Context7
Up-to-date docs for AI agents
作者提供的说明(英文原文)
Liliphant turns every meeting into connected knowledge, decisions, and actionable insights.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
适用于网页版、桌面版和手机版 Claude:
https://mcp.liliphant.com/mcp在终端中运行这条命令
claude mcp add --transport http mcp https://mcp.liliphant.com/mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"mcp": {
"url": "https://mcp.liliphant.com/mcp"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"mcp": {
"type": "http",
"url": "https://mcp.liliphant.com/mcp"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
ChatGPT 只能连接互联网上的服务器:
https://mcp.liliphant.com/mcp菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
工具名称和描述与服务器在 2026年11月6日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。
search_liliphant_docsSearch the Liliphant API documentation with a natural-language question. Returns the most relevant passages with their page URLs.
get_liliphant_api_docsBrowse the Liliphant API API docs, one level at a time. Call it without arguments to get the top level: the modules and pages with a short description and the endpoints they hold. Call it with `path` set to a module's or page's link (or path) to get what is inside it; each listin
call_any_read_api_of_liliphantRead from any Liliphant API API endpoint with a GET request for the user and return its response. Use it once you know the exact endpoint: look it up with get_liliphant_api_docs first to get its URL, headers, query params and body, unless the skill or a dedicated tool on this ser
call_any_api_of_liliphantSend a POST, PUT, PATCH or DELETE request to any Liliphant API API endpoint for the user and return its response. Use it once you know the exact endpoint: look it up with get_liliphant_api_docs first to get its URL, headers, query params and body, unless the skill or a dedicated
get_meReturns who is signed in and every company they can open, with their role in each. This is the first call a client makes after sign-in: almost every other call needs a company id from companies[].id. Any signed-in person may call it. It also does housekeeping on the way: it makes
list_meetingsLists the analysed meetings the caller may see, as cards, newest first, with the filter choices the Meetings screen offers. Use it to show or search the meeting list, and to find a meetingId for Get Meeting, Get Meeting Transcript, Get Share Link or the notes routes (meetings[].i
ask_a_questionAnswers a plain-language question from the company's processed meetings, with a headline, a short answer, an optional chart and the quotes it is based on. Use it whenever someone asks what was said, decided or promised in their meetings. Leave out meetingId to search every meetin
quickstart-liliphantLiliphant API quickstart: read the user's meetings and ask questions answered from what people actually said. Load before any Liliphant task. Call this to load the full instructions for this skill before doing the task.
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过域名 mcp.liliphant.com 验证(注册中心会核实域名所有权)
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
在 5887 毫秒内响应(HTTP 200)
无需登录
已读取 8 个工具描述,未发现针对 AI 的隐藏指令
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于–,最新版本(1.0.0)于6天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Context7, Codebase Memory, Exa
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Liliphant joins your company's calls, transcribes them and pulls out decisions, promises, open questions and risks, each linked to the words someone said. This MCP server lets AI assistants read your meetings and answer questions from what people actually said.
It is a remote MCP server (Streamable HTTP) at https://mcp.liliphant.com/mcp. Nothing to install: your AI tool connects to it, and you sign in to Liliphant once in the browser.
| Tool | What it does |
|---|---|
get_me | Who is signed in and the companies they can open |
list_meetings | Your meetings, newest first; filter by text, type, person, tag or date |
ask_a_question | Answers from your meetings, with quotes |
search_liliphant_docs, get_liliphant_api_docs, quickstart-liliphant | Liliphant docs and API reference |
call_any_read_api_of_liliphant, call_any_api_of_liliphant | Any other Liliphant API endpoint (read, or create/change/delete) |
Install it from the Cline MCP Marketplace, or open MCP Servers → Configure MCP Servers and add this to cline_mcp_settings.json:
{
"mcpServers": { "liliphant": { "type": "streamableHttp", "url": "https://mcp.liliphant.com/mcp", "disabled": false, "autoApprove": [] } } }
Then use the sign-in button next to `liliphant` in the MCP Servers list and sign in to Liliphant in the browser. Agent-driven install steps are in [llms-install.md](llms-install.md).
claude mcp add --transport http liliphant https://mcp.liliphant.com/mcp
then run /mcp and sign in.
server.json is the listing for the official MCP Registry, as com.liliphant.mcp/mcp. The com.liliphant.mcp name is proven by owning the mcp.liliphant.com domain.
One-time setup: create a signing key and publish its public half on liliphant.com (Git Bash or any shell with OpenSSL):
openssl genpkey -algorithm Ed25519 -out mcp-registry-key.pem
echo "v=MCPv1; k=ed25519; p=$(openssl pkey -in mcp-registry-key.pem -pubout -outform DER | tail -c 32 | base64)"
Add the printed line as a TXT record on `liliphant.com`. Keep `mcp-registry-key.pem` private and out of this repo.
Publish (bump version first for any later change):
mcp-publisher login dns --domain mcp.liliphant.com --private-key "$(openssl pkey -in mcp-registry-key.pem -noout -text | grep -A3 'priv:' | tail -n +2 | tr -d ' :\n')"
mcp-publisher publish