Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"docusaurus-plugin-mcp-server": {
"args": [
"-y",
"docusaurus-mcp-verify"
],
"command": "npx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
A Docusaurus plugin that exposes an MCP (Model Context Protocol) server endpoint, allowing AI agents like Claude, Cursor, and other MCP-compatible tools to search and retrieve your documentation.
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
npx -y 'docusaurus-mcp-verify' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
Checked docusaurus-mcp-verify against OSV.dev.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in developer-tools / writing
A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.
XcodeBuildMCP provides tools for Xcode project management, simulator management, and app utilities.
Asynchronous coordination layer for AI coding agents: identities, inboxes, searchable threads, and advisory file leases over FastMCP + Git + SQLite
MCP server for accessing Figma plugin console logs and screenshots via Cloudflare Workers or local mode
MCP Security Weekly
Get CVE alerts and security updates for Docusaurus Plugin Mcp Server and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
A Docusaurus plugin that exposes an MCP (Model Context Protocol) server endpoint, allowing AI agents like Claude, Cursor, and other MCP-compatible tools to search and retrieve your documentation.
npm install docusaurus-plugin-mcp-server
// docusaurus.config.js
module.exports = {
plugins: [
[
'docusaurus-plugin-mcp-server',
{
server: {
name: 'my-docs',
version: '1.0.0',
},
},
],
],
};
Choose your deployment platform:
Create api/mcp.js:
import { createVercelHandler } from 'docusaurus-plugin-mcp-server/adapters';
import path from 'path';
import { fileURLToPath } from 'url';
const __dirname = path.dirname(fileURLToPath(import.meta.url));
export default createVercelHandler({
docsPath: path.join(__dirname, '../build/mcp/docs.json'),
indexPath: path.join(__dirname, '../build/mcp/search-index.json'),
name: 'my-docs',
baseUrl: 'https://docs.example.com',
});
Add to vercel.json:
{
"functions": {
"api/mcp.js": {
"includeFiles": "build/mcp/**"
}
},
"rewrites": [{ "source": "/mcp", "destination": "/api/mcp" }]
}
Create netlify/functions/mcp.js:
import { createNetlifyHandler } from 'docusaurus-plugin-mcp-server/adapters';
import path from 'path';
import { fileURLToPath } from 'url';
const __dirname = path.dirname(fileURLToPath(import.meta.url));
export const handler = createNetlifyHandler({
docsPath: path.join(__dirname, '../../build/mcp/docs.json'),
indexPath: path.join(__dirname, '../../build/mcp/search-index.json'),
name: 'my-docs',
baseUrl: 'https://docs.example.com',
});
Add to netlify.toml:
[build]
publish = "build"
[functions]
directory = "netlify/functions"
included_files = ["build/mcp/**"]
[[redirects]]
from = "/mcp"
to = "/.netlify/functions/mcp"
status = 200
Cloudflare Workers can't access the filesystem, so you need to import the data directly:
import { createCloudflareHandler } from 'docusaurus-plugin-mcp-server/adapters';
import docs from '../build/mcp/docs.json';
import searchIndex from '../build/mcp/search-index.json';
export default {
fetch: createCloudflareHandler({
docs,
searchIndexData: searchIndex,
name: 'my-docs',
baseUrl: 'https://docs.example.com',
}),
};
npm run build
# Deploy to your platform
Claude Code:
claude mcp add --transport http my-docs https://docs.example.com/mcp
Cursor / VS Code:
{
"mcpServers": {
"my-docs": {
"url": "https://docs.example.com/mcp"
}
}
}
Add a dropdown button to your docs site so users can easily install the MCP server in their AI tool:
import { McpInstallButton } from 'docusaurus-plugin-mcp-server/theme';
function NavbarItems() {
return <McpInstallButton serverUrl="https://docs.
... [View full README on GitHub](https://github.com/scalvert/docusaurus-plugin-mcp-server#readme)