Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

知你AI助手|多平台客户与客服数据 MCP

REMOTE · MCP.H5BQB.TOP · SCANNED SEP 14

连接个微、企微、视频号、微信小程序、公众号、服务号、微信客服、微信小店、抖音号、小红书、微博、网站及H5客服的客户资料、会话与聊天记录,供AI查询分析。

Available components

74 Trust /100
Trust breakdown (7 categories)

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 Security74
Transport & Reachability100
Schema Quality & AI Usability77
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 3602 tokens (~277/item across 13 items; 12 tools + 1 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 Management20
  • Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 14 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
Install

How do I install the 知你AI助手|多平台客户与客服数据 MCP server?

知你AI助手|多平台客户与客服数据 MCP is a hosted endpoint at https://mcp.h5bqb.top/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 · mcp.h5bqb.top

# add to Claude Code
claude mcp add --transport http zhinikefu-zhini-ai-assistant 'https://mcp.h5bqb.top/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "zhinikefu-zhini-ai-assistant": {
      "url": "https://mcp.h5bqb.top/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "zhinikefu-zhini-ai-assistant": {
      "type": "http",
      "url": "https://mcp.h5bqb.top/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.zhinikefu-zhini-ai-assistant]
url = "https://mcp.h5bqb.top/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "zhinikefu-zhini-ai-assistant": {
      "type": "remote",
      "url": "https://mcp.h5bqb.top/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add zhinikefu-zhini-ai-assistant --url 'https://mcp.h5bqb.top/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  zhinikefu-zhini-ai-assistant:
    url: "https://mcp.h5bqb.top/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "zhinikefu-zhini-ai-assistant": {
      "Transport": "http",
      "Url": "https://mcp.h5bqb.top/mcp"
    }
  }
}
# add to Vellum
assistant mcp add zhinikefu-zhini-ai-assistant -t streamable-http -u 'https://mcp.h5bqb.top/mcp'
// mcp.json
{
  "mcpServers": {
    "zhinikefu-zhini-ai-assistant": {
      "type": "http",
      "url": "https://mcp.h5bqb.top/mcp"
    }
  }
}

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

Changelog

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.

  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 0
    • Tool “zhini_get_apikey_usage” rewrote its description, which is the text the model reads security
  • 11 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Sept 26 +1
    • Stability: unverified → 0.03 functional
  • 8 Sept 26 71

    First indexed and scored.

Diagnostics

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 14 Sept 2026 · Probed https://mcp.h5bqb.top/mcp

TLS valid

Negotiated TLS 1.2 with TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=mcp.h5bqb.top CN=TrustAsia DV TLS RSA CA 2024,O=TrustAsia Technologies\, Inc.,C=CN 14 Jul 2026 12 Oct 2026 RSA 2048 SHA256-RSA 10483f9230441251a8f199762dc954ca621ff58f
SANs: mcp.h5bqb.top
CN=TrustAsia DV TLS RSA CA 2024,O=TrustAsia Technologies\, Inc.,C=CN (CA) CN=TrustAsia TLS RSA Root CA,O=TrustAsia Technologies\, Inc.,C=CN 15 May 2024 15 May 2034 RSA 4096 SHA384-RSA 1c9e6b412deb0a85461de03dbe30984d0573888b
CN=TrustAsia TLS RSA Root CA,O=TrustAsia Technologies\, Inc.,C=CN (CA) CN=Certum Trusted Network CA,OU=Certum Certification Authority,O=Unizeto Technologies S.A.,C=PL 7 Oct 2025 14 Jan 2029 RSA 4096 SHA384-RSA b2dc4c34932d709cd4bf0b099401695c

Background: What to check on a remote MCP endpoint →

DNSSEC secure

Validation of mcp.h5bqb.top. Secure

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
top. present 26780 8 Verified
h5bqb.top. present 58879 13 Verified
mcp.h5bqb.top. Verified address RRset verified with the apex keys
Authentication Challenged, unverified

The endpoint asked for a token, but we could not retrieve and validate the RFC 9728 metadata that tells a client how to obtain one.

Result Challenged, unverified
Enforced On tool calls
HTTP status 200

WWW-Authenticate challenge Bearer realm="zhini-mcp-service"

Bearer realm="zhini-mcp-service"

Protected resource metadata

Retrieved No
Problem no_resource_metadata

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.h5bqb.top/mcp Verified 200
http (plaintext) http://mcp.h5bqb.top/mcp Inconclusive 405
MCP tools · 12 exposed · ~3,470 tokens

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 →

Tool Tokens
zhini_fetch_messages ~362

读取聊天消息。支持按 sid 首次加载会话消息、按 mid 游标翻页、按 uid 查询某客户消息。适用于查看当前会话上下文、查看历史会话命中词前后文、按 UID 拉取某段时间内消息并总结诉求/投诉/售后问题。已知 uid/sid/mid 时直接调用本工具,不要先搜索。约束:sid、mid、uid 至少传一个;传 mid 时建议同时传 direction;按 uid 查询时 start_time/end_time 可选;size 最大 20。时间语义:start_time/end_time 是消息发生时间过滤,不是会话开启时间。

NameTypeReqDescription
directionstring翻页方向。backward 表示更早消息,forward 表示更新消息。
end_timenumber查询消息结束时间,秒级 Unix 时间戳。按 uid 查询时可选,表示消息发生时间。
include_midnumber为 1 时包含指定 mid;翻页查看某条消息前后文时使用。
midstring消息 ID。按游标翻页时传;传 mid 时建议同时传 direction。
sidstring会话 ID。首次按会话加载消息时传。
sizeinteger返回消息数量,默认 20,最大 20。
start_timenumber查询消息开始时间,秒级 Unix 时间戳。按 uid 查询时可选,表示消息发生时间。
uidstring知你侧客户 UID。按客户查询消息时传,可结合 start_time/end_time 限定消息发生时间。

No output schema declared.

No examples provided.

zhini_get_apikey_usage ~121

查询当前请求 API Key 所属账号的总配额、账号已使用量、账号剩余量,以及当前请求 API Key 的实时已使用量。工具无业务入参;服务端使用当前请求提供的 API Key 调用配额接口,并标准化返回 total、remaining、used、current_api_key_used,其中前三项是账号整体数据,最后一项是当前请求 API Key 数据。安全边界:不允许模型传入 apikey 或内部 api_key 查询参数,也不返回完整 API Key。

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

zhini_get_current_kefu ~164

获取当前调用者的客服 ID,即 kfid。用于在调用 zhini_list_active_sessions 前识别当前会话列表中哪些是自己正在接待的会话,或在用户明确说“我处理过、我接待过、我回复过、归属于我”等第一人称归属条件时构造 kfid 筛选。重要边界:用户只要求查询当天或某个时间范围内的对话、咨询过的客户时,默认范围是当前授权账号关联的所有渠道,不表示当前调用客服本人处理过,不应调用本工具或自动附加当前 kfid。本工具只输出 kfid,不输出手机号、姓名、团队、企业或负责渠道等身份信息。

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

zhini_get_customer_profile ~151

按客户 UID 获取客户资料和标签,用于确认客户身份、来源、负责人、联系方式、备注和标签。适用于客服回复前、销售跟进前、复盘客户历史前。边界:只读查询,不修改客户资料、备注、负责人或标签。前置:如果用户只给姓名/手机号/微信号,先用 zhini_search_customers 找 uid;如果已经有 uid,直接调用本工具。后续:需要聊天上下文时调用 zhini_fetch_messages。

NameTypeReqDescription
uidstringyes知你侧客户 UID。通常由 zhini_search_customers 返回,也可由会话数据中的 uid 字段提供。

No output schema declared.

No examples provided.

zhini_list_active_sessions ~334

获取当前授权客服账号所负责渠道下尚未关闭、尚未结束的当前会话队列。用于查看此刻的待接待、我的会话、同事会话、AI 会话状态,或从当前队列选定会话后读取消息/客户资料。重要边界:这是当前队列快照,不是历史查询;当天或更早已经由当前授权账号、其他客服结束/关闭的会话不会返回,不能用本工具汇总某天或某段时间内的全部用户、全部接待或完整会话。需要完整用户范围时调用 zhini_search_customers;需要已结束、已关闭或历史会话时调用 zhini_search_sessions,必要时再用 zhini_fetch_messages 按消息时间验证。范围:只返回当前授权账号负责渠道下的会话,不是全企业所有会话;我的会话全部返回,同事会话最多显示 250 个,排队中/等待接待会话最多显示 100 个,达到上限时摘要应提示可能被截断。前置:需要区分“我的会话/同事会话”时,先调用 zhini_get_current_kefu 获取当前 kfid。

NameTypeReqDescription
kfidstring当前调用者客服 ID。可由 zhini_get_current_kefu 获取;传入后可标记 queue_type:mine、colleague、waiting、ai。未传 kfid 时不能判断 mine/colleague,只能识别 waiting、ai、assigned_unknown。

No output schema declared.

No examples provided.

zhini_list_channels ~205

获取渠道列表,用于把渠道名解析成 channel_id,并解释渠道类型。适用于用户说“查公众号A的客户”“查小红书渠道的历史会话”“按渠道分析咨询来源”时,先解析渠道 ID。支持 all、miniapp、pubapp、wxbot、webplugin、h5plugin、wework_kf、douyin、douyin_private、weibo、wework_bot、wxbot_channel、xiaohongshu、minigame、wxstore;不暴露已废弃渠道。前置:无。后续:拿到 channel_id 后可调用 zhini_search_customers 或 zhini_search_sessions。

NameTypeReqDescription
group_by_typeboolean是否按渠道类型聚合返回 groups,默认 true。
typestring渠道类型。all 表示全部;也可指定 miniapp、pubapp、wxbot、xiaohongshu 等具体类型。

No output schema declared.

No examples provided.

zhini_list_kefu ~162

获取当前授权范围内的客服列表,用于把客服姓名解析成 kfid。适用于“客服A负责哪些客户”“抽查某客服历史接待”“队列统计时把 kfid 转成人名”等场景。only_active=true 时只返回可用客服;name 为空时可标准化为未命名。前置:无。后续:拿到 kfid 后可调用 zhini_search_customers、zhini_search_sessions,或在 zhini_list_active_sessions 中辅助标记 mine/colleague。

NameTypeReqDescription
only_activeboolean是否过滤 status=0 的客服。
scenestring|number业务场景;客户/历史筛选通常传 1。

No output schema declared.

No examples provided.

zhini_list_tag_groups ~93

获取标签分组,用于了解标签体系、解释标签归属,或在列出某分组标签前获取 tag_group_id。边界:只读字典工具,不新增、修改或删除标签分组。前置:无。后续:已知分组后可调用 zhini_list_tags;用户直接给标签名时通常优先调用 zhini_search_tags。

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

zhini_list_tags ~180

分页获取标签列表,用于在已知标签分组 ID 时列出该分组下的标签,并为客户搜索或历史会话搜索提供 tag_id。page 从 1 开始;page_size 最大 20。前置:可先调用 zhini_list_tag_groups 获取分组;如果用户只提供标签中文名,优先调用 zhini_search_tags 解析 tag_id。后续:拿到 tag_id 后可调用 zhini_search_customers 或 zhini_search_sessions。

NameTypeReqDescription
pageinteger页码,从 1 开始,默认 1。
page_sizeinteger每页返回标签数量,最大 20。
tag_group_idstring标签分组 ID。可由 zhini_list_tag_groups 返回;不传时查询默认标签范围。

No output schema declared.

No examples provided.

zhini_search_customers ~704

搜索客户通讯录,用于根据客户名、手机号、微信号、客服、负责人、明确标签、渠道、性别、联系人类型或时间范围完整召回符合条件的客户 UID。用户只要求查询当天或某个时间范围内咨询过的客户时,默认查询当前授权账号关联的所有渠道范围,不代表当前调用客服本人接待或回复过;除非用户明确说“我处理过、我接待过、我回复过、归属于我”或指定某客服/渠道,否则不要自动传 kfid、pic_kfids 或 channel_id。用户要求查询某天或某段时间内的全部用户、包括会话已经结束/关闭的用户时,应使用本工具分页查询,不能用 zhini_list_active_sessions 代替。重要边界:自然语言中的“XXX 用户/客户”默认是业务语义或筛选条件,不应自动转换为 tag_id。可由名称、时间、渠道、客服等结构化字段表达的条件直接使用本工具;必须根据聊天内容判断的条件,应结合 zhini_search_sessions 和 zhini_fetch_messages 识别。只有用户明确要求某标签或上下文已有 tag_id 时才按标签筛选,且 tag_id 只覆盖已标注客户。用户给客户姓名/手机号/微信号时先用本工具召回候选客户;如果匹配多个客户,应让用户确认。用户明确给出标签名、渠道名、客服名时,应先分别调用 zhini_search_tags、zhini_list_channels、zhini_list_kefu 解析 ID。禁止空条件拉全量;page 从 0 开始;page_size 最大 20。后续:拿到 uid 后通常调用 zhini_get_customer_profile 或 zhini_fetch_messages。

NameTypeReqDescription
add_friend_timearray添加好友时间范围,秒级 Unix 时间戳二元组;[0,0] 表示无添加时间。
channel_idarray渠道 ID 列表。用户给渠道名时应先调用 zhini_list_channels 解析 channel_id。
kfidarray归属员工/客服 ID 列表。用户给客服名时应先调用 zhini_list_kefu 解析 kfid。
last_contact_timearray最后联系时间范围,秒级 Unix 时间戳二元组;[0,0] 表示无最后联系时间。
namestring客户昵称或名称关键词。
pageinteger页码,从 0 开始。
page_sizeinteger每页返回客户数量,默认 20,最大 20。
phonestring手机号关键词。
pic_kfidsarray负责人 ID 列表。用户给负责人姓名时应先调用 zhini_list_kefu 解析 kfid。
sexarray性别枚举数组:0 未知,1 男,2 女。
tag_idarray标签 ID 列表。用户给标签名时应先调用 zhini_search_tags 解析 tag_id。
user_wechat_idstring微信号关键词。
wx_contact_typearray联系人类型数组:0 联系人,1 群组。

No output schema declared.

No examples provided.

zhini_search_sessions ~747

搜索历史会话,用于按客户名、消息关键词、消息发送时间范围、客服、渠道、明确标签、联系人类型召回包括已结束、已关闭会话在内的历史会话候选。用户只要求查询当天或某个时间范围内的对话、咨询记录时,默认查询当前授权账号关联的所有渠道范围,不代表当前调用客服本人接待或回复过;除非用户明确说“我处理过、我接待过、我回复过、归属于我”或指定某客服/渠道,否则不要自动传 kfid 或 channel_id。用户要求查询某天或某段时间内的全部接待、完整会话或已结束会话时,应使用本工具分页查询,不能只调用 zhini_list_active_sessions。自然语言中的“XXX 用户/客户”默认是业务语义;当 XXX 必须根据聊天判断时,使用 msg 按相关表达召回候选,再用 msg_stime 限定消息发送时间范围,最后用 zhini_fetch_messages 读取完整上下文并由模型分类,不要先把 XXX 当成标签名。只有用户明确提到标签或已有 tag_id 时,标签才作为筛选条件或补充信号。关键词命中只是召回信号,不等于最终分类。条件性限制:仅当 msg 非空时,关键词历史检索只支持最近半年内的记录;msg 未传或为空、仅使用其他筛选条件(包括 msg_stime)时不受这条关键词专属限制。重要时间语义:msg_stime 表示消息发送时间范围,用于筛选时间段内包含消息的会话,不表示对话开启时间;旧字段 stime 已移除,不要传入。禁止空条件拉全量;page 从 0 开始;本工具不接收数量参数,底层查询默认每次返回 30 条,MCP 可全部展示给模型。

NameTypeReqDescription
channel_idarray渠道 ID 列表。仅在用户明确指定渠道时传;用户未指定渠道时默认覆盖当前授权账号关联的所有渠道。用户给渠道名时应先调用 zhini_list_channels 解析 channel_id。
kfidarray客服 ID 列表。仅在用户明确指定某客服,或明确说查询当前调用者本人处理过/接待过/回复过/归属于本人的会话时传;第一人称场景可先用 zhini_get_current_kefu 获取 kfid。通用时间范围查询不要自动传当前 kfid。
msgstring消息内容关键词。适合搜索订单号、手机号片段、产品名、错误提示、投诉词、活动词等。仅当本字段非空时触发关键词历史检索限制:只支持最近半年内的记录。
msg_stimearray消息发送时间范围,秒级时间戳;按该范围内包含消息的会话筛选,不表示对话开启时间。与非空 msg 组合时,关键词检索只支持最近半年。
namestring客户名称关键词。
pageinteger页码,从 0 开始。
tag_idarray标签 ID 列表。用户给标签名时应先调用 zhini_search_tags 解析 tag_id。
wx_contact_typearray联系人类型数组:0 联系人,1 群组。

No output schema declared.

No examples provided.

zhini_search_tags ~247

按关键词搜索标签,用于把用户明确提出的标签名解析成稳定 tag_id。典型场景:用户说“查带高意向标签的客户”“按高意向标签筛选”,先调用本工具搜索“高意向”,再用 tag_id 调用 zhini_search_customers 或 zhini_search_sessions。重要边界:自然语言中的“XXX 用户/客户”默认表示业务语义或筛选条件,不表示名为 XXX 的标签;只有用户明确提到“标签、带标签、按标签筛选”,或上下文已给出 tag_id 时才调用本工具。标签只代表已经被人工或系统标注的客户,不等于业务语义上的完整人群。空关键词应返回参数错误。include_grouped=true 时按 tag_group_id 聚合,便于用户确认同名或相似标签。

NameTypeReqDescription
include_groupedboolean是否按 tag_group_id 聚合返回,便于模型和用户确认同名或相似标签。
search_keywordstringyes标签搜索关键词。不能为空,例如 高意向、售后、VIP。

No output schema declared.

No examples provided.

Common questions

What is the 知你AI助手|多平台客户与客服数据 MCP server?

知你AI助手|多平台客户与客服数据 MCP is listed in the public MCP registry as io.github.zhinikefu/zhini-ai-assistant. 连接个微、企微、视频号、微信小程序、公众号、服务号、微信客服、微信小店、抖音号、小红书、微博、网站及H5客服的客户资料、会话与聊天记录,供AI查询分析。 This page covers its hosted endpoint (https://mcp.h5bqb.top/mcp).

Is the 知你AI助手|多平台客户与客服数据 MCP server safe to use?

知你AI助手|多平台客户与客服数据 MCP scores 74 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 知你AI助手|多平台客户与客服数据 MCP server expose?

知你AI助手|多平台客户与客服数据 MCP exposes 12 tools: zhini_get_current_kefu, zhini_list_active_sessions, zhini_get_customer_profile, zhini_list_tag_groups, zhini_list_tags, and 7 more. Their descriptions and schemas cost roughly 3,470 tokens of context every time the server is loaded.

Does the 知你AI助手|多平台客户与客服数据 MCP server require authentication?

Yes. 知你AI助手|多平台客户与客服数据 MCP asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the 知你AI助手|多平台客户与客服数据 MCP server still maintained?

知你AI助手|多平台客户与客服数据 MCP is still listed as active in the MCP registry. We last reached this channel on 14 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.