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Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.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)
Read-only search over chinaready.co — China market entry for Western software teams.
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://mcp.chinaready.co/mcpRun this in your terminal
claude mcp add --transport http search https://mcp.chinaready.co/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"search": {
"url": "https://mcp.chinaready.co/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": {
"search": {
"type": "http",
"url": "https://mcp.chinaready.co/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://mcp.chinaready.co/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.
We have not read this server’s tool list yet; we check endpoints in rotation.
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 8, 2026
The registry name was verified against the domain chinaready.co (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
Not checked yet; we read the tool list when we check the endpoint
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 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 (1.0.0) reached the registry 26 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.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Remote MCP server for [chinaready.co](https://chinaready.co) — the practical guide for Western SaaS, app, and game teams entering Mainland China. Ask about ICP filing and licensing, app-store and game publishing, China cloud regions (AWS China, Azure China, Alibaba Cloud), payments, and compliance; every answer cites its source page.
https://mcp.chinaready.co/mcp (Streamable HTTP, stateless)| Tool | What it does |
|---|---|
search | Hybrid semantic + keyword search over the corpus; returns ranked excerpts with absolute chinaready.co URLs |
list_topics | The topics the corpus covers, with example queries and hub pages |
get_article | Reads any chinaready.co page as clean Markdown |
All tools are read-only (readOnlyHint: true).
Claude — claude.ai → Settings → Connectors → Add custom connector → paste https://mcp.chinaready.co/mcp → choose *No sign in* → Add.
Claude Code
claude mcp add --transport http chinaready https://mcp.chinaready.co/mcp
Cursor — one click:
https://cursor.com/en/install-mcp?name=chinaready&config=eyJ1cmwiOiJodHRwczovL21jcC5jaGluYXJlYWR5LmNvL21jcCJ9
VS Code — one click (opens the redirect installer):
https://insiders.vscode.dev/redirect/mcp/install?name=chinaready&config=%7B%22url%22%3A%22https%3A%2F%2Fmcp.chinaready.co%2Fmcp%22%7D
or in .vscode/mcp.json:
{ "servers": { "chinaready": { "url": "https://mcp.chinaready.co/mcp" } } }
Any MCP client (Windsurf, Zed, LibreChat, …) — remote server, no command, no keys:
{ "mcpServers": { "chinaready": { "url": "https://mcp.chinaready.co/mcp" } } }
npm install
npm test # vitest unit tests (protocol + tools, upstream mocked) npm run deploy # wrangler deploy (needs your Cloudflare auth)
The server is a thin stateless proxy over Chinaready's public retrieval API (search.chinaready.co); it stores nothing and needs no environment variables. Outbound calls go only to search.chinaready.co (retrieval) and chinaready.co (article fetch) — no other network destinations. get_article only fetches chinaready.co pages it has validated as safe site paths.
Every RPC message writes one data point to the chinaready_mcp_usage Analytics Engine dataset (blobs: method, tool, outcome, truncated ua; retention ~90 days). Method and tool names only — arguments and query content are never logged.
CLOUDFLARE_API_TOKEN=… CLOUDFLARE_ACCOUNT_ID=… npm run usage # last 7 days
CLOUDFLARE_API_TOKEN=… CLOUDFLARE_ACCOUNT_ID=… npm run usage 30 # last 30 days
Prints the daily volume, the RPC funnel (initialize → tools/list → tools/call), tool-call breakdown with error outcomes, and a client split (sdk / probe-bot / browser) so real usage can be told apart from the MCP directory liveness bots. The token needs *Analytics Engine Read*.
Raw queries go through the Analytics Engine SQL API (POST /accounts/{account}/analytics_engine/sql):
SELECT blob2 AS tool, sum(_sample_interval) AS hits
FROM chinaready_mcp_usage WHERE timestamp > now() - INTERVAL '7' DAY AND blob1 = 'tools/call' GROUP BY tool ORDER BY hits DESC
MIT