MCP JinaAI Reader Server
The MCP JinaAI Reader Server converts web content into LLM-friendly text using Jina.ai's Reader API.
Extract web content: Efficiently retrieve and process web content with preserved structure and formatting.
Customize extraction: Use CSS selectors to target, exclude, or wait for specific elements.
Enhance output: Include summaries of links and images, generate alt text, and extract iframe content.
Control behavior: Set timeout limits, bypass caching for fresh results, and choose between JSON or streaming response formats.
Support various content types: Process different web content including documentation.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP JinaAI Reader Server read the React documentation at https://react.dev/learn"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-jinaai-reader
⚠️ Notice
This repository is no longer maintained.
The functionality of this tool is now available in mcp-omnisearch, which combines multiple MCP tools in one unified package.
Please use mcp-omnisearch instead.
A Model Context Protocol (MCP) server for integrating Jina.ai's Reader API with LLMs. This server provides efficient and comprehensive web content extraction capabilities, optimized for documentation and web content analysis.
Related MCP server: Jina AI Remote MCP Server
Features
📚 Advanced web content extraction through Jina.ai Reader API
🚀 Fast and efficient content retrieval
📄 Complete text extraction with preserved structure
🔄 Clean format optimized for LLMs
🌐 Support for various content types including documentation
🏗️ Built on the Model Context Protocol
Configuration
This server requires configuration through your MCP client. Here are examples for different environments:
Cline Configuration
Add this to your Cline MCP settings:
{
"mcpServers": {
"jinaai-reader": {
"command": "node",
"args": ["-y", "mcp-jinaai-reader"],
"env": {
"JINAAI_API_KEY": "your-jinaai-api-key"
}
}
}
}Claude Desktop with WSL Configuration
For WSL environments, add this to your Claude Desktop configuration:
{
"mcpServers": {
"jinaai-reader": {
"command": "wsl.exe",
"args": [
"bash",
"-c",
"JINAAI_API_KEY=your-jinaai-api-key npx mcp-jinaai-reader"
]
}
}
}Environment Variables
The server requires the following environment variable:
JINAAI_API_KEY: Your Jina.ai API key (required)
API
The server implements a single MCP tool with configurable parameters:
read_url
Convert any URL to LLM-friendly text using Jina.ai Reader.
Parameters:
url(string, required): URL to processno_cache(boolean, optional): Bypass cache for fresh results. Defaults to falseformat(string, optional): Response format ("json" or "stream"). Defaults to "json"timeout(number, optional): Maximum time in seconds to wait for webpage loadtarget_selector(string, optional): CSS selector to focus on specific elementswait_for_selector(string, optional): CSS selector to wait for specific elementsremove_selector(string, optional): CSS selector to exclude specific elementswith_links_summary(boolean, optional): Gather all links at the end of responsewith_images_summary(boolean, optional): Gather all images at the end of responsewith_generated_alt(boolean, optional): Add alt text to images lacking captionswith_iframe(boolean, optional): Include iframe content in response
Development
Setup
Clone the repository
Install dependencies:
npm installBuild the project:
npm run buildRun in development mode:
npm run devPublishing
Update version in package.json
Build the project:
npm run buildPublish to npm:
npm publishContributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
MIT License - see the LICENSE file for details.
Acknowledgments
Built on the Model Context Protocol
Powered by Jina.ai Reader API
Available Tools
1 toolread_urlB
Convert any URL to LLM-friendly text using Jina.ai Reader
Inputs: url (required), no_cache, format, timeout, +7 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool's purpose is clearly defined and distinct by default.
A single tool inherently has perfect naming consistency, as there are no other tools to compare against. The tool name 'read_url' follows a clear verb_noun pattern.
One tool is too few for a server with a purpose that could reasonably support more operations, such as handling different URL types or providing metadata extraction. This minimal set feels thin and under-scoped for the domain.
The server's domain appears to be URL content reading, but the single tool only covers basic text conversion. There are obvious gaps, such as no tools for handling errors, extracting structured data, or managing different content formats, which limits agent effectiveness.
Maintenance
Related MCP Connectors
Jina AI Reader/Search MCP — turn any URL into clean LLM-ready markdown, plus web search.
Clean Markdown and AI-readability scoring for any URL. Built for AI agents.
Read any public web page as clean Markdown for LLMs. Respects robots.txt. Free tier; x402 paid API.
Extract clean markdown, DESIGN.md specs, and link graphs from any URL for LLMs.
Related MCP Servers
- AlicenseAqualityFmaintenanceIntegrates Jina.ai's Grounding API with LLMs for real-time, fact-based web content grounding and analysis, enhancing LLM responses with precise, verified information.120 npm1MIT
- AlicenseNot gradedqualityNot gradedmaintenanceProvides access to Jina AI's web reading, search, embeddings, and reranking capabilities. Enables URL content extraction, web/arXiv/image search, document deduplication, and relevance ranking through natural language.Apache 2.0
- AlicenseNot gradedqualityNot gradedmaintenanceProvides web content extraction, search capabilities (web, arXiv, SSRN, images), semantic deduplication, and reranking through Jina AI's Reader, Embeddings, and Reranker APIs.1Apache 2.0
- AlicenseNot gradedqualityDmaintenanceProvides tools for web content extraction, search, embeddings, reranking, and image processing via Jina AI APIs, enabling intelligent data retrieval and analysis.Apache 2.0