Neo Reader
Convert any webpage to clean, LLM-ready markdown in under 2 seconds. No credits, no multipliers, no surprises. Production-ready API with 99.9% uptime. Start free.
https://neoreader.devOpens ChatGPT on the web or desktop and asks it to use the WebMCP tools available here.
Connect straight to this server’s public endpoint.
https://mcp.neoreader.dev/We add this server to your workspace, then open Studio — saved access, one connection to many servers, with a history of what ran.
Last probed Sep 14, 2026 · mcp.neoreader.dev
26tools discovered
Showing 25 of 26 from the live probe.
Register User
Register a new user account. Creates a new user and returns JWT tokens for authentication. Store the tokens securely for subsequent requests.
Login User
Login with email and password. Authenticates user and returns JWT tokens. Automatically updates the MCP server's authentication configuration.
Refresh Token
Refresh access token using refresh token. When your access token expires (default: 15 minutes), use this to get a new one. The old refresh token is automatically revoked (token rotation).
Logout User
Logout user by revoking refresh token.
Change Password
Change user password. All refresh tokens are revoked after password change. You must login again.
Convert URL to Markdown
Convert URL to clean, LLM-friendly markdown. This is the primary tool for converting webpages to markdown. Uses browser automation (Playwright) for JavaScript-rendered content and fast HTTP fetching for static pages.
Convert URL to HTML
Extract raw HTML from URL. Returns the HTML content after JavaScript execution and content extraction. Useful for custom processing or when you need the exact HTML structure.
Convert URL to Text
Extract plain text from URL. Returns text content via document.body.innerText. No formatting, just pure text.
Capture Screenshot
Capture viewport screenshot (1024x1024) of URL. Returns a redirect URL to the PNG screenshot. The screenshot shows the viewport (visible area) at 1024x1024 resolution.
Capture Full Page Screenshot
Capture full-page screenshot of URL. Returns a redirect URL to the PNG screenshot. Captures the entire page height (1024px wide, variable height).
Convert URL with Proxy
Convert URL to markdown using a proxy server. Useful for geo-restricted content or routing through corporate proxies. Supports HTTP, HTTPS, SOCKS4, and SOCKS5 proxies.
Convert Authenticated URL
Convert URL to markdown with cookie authentication. Useful for accessing content behind authentication walls, paywalls, or user-specific content.
Convert URL with Custom User Agent
Convert URL to markdown with custom User-Agent. Useful for mobile vs desktop rendering, bot identification, or bypassing user-agent restrictions.
Get User Profile
Get current user profile. Returns user information including email, full name, role, and account status. Requires authentication (X-API-Key header, Authorization: Bearer token, or login). Returns: User profile with id, email, full_name, is_active, is_verified, role, timestamps Raises: NotAuthenticatedError: If no credentials are available. APIError: If the Neo Reader API rejects the request or is unreachable.
Update User Profile
Update current user profile. Update user's full name or email address. At least one field must be provided. Changing email resets email verification status. Requires authentication (X-API-Key header, Authorization: Bearer token, or login).
Create API Key
Create a new API key for programmatic access. API keys are long-lived authentication credentials for server-to-server integrations. The raw key is only shown once - save it securely immediately. Requires authentication (X-API-Key header, Authorization: Bearer token, or login).
List API Keys
List all API keys for authenticated user. Returns metadata for all API keys including name, prefix, status, and usage. Raw keys are never returned after creation. Requires authentication (X-API-Key header, Authorization: Bearer token, or login).
Revoke API Key
Revoke an API key. Permanently revokes an API key. The key will immediately stop working. This action cannot be undone. Requires authentication (X-API-Key header, Authorization: Bearer token, or login).
NeoReader Health Check
Check Neo Reader API health status. Simple health check endpoint to verify the API is running and accessible. No authentication required. Returns: Health status ("healthy" if API is operational) Raises: APIError: If the API is unreachable or reports an error status.
Get API Stats
Get Neo Reader API statistics. Returns abuse-detection statistics: checks performed, clients blocked, checks that failed open, and the configured detection window. Returns: API statistics (abuse_checks_total, abuse_blocks_total, abuse_checks_degraded_total, window_seconds, max_domains_per_window) Raises: APIError: If the Neo Reader API rejects the request or is unreachable.
Discover Website
Start a website discovery job to find all URLs on a website. This tool crawls a website and discovers all accessible URLs. The job runs asynchronously - use get_discovery_job_status to check progress and get results. WORKFLOW: 1. Call discover_website with start URL and options 2. Get job_id from response 3. Poll get_discovery_job_status with job_id until status is "completed" 4. Process the discovered URLs
Get Discovery Job Status
Get the status and results of a discovery job. Poll this endpoint after starting a discovery job with discover_website. Continue polling until status is "completed", "failed", or "cancelled". STATUS VALUES: - pending: Job created, waiting for worker - queued: Job assigned to worker - running: Actively crawling (progress info available) - completed: Success! URLs available in response - failed: Error occurred (partial results may be available) - cancelled: User cancelled (partial results availa
Cancel Discovery Job
Cancel a running discovery job. Use this to stop a crawl that's taking too long or no longer needed. Partial results will be returned.
List Discovery Jobs
List all discovery jobs for your client. Returns a list of all discovery jobs with their current status. Useful for tracking multiple jobs or finding job IDs.
Wait for Discovery Completion
Wait for a discovery job to complete and return the final results. This is a CONVENIENCE TOOL that polls get_discovery_job_status automatically until the job completes, fails, or times out. Use this instead of manual polling. IMPORTANT: This tool blocks until completion. For long-running jobs, consider using discover_website + get_discovery_job_status manually to show progress updates to users.
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
Directory coverage for brandsConvert any webpage to clean, LLM-ready markdown in under 2 seconds. No credits, no multipliers, no surprises. Production-ready API with 99.9% uptime. Start free.
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
Operate Neo Reader? Verify ownership to take over this directory entry.
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles probed 26 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
No provider sign-in was required during MCPBundles' probe. Your client may still need MCPBundles credentials depending on how you connect.
MCPBundles is an independent platform built on the open Model Context Protocol standard. Not affiliated with Anthropic PBC or Claude.