Context7
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Description from the maker (original English)
Search and browse classical Chinese poetry on haitang.app. Read-only and public.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://haitang.app/mcpRun this in your terminal
claude mcp add --transport http haitang https://haitang.app/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"haitang": {
"url": "https://haitang.app/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"haitang": {
"type": "http",
"url": "https://haitang.app/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://haitang.app/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Tool names and descriptions exactly as the server reported them on Nov 7, 2026. The maker wrote them, not us; we show them as plain text.
search_poetrySearch public classical Chinese poetry by keyword across authors and works. Returns public URLs and short excerpts. Use get_work or get_author for details.
list_dynastiesList all public dynasties as name/slug pairs. Use the dynasty name as category when browsing works or authors. Optional browse filters also return live facets for collections, dynasties and types; the static list stays complete.
list_collectionsList all public collections as name/slug pairs. Use the collection slug as the collection ID string when browsing works. Optional browse filters also return live facets for collections, dynasties and types; the static list stays complete.
list_typesList all public work kinds as name/slug pairs. Use the kind slug as tag when browsing works. Optional browse filters also return live facets for collections, dynasties and types; the static list stays complete.
list_sortsList public work sort labels and slugs. A null slug means omit sort for the site default order.
list_themesList the public 主题 taxonomy group with its name, slug and categories.
list_festivalsList the public 节日 taxonomy group with its name, slug and categories.
list_solar_termsList the public 节气 taxonomy group with its name, slug and categories.
list_cipaiList the public 词牌 taxonomy group with its name, slug and categories.
list_seasonsList the public 时令 taxonomy group with its name, slug and categories.
list_geographyList the public 地理 taxonomy group with its name, slug and categories.
list_groupsList the remaining public taxonomy groups: 选集, 写景, 时间, 花卉, 课本, 城市, 名山, 用典 and 书籍, with their categories.
list_worksBrowse public works with optional collection ID, dynasty name (category), kind slug (tag), sort and page. Returns public work URLs and page metadata.
list_authorsBrowse public authors, optionally filtered by dynasty name (category). Returns public author URLs and page metadata.
get_workRead a public work by numeric ID, including poem text, introduction, annotations, translation, collections and quotes. A missing work returns work: null.
get_authorRead a public author by numeric ID and a page of their works. A missing author returns author: null.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account MkFastHQ, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 965 ms (HTTP 200)
No sign-in needed
Read 16 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.1.0) reached the registry 10 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Context7, Codebase Memory, Exa
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
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.
No README found in the repo