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Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.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 technical documentation and read web pages as markdown.
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 …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"refdocs": {
"command": "npx",
"args": [
"-y",
"@reneturcios/refdocs",
"mcp"
]
}
}
}Run this in your terminal
claude mcp add refdocs -- npx -y @reneturcios/refdocs mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"refdocs": {
"command": "npx",
"args": [
"-y",
"@reneturcios/refdocs",
"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": {
"refdocs": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/refdocs",
"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.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
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.
Runs on your computer; the tool list appears in your AI app after you install it.
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 CloudCorpRecords, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
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 on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.1.0) reached the registry 5 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js, Docker on your computer.
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.
refdocs answers documentation questions and turns web pages into something an agent can actually read. Search runs across public technical documentation and GitHub for the facts or code snippet behind a question, and any URL can be fetched and handed back as clean markdown instead of raw HTML.
It is one small program with two faces: a command-line tool for quick lookups, and a stdio MCP server that gives agents the same two operations as tools.
Both operations require a Ref API key:
export REF_API_KEY="your-key-here"
The search endpoint defaults to https://api.ref.tools. Override it with REF_API_BASE_URL when you are pointing at another deployment. The key is checked before any request is made; when it is missing the tool fails with an error that names REF_API_KEY.
npx @reneturcios/refdocs search "How do I stream a response with fetch?"
Or run the container image:
docker run -i -e REF_API_KEY ghcr.io/cloudcorprecords/refdocs
The container defaults to the MCP server (see below). Pass CLI arguments to use it as a CLI instead.
# Search the documentation
refdocs search "How do I use the cache API in Next.js?" refdocs search "What does this error mean?" --json
refdocs read https://example.test/some/guide refdocs read https://example.test/some/guide --json
refdocs check
refdocs --version
Exit codes: 0 on success, 1 when a lookup fails or the configuration is not ready (the error names the problem), 2 for usage errors.
One bin serves both faces. The mcp subcommand starts a stdio MCP server:
npx -y @reneturcios/refdocs mcp
MCP client configuration:
{
"mcpServers": { "refdocs": { "command": "npx", "args": ["-y", "@reneturcios/refdocs", "mcp"], "env": { "REF_API_KEY": "your-key-here" } } } }
| Tool | Input | What it returns |
|---|---|---|
ref_search_documentation | query (string, required) — a full sentence or question to search for | Matching documentation results from public documentation and GitHub, each with its title, URL, and content or snippet when the upstream provides them. |
ref_read_url | url (string, required) — the URL of the webpage to read | The page content converted to markdown: headings, links, lists, emphasis, and code blocks are kept in markdown form, while scripts, styles, and other non-content markup are dropped. |
Search responses are parsed tolerantly: a bare array, a results list, and a documents list are all accepted. Reading plain-text URLs returns the text unchanged.
npm install
npm run build # tsc -> dist/ npm test # node test runner over test/*.test.ts, no network npm run dev # run the CLI from source via tsx
Tests run entirely against a fake fetch function; no live API calls are made.
MIT — see LICENSE.