.
What it is
What does this server offer?
Observed inventoryNone of its 148 tools are described as changing anything. For 148 the reading was uncertain, so no mark is shown.
- get_product_overviewon 9 other servers
“面灵AI 的产品介绍:各产品线能做什么、支持哪些面试 / 笔试平台、客户端下载、价格页与帮助文档链接。回答用户关于面灵AI 的任何问题前先读一遍。”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
- list_planson 68 other servers
“列出当前在售的套餐、价格与每档包含的时长 / 次数 / 有效期。”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
- get_purchase_linkon 5 other servers
“生成某个套餐的购买链接,交给用户在浏览器中打开:用户登录面灵AI 后自动进入该套餐的付款,支持支付宝与微信支付。商品 ID 取自 list_plans。”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
productIdstringrequired“list_plans 中的商品 ID”
- get_campus_job_filterson 1 other server
“校招 / 实习岗位库的筛选项可选值(招聘类型、职能、城市、公司)与岗位库规模。”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
- search_campus_jobson 2 other servers
“在面灵AI 的校招 / 实习岗位库中搜索在招岗位,返回第一页结果(每行一个岗位)。投递直达链接与后续翻页需在面灵AI 网站登录后查看。”
Publisher declares: read-only yes · destructive no · open-world no
6 inputs
keywordstring“岗位名称或职责关键词,如「后端开发」「产品经理」”companystring“公司名,如「字节跳动」”citystring“工作城市,如「上海」,取值见 get_campus_job_filters 的 city 一行”employmentTypestring“招聘类型,取值见 get_campus_job_filters 的 employmentType 一行”jobFunctionstring“职能,取值见 get_campus_job_filters 的 jobFunction 各行”sortstring“hot = 热度,recent = 最近收录,published = 最近发布”
- search_interview_questionson 1 other server
“按公司、岗位或关键词搜索真实面试中被问过的题目,按出现频次排序,返回第一页(每行一题)。参考解析需在面灵AI 网站登录后查看。”
Publisher declares: read-only yes · destructive no · open-world no
4 inputs
companystring“公司名”positionstring“岗位,如「后端开发」「算法」”keywordstring“题目关键词”sortstring“hot = 出现次数最多,recent = 最近被问到”
- get_accounton 181 other servers
“查看当前账号:剩余面试 / 笔试时长、会员等级与到期时间、模拟面试与押题次数、网申额度,以及最近 10 笔订单的付款状态。用户通过购买链接付款后,用它确认是否到账。(需要用户授权,范围 account:read)”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
- list_interviewson 9 other servers
“列出用户的面试记录(实时面试与模拟面试),每行一场,新的在前,每页 20 场。(需要用户授权,范围 interviews:read)”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs
typestring“INTERVIEW = 实时面试,MOCK_INTERVIEW = 模拟面试;不传 = 全部”pageinteger
- get_interview_reporton 2 other servers
“读取某场面试的复盘报告:总结、各维度得分、优点与不足、建议,以及逐题的问答、得分、评价与改进建议。面试 ID 取自 list_interviews。(需要用户授权,范围 interviews:read)”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
interviewIdstringrequired
- get_interview_transcripton 1 other server
“读取某场面试的完整问答记录(面试官与用户的发言,按时间顺序,每次 80 条,用 offset 翻页)。(需要用户授权,范围 interviews:read)”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs, 1 required
interviewIdstringrequiredoffsetinteger
- list_resumeson 2 other servers
“列出用户上传的简历(每行一份)。示例简历标注为 sample,不代表用户本人背景。(需要用户授权,范围 resumes:read)”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
- get_resumeon 10 other servers
“读取一份简历的文本内容。简历 ID 取自 list_resumes。(需要用户授权,范围 resumes:read)”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
resumeIdstringrequired
Show 88 more tools
- list_job_applicationson 2 other servers
“列出用户的网申投递记录:总体统计与每条投递的投递 ID、公司、岗位、投递状态、进展(每页 50 条)。按投递操作的工具所需的投递 ID 取自这里。(需要用户授权,范围 job_applications:read)”
Publisher declares: read-only yes · destructive no · open-world no
1 input
pageinteger
- get_login_deviceson 1 other server
“查看近 7 天登录过该账号的设备数量,以及是否检测到两台以上电脑(网页或客户端)登录,用于判断账号是否被他人共用。(需要用户授权,范围 account:read)”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
- redeem_creditson 1 other server
“把账户中的积分兑换为面试时长与模拟面试次数:每 200 积分换 60 分钟时长与 2 次模拟面试,一次兑换全部积分,不足 200 的余数随之清零。积分余额见 get_account。会消耗用户的时长、次数或产生付款,执行前向用户说明扣费内容并取得同意。(需要用户授权,范围 account:write)”
Publisher declares: read-only no · destructive yes · open-world no
Takes no inputs.
- get_gift_code_infoon 1 other server
“查询一个礼包码(含代理商兑换卡)包含的权益、是否过期、是否已领完、当前账号能否领取。(需要用户授权,范围 account:read)”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
codestringrequired“礼包码或兑换卡密”
- redeem_gift_codeon 2 other servers
“领取一个礼包码(含代理商兑换卡),权益立即计入当前账号;每个码每个账号只能领一次。可先用 get_gift_code_info 查看内容。(需要用户授权,范围 account:write)”
Publisher declares: read-only no · destructive no · open-world no
1 input, 1 required
codestringrequired“礼包码或兑换卡密”
- list_pending_subscription_cardson 1 other server
“列出用户已购买但尚未激活的会员卡(下单时选择「稍后激活」的卡),以及每张卡能否原路退款、可退金额。(需要用户授权,范围 account:read)”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
- activate_subscription_cardon 1 other server
“激活一张未激活的会员卡:从此刻开始计时,已有生效中的会员时接续在其后;激活后不能再退款。卡 ID 取自 list_pending_subscription_cards。会消耗用户的时长、次数或产生付款,执行前向用户说明扣费内容并取得同意。(需要用户授权,范围 account:write)”
Publisher declares: read-only no · destructive yes · open-world no
1 input, 1 required
cardIdstringrequired
- refund_subscription_cardon 1 other server
“退掉一张未激活的会员卡:款项原路退回付款账户,卡同时作废。只有 list_pending_subscription_cards 中标有可退金额的卡才能退。会消耗用户的时长、次数或产生付款,执行前向用户说明扣费内容并取得同意。(需要用户授权,范围 account:write)”
Publisher declares: read-only no · destructive yes · open-world no
1 input, 1 required
cardIdstringrequired
- list_agent_grantson 2 other servers
“列出当前账号已授权的 AI 助理:名称、网址、授权范围、授权时间与最近使用时间。(需要用户授权,范围 account:read)”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
- revoke_agent_granton 1 other server
“撤销一个 AI 助理的授权,该助理持有的令牌立即失效;撤销的若是当前这个助理自己的授权,之后的调用需用户重新授权。授权 ID 取自 list_agent_grants。(需要用户授权,范围 account:write)”
Publisher declares: read-only no · destructive no · open-world no
1 input, 1 required
grantIdstringrequired
- check_order_statuson 11 other servers
“查询一笔订单是否已付款到账。用户在收银台付款后用它确认;状态为 PAID 即已到账。(需要用户授权,范围 account:read)”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
orderNumberstringrequired“下单工具返回的订单号,或 get_account 最近订单中的订单号”
- create_payment_orderon 3 other servers
“为某个商品下单并生成付款链接,由用户本人完成付款。wxpay 返回 weixin:// 开头的微信支付链接,需生成二维码供用户用微信扫一扫(直接点开无效);alipay 返回一个网页地址,用户在电脑浏览器打开后用支付宝扫页面上的二维码;alipay_wap 返回手机浏览器打开即跳转支付宝 App 的地址。付款后用 check_order_status 确认到账。商品 ID 取自 list_pla…”
Publisher declares: read-only no · destructive yes · open-world no
4 inputs, 2 required
productIdstringrequired“list_plans 中的商品 ID”channelstringrequired“wxpay = 微信扫码;alipay = 电脑浏览器打开、支付宝扫码;alipay_wap = 手机浏览器打开、跳转支付宝”couponCodestring“优惠码(仅新用户首单可用)”deferActivationboolean“仅会员卡可用:true = 付款后先存为未激活卡,由用户在面试前自行激活(activate_subscription_card)”
- preview_coupon
“预览优惠码能否使用、折扣多少;传商品 ID 时同时算出该商品的折后价。优惠码仅新用户首单可用,不会因预览而占用。(需要用户授权,范围 account:read)”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs, 1 required
couponCodestringrequired“优惠码”productIdstring“list_plans 中的商品 ID;不传只校验优惠码本身”
- get_upgrade_offer
“查看用户当前是否有升级券(购买满 2 次尝鲜包后发放的一次性折扣)、折扣多少、适用哪些商品、何时过期。下单时自动抵扣,无需填写。(需要用户授权,范围 account:read)”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
- submit_feedbackon 157 other servers
“以用户身份向面灵AI 提交一条反馈(故障、建议或其他),可附截图;处理进展与回复用 list_my_feedbacks / get_my_feedback 查看。(需要用户授权,范围 account:write)”
Publisher declares: read-only no · destructive no · open-world no
5 inputs, 1 required
messagestringrequired“反馈正文”titlestring“标题;不传取正文前 20 字”typestring“BUG = 故障,SUGGESTION = 建议,OTHER = 其他”notifyEmailstring“有回复时通知的邮箱;不传则只在站内通知”screenshotsarray“截图,最多 6 张”
- list_my_feedbackson 1 other server
“列出用户提交过的反馈(每行一条,最近有回复的在前,每页 20 条),含状态、往来条数、是否有未读回复与最后一条消息摘要。(需要用户授权,范围 account:read)”
Publisher declares: read-only yes · destructive no · open-world no
1 input
pageinteger
- get_my_feedbackon 2 other servers
“读取一条反馈的完整往来(用户与客服的每条消息),读取后该反馈的未读标记清除。反馈 ID 取自 list_my_feedbacks。(需要用户授权,范围 account:read)”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
feedbackIdstringrequired
- reply_to_my_feedbackon 1 other server
“在用户自己的一条反馈下追加一条消息(可附截图),客服会继续跟进。反馈 ID 取自 list_my_feedbacks。(需要用户授权,范围 account:write)”
Publisher declares: read-only no · destructive no · open-world no
3 inputs, 2 required
feedbackIdstringrequiredcontentstringrequiredscreenshotsarray“截图,最多 6 张”
- update_feedback_notify_emailon 1 other server
“修改一条反馈有回复时通知的邮箱;传 null 表示不再发邮件、只在站内通知。反馈 ID 取自 list_my_feedbacks。(需要用户授权,范围 account:write)”
Publisher declares: read-only no · destructive no · open-world no
2 inputs, 2 required
feedbackIdstringrequirednotifyEmailstring or nullrequired
- get_wechat_support_link
“获取用户专属的微信客服链接,用户在微信中打开即可与客服对话,对话自动关联其账号。链接三天内有效。(需要用户授权,范围 account:read)”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
- upload_resumeon 6 other servers
“上传一份简历文件(PDF / JPG / PNG / WEBP),服务端读出文字后存为用户的新简历,面试与网申可直接选用。文件内容以 base64 传入。返回新简历 ID,可用 get_resume 回读文字。(需要用户授权,范围 resumes:write)”
Publisher declares: read-only no · destructive no · open-world no
3 inputs, 2 required
fileNamestringrequired“文件名,如「张三-后端.pdf」”fileBase64stringrequired“文件内容,以 base64 传入”titlestring“简历标题;不传取文件名”
- create_resume_from_texton 1 other server
“用一段文字新建一份简历(如按用户要求修改后的简历全文),面试与网申可直接选用;不生成文件,原有简历不受影响。返回新简历 ID。(需要用户授权,范围 resumes:write)”
Publisher declares: read-only no · destructive no · open-world no
2 inputs, 2 required
titlestringrequired“简历标题”contentstringrequired“简历全文”
- delete_resumeon 1 other server
“删除用户的一份简历。简历 ID 取自 list_resumes。删除后不能恢复,执行前向用户说明要删除的内容并取得同意。(需要用户授权,范围 resumes:write)”
Publisher declares: read-only no · destructive yes · open-world no
1 input, 1 required
resumeIdstringrequired
- rename_interviewon 1 other server
“修改一场面试记录的标题(实时面试与模拟面试均可)。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
2 inputs, 2 required
interviewIdstringrequired“面试 ID,取自 list_interviews”titlestringrequired
- delete_interviewon 2 other servers
“删除一场面试记录,连同其报告与问答记录一并从列表中移除。删除后不能恢复,执行前向用户说明要删除的内容并取得同意。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive yes · open-world no
1 input, 1 required
interviewIdstringrequired“面试 ID,取自 list_interviews”
- retry_interview_reporton 1 other server
“重新生成一份生成失败的面试报告(get_interview_report 提示生成失败时使用)。生成在后台进行,约需一两分钟,之后用 get_interview_report 查看。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
1 input, 1 required
interviewIdstringrequired“面试 ID,取自 list_interviews”
- generate_interview_experienceon 1 other server
“由一场实时面试的记录整理出面经(面试官问了哪些问题),保存到该面试记录并返回全文;已有面经时重新生成并覆盖。只支持时长满 5 分钟的实时面试。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
1 input, 1 required
interviewIdstringrequired“面试 ID,取自 list_interviews”
- export_interview_markdownon 1 other server
“把一场面试的完整记录(问答与答题助手的解题)整理成排版规整的 Markdown,回包给出字数、目录、开头一段与全文下载链接。整理需要几十秒。(需要用户授权,范围 interviews:read)”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
interviewIdstringrequired“面试 ID,取自 list_interviews”
- list_answer_style_sourceson 1 other server
“列出可用于「学习我的回答风格」的面试记录(用户本人回答足够多的场次),新的在前。(需要用户授权,范围 interviews:read)”
Publisher declares: read-only yes · destructive no · open-world no
1 input
limitinteger
- learn_answer_styleon 1 other server
“从一场面试记录中学习用户本人的回答风格,生成一段风格要求文字,可作为发起面试时的「额外回答要求」使用。面试 ID 取自 list_answer_style_sources。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
1 input, 1 required
interviewIdstringrequired“面试 ID,取自 list_interviews”
- get_voiceprint_statuson 1 other server
“查看用户是否已登记声纹(电话面试模式用它区分用户与面试官的声音)以及登记时间、声纹服务当前是否可用。声纹在发起面试的音频设置中录音登记。(需要用户授权,范围 interviews:read)”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
- list_examson 4 other servers
“列出用户的笔试记录(桌面客户端截屏答题的场次),每行一场,最近有更新的在前,每页 20 场。(需要用户授权,范围 interviews:read)”
Publisher declares: read-only yes · destructive no · open-world no
1 input
pageinteger
- get_examon 2 other servers
“读取一场笔试记录:概况与每道题一行概览(题面开头、作答字数)。传 question(题号,从 1 开始)时附上该题的完整题面与作答。整场全文用 export_exam_markdown。(需要用户授权,范围 interviews:read)”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs, 1 required
examIdstringrequired“笔试记录 ID,取自 list_exams”questioninteger“题号,从 1 开始”
- update_examon 1 other server
“修改一场笔试记录的标题,或改绑 / 解绑它对应的岗位。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
3 inputs, 1 required
examIdstringrequired“笔试记录 ID,取自 list_exams”titlestringgoalIdstring or null“用户的岗位 ID;传 null 解除绑定,不传不改”
- delete_examon 1 other server
“删除一场笔试记录及其全部题目与作答。删除后不能恢复,执行前向用户说明要删除的内容并取得同意。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive yes · open-world no
1 input, 1 required
examIdstringrequired“笔试记录 ID,取自 list_exams”
- export_exam_markdownon 1 other server
“把一场笔试记录的全部题目与作答整理成排版规整的 Markdown(代码原样保留),回包给出字数、目录、开头一段与全文下载链接。整理需要几十秒。(需要用户授权,范围 interviews:read)”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
examIdstringrequired“笔试记录 ID,取自 list_exams”
- start_examon 3 other servers
“在用户电脑上开始一场笔试,与桌面客户端笔试页点击「开始笔试」完全相同:按所给的答题模式、考试平台、岗位开场,打开笔试浮窗并收起主窗口(平台需要或用户在设置中开启时为原生笔试窗口)。需要用户电脑上的桌面客户端已登录并在运行;客户端不在线、版本较旧、额度不足、已有面试或笔试在进行时如实返回原因,不会开始。开始本身不扣费,之后每次截图答题按所选模式扣用户的时长。开始后用户在考试页面上照常使用浮窗截图答…”
Publisher declares: read-only no · destructive yes · open-world no
5 inputs
modestring“答题模式:instant = 秒答模式(每张截图 2 分钟);quick = 快速模式(每张截图 2 分钟);programming = 编程模式(每题 5 分钟)。会员不扣时长。不传 = 用户在客户端笔试页当前选择的模式”platformstring or null“考试平台名称(如「牛客」「北森」「赛码」「华为时习知」「国考云」「易考锁屏客户端」),不在客户端名录中的平台照用户的说法填写;少数平台会自动打开所需的截图方式。传 null = 不指定平台,不传 = 沿用客户端笔试页当前选择”goalIdstring or null“绑定的岗位 ID,取自 list_interview_targets;传 null = 不绑定岗位。与 jobName 二选一,都不传 = 沿用客户端笔试页当前填写的岗位”jobNamestring“新岗位名称:用户没有保存过该岗位时填写,开始时当场创建(与在笔试页直接输入岗位相同)”companyNamestring“新岗位的公司名称,与 jobName 一起填写”
- end_examon 1 other server
“把一场进行中的笔试记录标记为已结束,并自动生成标题。只改记录状态,不会关闭用户电脑上的笔试窗口。笔试的发起与截屏答题只能在桌面客户端进行。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
1 input, 1 required
examIdstringrequired“笔试记录 ID,取自 list_exams”
- list_interview_targetson 1 other server
“列出用户已保存的面试岗位(公司 + 岗位名),发起面试 / 模拟面试时需要其中一个岗位 ID。每行一个,新的在前。(需要用户授权,范围 interviews:read)”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
- create_interview_targeton 1 other server
“新建一个面试岗位(公司 + 岗位名,可附岗位描述),返回岗位 ID,供发起面试使用。与网页端「新建岗位」相同。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
3 inputs, 1 required
namestringrequired“岗位名称”companyNamestring“公司名称”descriptionstring“岗位描述(JD),面试作答时作为背景”
- start_interviewon 5 other servers
“为用户发起一场实时面试或模拟面试,返回面试页链接,由用户在浏览器打开(仅支持网页版,不调起桌面客户端;用户需在浏览器登录同一账号)。实时面试:用户在面试页按提示共享带声音的会议标签页,点击「开始面试」后按在线时长扣面试时长;模拟面试:创建时预扣 1 次模拟面试次数。同一类型同时只能有一场进行中。未指定的高级配置(回答风格、自定义要求、翻译、复盘录音、联网搜索、知识库)沿用用户在网页端保存的面试偏…”
Publisher declares: read-only no · destructive yes · open-world no
14 inputs, 2 required
typestring“INTERVIEW = 实时面试,MOCK_INTERVIEW = 模拟面试”targetIdstringrequired“岗位 ID”resumeIdstringrequired“简历 ID”langstring“面试语言(决定语音识别模型);不传 = 用户偏好中的语言”extraLangsarray“仅实时面试:面试中还可切换到的其他语言;不传 = 用户偏好”knowledgeBaseIdsarray“知识库 ID 列表;实时面试不传 = 用户偏好中选中的知识库,模拟面试仅在开启 AI 辅助时生效”modestring“仅实时面试:online = 线上面试(采集会议声音),phone = 电话面试(手机免提外放、麦克风采集,需已注册声纹,仅中文 / 粤语 / 英语)”roundstring“仅实时面试:本场是该岗位第几轮”difficultystring“仅模拟面试:难度(工作年限)”assistModeboolean“仅模拟面试:是否开启 AI 辅助(每道题给出参考回答)”questionCountinteger“仅模拟面试:题量;不传 = AI 自行安排”basicsRatiointeger“仅模拟面试:基础知识题占比 0–100;不传 = AI 自行安排”focusstring“仅模拟面试:本场主攻方向”skipIntroboolean“仅模拟面试:跳过自我介绍”
- get_live_session_statuson 3 other servers
“查看用户当前进行中的实时面试、模拟面试与笔试:会话 ID、岗位、开始时间、到期时间,以及面试页是否在线、由哪一端执行(桌面客户端 / 网页)和页面状态(是否已点开始、AI 是否在作答、语言、自动回答、一题一卡等)。(需要用户授权,范围 interviews:read)”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
- end_live_interviewon 1 other server
“结束用户进行中的实时面试或模拟面试,与面试页上的「结束面试」相同:结算本场时长(实时面试退回最后一句之后多扣的时长)并开始生成复盘报告。结束后面试页会在几秒内自动关闭。结束后不能恢复。会消耗用户的时长、次数或产生付款,执行前向用户说明扣费内容并取得同意。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive yes · open-world no
1 input
typestring“INTERVIEW = 实时面试,MOCK_INTERVIEW = 模拟面试”
- set_live_interview_optionson 1 other server
“修改进行中的实时面试的设置:识别语言(只能在开场时选定的语言集合内切换,切换后页面自动重连一次)、自动回答(关闭后只在「立即回答」时作答)、一题一卡(同一道题的续说与追问归入一张卡)。自动回答与一题一卡只有桌面客户端的面试浮窗支持。只传要改的项。需要用户已在网页或桌面客户端打开这场面试的页面并处于连接状态;操作由该页面执行,与用户点击对应按钮完全相同。(需要用户授权,范围 interviews:…”
Publisher declares: read-only no · destructive no · open-world no
3 inputs
langstring“识别语言”autoAnswerboolean“自动回答”turnCardsboolean“一题一卡”
- ask_live_interviewon 1 other server
“在进行中的实时面试里替用户提一个问题:这段文字作为面试官的问题交给 AI 作答,答案显示在面试页上;AI 正在作答时先打断那一路再回答这一句。与桌面客户端「语音提问」走同一条作答链路,需用户已点击「开始面试」。作答期间按在线时长计费。需要用户已在网页或桌面客户端打开这场面试的页面并处于连接状态;操作由该页面执行,与用户点击对应按钮完全相同。会消耗用户的时长、次数或产生付款,执行前向用户说明扣费内…”
Publisher declares: read-only no · destructive yes · open-world no
1 input, 1 required
questionstringrequired“问题原文”
- answer_live_interview_nowon 1 other server
“在进行中的实时面试里按「立即回答」:以面试官刚说的、还没回答的那段话(至少 6 个字)立即作答;AI 正在作答时先打断再答。关闭自动回答时用它触发作答。需要用户已在网页或桌面客户端打开这场面试的页面并处于连接状态;操作由该页面执行,与用户点击对应按钮完全相同。会消耗用户的时长、次数或产生付款,执行前向用户说明扣费内容并取得同意。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive yes · open-world no
Takes no inputs.
- interrupt_live_interview_answeron 1 other server
“打断进行中的实时面试里 AI 正在输出的回答(已输出的部分保留)。只在 AI 正在输出时有效。需要用户已在网页或桌面客户端打开这场面试的页面并处于连接状态;操作由该页面执行,与用户点击对应按钮完全相同。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
Takes no inputs.
- answer_mock_interviewon 1 other server
“在进行中的模拟面试里提交用户对当前问题的作答(文字),与面试页上编辑后点击「发送」相同;提交后 AI 面试官给出下一题或结束面试。AI 面试官正在提问时不能提交。需要用户已在网页或桌面客户端打开这场面试的页面并处于连接状态;操作由该页面执行,与用户点击对应按钮完全相同。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
1 input, 1 required
answerstringrequired“作答原文”
- set_mock_interview_assiston 1 other server
“开关进行中的模拟面试的 AI 辅助(每道题给出参考回答),与面试页上的开关相同。需要用户已在网页或桌面客户端打开这场面试的页面并处于连接状态;操作由该页面执行,与用户点击对应按钮完全相同。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
1 input, 1 required
enabledbooleanrequired
- solve_screen_questionon 1 other server
“让用户正在运行的页面立即截取用户屏幕并解题,与按「截图答题」按钮 / 快捷键相同;按当前档位与页数扣费,答案显示在用户的页面上。AI 助理不需要也无法提供图片。执行端:用户正在进行笔试时为桌面客户端的笔试浮窗(需已开始本场笔试);否则为进行中的实时面试 / 模拟面试页面里的截图答题(网页端需已共享屏幕)。会消耗用户的时长、次数或产生付款,执行前向用户说明扣费内容并取得同意。(需要用户授权,范围 …”
Publisher declares: read-only no · destructive yes · open-world no
Takes no inputs.
- follow_up_screen_questionon 1 other server
“对用户页面上当前这道截图题追问一句(如「换一种解法」「解释第 3 行」),与在页面上输入追问相同;AI 正在作答时不能追问。笔试追问按档位计费。执行端:用户正在进行笔试时为桌面客户端的笔试浮窗(需已开始本场笔试);否则为进行中的实时面试 / 模拟面试页面里的截图答题(网页端需已共享屏幕)。会消耗用户的时长、次数或产生付款,执行前向用户说明扣费内容并取得同意。(需要用户授权,范围 intervie…”
Publisher declares: read-only no · destructive yes · open-world no
1 input, 1 required
messagestringrequired“追问内容”
- answer_exam_nowon 1 other server
“在桌面客户端的笔试浮窗上按「直接答」:停止仍在进行的查证,按已有内容立即写出答案(不是中止,本题照常完成)。只在笔试题正在作答时有效。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
Takes no inputs.
- get_question_bank_question
“查看题库中一道题的详情:题干、参考解析、分类、被问次数、问过的公司与岗位、其他问法。题目 ID 取自 search_interview_questions、draw_questions 等工具。参考解析需要用户登录授权,免费用户每天可查看的解析数量有限(已看过的题不重复计数),额度用完时返回 locked。”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
idstringrequired“题目 ID”
- list_related_questions
“列出与某道题相关的高频题(优先同标签,其次同岗位,按被问次数排序),每行一题。题目 ID 取自 search_interview_questions 等工具。”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs, 1 required
idstringrequired“题目 ID”limitinteger“返回条数”
- list_question_bank_companies
“题库中的公司热榜:按真实面试出现次数排序列出公司及其题目数,可按岗位或关键词筛选。公司名可作为 search_interview_questions、draw_questions 的 company 参数。未登录时只能查看前几页。”
Publisher declares: read-only yes · destructive no · open-world no
3 inputs
positionstring“岗位,如「后端开发」「算法」”keywordstring“公司名关键词”pageinteger“页码,从 1 开始”
- draw_questions
“从题库抽一组题用于刷题:random 为随机抽取,real 为按真实出现频次抽取。返回题目 ID 与题干,参考解析用 get_question_bank_question 逐题查看。”
Publisher declares: read-only yes · destructive no · open-world no
8 inputs
positionstring“岗位,如「后端开发」「算法」”companystring“公司名”employmentTypestring“招聘类型,如「校招」「实习」「社招」”interviewRoundstring“面试轮次,如「一面」「二面」「HR面」”categorystring“题目分类”keywordstring“题目关键词”modestring“random = 随机,real = 按真实频次”sizeinteger“抽取题数”
- draw_interview_session
“从题库还原一场真实面试:抽取一篇面经中面试官按顺序追问的完整题目链(公司、岗位、月份、题目 ID 顺序即追问顺序)。该筛选条件下没有足够长的场次时如实返回「没有」,此时可改用 draw_questions 抽散题。”
Publisher declares: read-only yes · destructive no · open-world no
4 inputs
positionstring“岗位,如「后端开发」「算法」”companystring“公司名”employmentTypestring“招聘类型,如「校招」「实习」「社招」”interviewRoundstring“面试轮次,如「一面」「二面」「HR面」”
- save_questions_to_knowledge_base
“把题库中选中的题目连同参考解析新建为一份面试知识库,真实面试时面试助手可直接使用。题目 ID 取自 search_interview_questions 等工具,一次最多 30 道;没有参考解析的题不会加入,与查看解析共用每日额度,因额度不足未加入的题数在 locked 中返回。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
1 input, 1 required
idsarrayrequired
- share_question_prediction
“为一条已完成(done)的押题生成公开分享链接。访客打开只能看到总述与前 3 题的题干和考察点,看不到作答思路与简历素材。记录 ID 取自 list_question_predictions;可用 unshare_question_prediction 取消。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
1 input, 1 required
idstringrequired“押题记录 ID”
- unshare_question_prediction
“取消一条押题的公开分享,之前发出的分享链接随即无法打开。记录 ID 取自 list_question_predictions。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
1 input, 1 required
idstringrequired“押题记录 ID”
- submit_interview_experience
“以用户名义提交一篇面经(公司、岗位、轮次、面试月份、正文 10–8000 字)。提交后进入人工审核,审核通过才进入题库;审核状态用 list_my_interview_experiences 查看。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
5 inputs, 3 required
companystringrequiredpositionstringrequiredroundstringperiodstringcontentstringrequired
- list_my_interview_experiences
“列出用户提交过的面经:公司、岗位、轮次、面试月份、审核状态与审核备注,每页最多 30 条。(需要用户授权,范围 interviews:read)”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs
pagenumberpageSizenumber
- start_question_predictionon 1 other server
“为用户的目标岗位发起一次题库定制(押题):检索真实题库并结合简历,生成近期高频题与作答思路。发起后在后台生成,约 2–5 分钟,立即返回记录 ID;之后用 get_question_prediction 查看进度与结果,状态为 done 才算完成。非 PRO 用户生成成功后扣 1 次押题次数(失败不扣),PRO 用户占用本周 5 次额度中的 1 次(失败退回)。会消耗用户的时长、次数或产生付款,…”
Publisher declares: read-only no · destructive yes · open-world no
4 inputs, 1 required
goalIdstringrequired“目标岗位 ID”resumeIdstring“简历 ID,取自 list_resumes;不传则只按岗位出题”experiencestring“经验水平:应届生 / 1-3 年经验 / 3-5 年经验 / 5-10 年经验 / 10 年以上”langstring“输出语言的英文名,如 Simplified Chinese、English;不传按用户界面语言”
- list_question_predictionson 1 other server
“列出用户的押题(题库定制)记录:记录 ID、岗位、公司、生成时间、状态(generating 生成中 / done 完成 / failed 失败)与题数。(需要用户授权,范围 interviews:read)”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
- get_question_predictionon 1 other server
“查看一次押题(题库定制)的状态与结果。记录 ID 取自 list_question_predictions 或 start_question_prediction。默认返回状态、总述与题目概览(每行一题);传 indexes 返回指定题目的考察点、作答思路与可用素材。状态为 generating 时返回当前进度,failed 时返回失败原因。(需要用户授权,范围 interviews:read)”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs, 1 required
idstringrequired“押题记录 ID”indexesarray“要查看全文的题目序号(从 1 开始)”
- delete_question_predictionon 1 other server
“删除一条押题(题库定制)记录。记录 ID 取自 list_question_predictions。已扣的次数不退回。删除后不能恢复,执行前向用户说明要删除的内容并取得同意。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive yes · open-world no
1 input, 1 required
idstringrequired“押题记录 ID”
- save_question_prediction_to_knowledge_baseon 1 other server
“把一次押题的全部题目与作答思路新建为一份面试知识库,真实面试时面试助手可直接使用。记录 ID 取自 list_question_predictions,返回新知识库 ID。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
1 input, 1 required
idstringrequired“押题记录 ID”
- list_knowledge_baseson 2 other servers
“列出用户的面试知识库:ID、名称、来源(custom 手写 / file 文件 / ai 生成)、问答条数、正文字数。知识库在面试时挂载,让面试助手的回答贴合用户的个人背景。(需要用户授权,范围 interviews:read)”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
- get_knowledge_baseon 4 other servers
“查看一份面试知识库:名称、正文开头与总字数、问答条目概览(每行一条)。知识库 ID 取自 list_knowledge_bases。正文较长时传 contentOffset 分段读取(每段 4000 字);传 entryIds 返回这些条目的完整问答。(需要用户授权,范围 interviews:read)”
Publisher declares: read-only yes · destructive no · open-world no
3 inputs, 1 required
idstringrequired“知识库 ID”contentOffsetinteger“从正文第几个字开始读取”entryIdsarray“要查看完整问答的条目 ID”
- create_knowledge_baseon 1 other server
“新建一份面试知识库,可附带一段自由正文(项目介绍、个人经历等)。返回知识库 ID,之后可用 add_knowledge_base_entry、import_knowledge_base_entries 添加问答。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
2 inputs, 1 required
namestringrequiredcontentstring“自由正文”
- update_knowledge_baseon 2 other servers
“修改一份面试知识库的名称或正文;只传要改的字段,未传的保持原样。传 content 会整段替换原正文。知识库 ID 取自 list_knowledge_bases。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
3 inputs, 1 required
idstringrequired“知识库 ID”namestringcontentstring
- add_knowledge_base_entryon 1 other server
“向一份面试知识库添加一条预设问答(问题 + 参考答案)。知识库 ID 取自 list_knowledge_bases;返回条目 ID。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
3 inputs, 3 required
materialIdstringrequired“知识库 ID”questionstringrequiredanswerstringrequired
- update_knowledge_base_entryon 1 other server
“修改知识库中的一条问答;只传要改的问题或答案,未传的保持原样。条目 ID 取自 get_knowledge_base。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
4 inputs, 2 required
materialIdstringrequired“知识库 ID”entryIdstringrequired“条目 ID”questionstringanswerstring
- import_knowledge_base_entrieson 1 other server
“向一份面试知识库批量导入问答(一次 1–200 条,追加在已有条目之后)。知识库 ID 取自 list_knowledge_bases;超出单库容量时整批拒绝。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
2 inputs, 2 required
materialIdstringrequiredentriesarrayrequired
- upload_knowledge_base_fileon 1 other server
“上传一个文件新建为面试知识库:抽取文件文字作为知识库正文,返回知识库 ID 与正文字数。文件内容以 base64 传入;支持 .pdf .doc .docx .txt .md .jpg .jpeg .png .webp,单个文件不超过 10MB。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
2 inputs, 2 required
fileNamestringrequired“文件名(含扩展名)”fileBase64stringrequired“文件内容的 base64”
- generate_knowledge_base_entrieson 1 other server
“按用户的简历和 / 或目标岗位,由 AI 预测面试问题并写好参考答案,直接追加到指定知识库(默认 8 条,最多 15 条)。知识库 ID 取自 list_knowledge_bases,简历 ID 取自 list_resumes;简历与岗位至少给一个。返回新增条数。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
5 inputs, 1 required
materialIdstringrequiredresumeIdstringgoalIdstringcountintegerlangstring
- delete_knowledge_baseon 1 other server
“删除一份面试知识库(含其中全部问答)。知识库 ID 取自 list_knowledge_bases。删除后不能恢复,执行前向用户说明要删除的内容并取得同意。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive yes · open-world no
1 input, 1 required
idstringrequired“知识库 ID”
- delete_knowledge_base_entryon 1 other server
“删除知识库中的一条问答。条目 ID 取自 get_knowledge_base。删除后不能恢复,执行前向用户说明要删除的内容并取得同意。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive yes · open-world no
1 input, 1 required
idstringrequired“条目 ID”
- list_official_knowledge_baseson 1 other server
“列出官方资料库:补充模型训练数据中缺失的近一年行业知识,持续更新,开始面试时可与用户自己的知识库一起直接挂载,无需导入。(需要用户授权,范围 interviews:read)”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
- get_official_knowledge_baseon 1 other server
“查看一个官方资料库的说明与条目概览(每行一条);传 indexes 返回指定条目的完整内容与出处。资料库 ID 取自 list_official_knowledge_bases。(需要用户授权,范围 interviews:read)”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs, 1 required
idstringrequired“官方资料库 ID”indexesarray“要查看全文的条目序号(从 1 开始)”
- list_hot_word_librarieson 1 other server
“列出可绑定到目标岗位的热词库:官方词库与用户自建词库(isOwn=true)的 ID 和名称。热词让语音识别准确识别专有名词。(需要用户授权,范围 interviews:read)”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
- list_my_hot_wordson 1 other server
“列出用户自建的热词库及其中的全部热词。(需要用户授权,范围 interviews:read)”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
- create_hot_word_libraryon 1 other server
“新建一个自建热词库(名称 + 热词列表,单库最多 200 个词,每人最多 20 个库)。返回词库 ID,可用 update_goal_hot_words 绑定到目标岗位。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
2 inputs, 1 required
namestringrequiredwordsarray
- update_hot_word_libraryon 1 other server
“修改一个自建热词库:可改名称、整体替换词表(words),或增删个别词(addWords / removeWords);未传的保持原样。词库 ID 取自 list_my_hot_words。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive no · open-world no
5 inputs, 1 required
idstringrequired“词库 ID”namestringwordsarrayaddWordsarrayremoveWordsarray
- delete_hot_word_libraryon 1 other server
“删除一个自建热词库,已绑定它的岗位随之解除绑定。词库 ID 取自 list_my_hot_words。删除后不能恢复,执行前向用户说明要删除的内容并取得同意。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only no · destructive yes · open-world no
1 input, 1 required
idstringrequired
- suggest_hot_word_librarieson 1 other server
“按岗位名称与描述,由 AI 从官方词库中挑选 2–4 个最匹配的,返回词库 ID 与名称。结果不会自动保存,绑定到岗位用 update_goal_hot_words。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs, 1 required
jobNamestringrequired“岗位名称”jobDescriptionstring“岗位描述”
- generate_hot_wordson 1 other server
“按岗位名称、描述与可选的简历,由 AI 生成一批面试中会说到、语音识别容易认错的专有名词。结果不会自动保存:写入自建词库用 create_hot_word_library / update_hot_word_library,写入岗位自定义热词用 update_goal_hot_words。简历 ID 取自 list_resumes。(需要用户授权,范围 interviews:write)”
Publisher declares: read-only yes · destructive no · open-world no
3 inputs, 1 required
jobNamestringrequiredjobDescriptionstringresumeIdstring
- get_goal_hot_wordson 1 other server
“查看一个目标岗位当前生效的热词:绑定的热词库(ID、名称、是否自建)与自定义热词。(需要用户授权,范围 interviews:read)”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
goalIdstringrequired
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. The first 100 of 148 tools are listed. Read 2026-11-18.
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
- 66% of 295
- Tools with a description
- 100% of 148
- Typical description length
- 123 characters
The tool set
Counted from the listing
- Tools
- 148
- Size of the list
- about 20,477 tokens for an agent to load (characters ÷ 4)
- Naming
- 148 of 148 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 0 of 148 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, comparing tools within groups of 40. 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 2026-11-18 (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://api.mianlingai.com/agent/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"mianling": {
"url": "https://api.mianlingai.com/agent/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"mianling": {
"type": "http",
"url": "https://api.mianlingai.com/agent/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"mianling","type":"http","url":"https://api.mianlingai.com/agent/mcp"}'Claude Code
claude mcp add --transport http mianling https://api.mianlingai.com/agent/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
"mcpServers": {
"mianling": {
"type": "streamableHttp",
"url": "https://api.mianlingai.com/agent/mcp",
"disabled": false,
"autoApprove": []
}
}
}Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
"mcpServers": {
"mianling": {
"httpUrl": "https://api.mianlingai.com/agent/mcp"
}
}
}OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.mianling] url = "https://api.mianlingai.com/agent/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
"context_servers": {
"mianling": {
"url": "https://api.mianlingai.com/agent/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://api.mianlingai.com/agent/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 2026-11-18. 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 2026-11-18. GitHub Advisory Database, CC BY 4.0
- Docker MCP catalogue. Not in the Docker MCP catalogue on 2026-11-18. Source: read 2026-11-18.
- Cline marketplace. Not in the Cline marketplace on 2026-11-18. Source: read 2026-11-18.
Own host
- security.txt. No security.txt at https://api.mianlingai.com/.well-known/ (HTTP 404, 2026-11-18). No security.txt at https://www.mianlingai.com/.well-known/ (HTTP 404, 2026-11-18). Source: api.mianlingai.com/.well-known/security.txt · read 2026-11-18.
- A2A agent card. No A2A agent card at https://api.mianlingai.com/.well-known/ (HTTP 404, 2026-11-18). No A2A agent card at https://www.mianlingai.com/.well-known/ (HTTP 404, 2026-11-18). Source: api.mianlingai.com/.well-known/agent-card.json · read 2026-11-18.
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 #6The 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 says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint api.mianlingai.com/agent/mcp | Session opened | matches | our test · 2026-11-18 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-11-18 |
Choosing
Record checks
Public records · not a safety rating1 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 2026-11-18. 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 com.mianlingai/mianling
Answered from the data aboveWho publishes com.mianlingai/mianling?
The registry ties the namespace com.mianlingai to the domain mianlingai.com; only its owner can publish under it. These are facts from the registry and GitHub, not a rating.
Does com.mianlingai/mianling need an API key or sign-in?
It opened a session without any credential on 2026-11-18. The registry entry declares no required credential; no declaration is not a guarantee.
Has com.mianlingai/mianling been security tested?
Partly. 3 of the 15 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. ProtocolProbe publishes no security verdict for a named server.
Found this page useful?
Anonymous · no sign-inA 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
Open without sign-in
It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.
- Inventory: exercised
- Hidden instructions: exercised
- Real execution: not run · our policy
- Secret leak: not run · nothing to check it against
- Internal addresses: not run · our policy
- Unconfirmed changes: not run · our policy
- Bad input: not run · our policy
- Model requests: not run · nothing to check it against
- Sensitive questions: not run · nothing to check it against
- Folder boundary: not run · our policy
- Log leaks: not run · nothing to check it against
- Hidden content: not run · nothing to check it against
- Fake assistant turns: not applicable
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not run · our policy
- Consent handling: not testable from outside
- Sign-in metadata: exercised
3 exercised12 not run (reason given)3 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 3 of the 15 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.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.exercised
- 3Real execution
real-executionCalls 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-leakPlants 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
ssrfChecks 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-confirmationChecks 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-handlingSends 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
samplingChecks 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-dataChecks 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-boundaryChecks 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-channelChecks 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-hidingChecks 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-redirectChecks 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-deputyChecks 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
- 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable - 14Token passthrough
token-passthroughChecks 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-validationChecks 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
Source: our own test, 2026-11-18, 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.
- 0 msStarted a read-only session with the server's remote endpoint
- 8,694 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 148 tools, 0 resources, 0 prompts.
- 23,215 msFinished: 3 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.
“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. “com.mianlingai/mianling: MCP server record.” Data checked 2026-11-18. https://protocolprobe.com/mcp/servers/com.mianlingai/mianling
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
[](https://protocolprobe.com/mcp/servers/com.mianlingai/mianling)
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