This server provides access to Jina AI's web services through Claude, offering tools for web content extraction, search, and fact-checking:
read_webpage: Extract and format web page content for LLMs, with options for output formats, links, images, and alt text.search_web: Search the web with configurable results, image retention, and return formats, returning structured results.fact_check: Verify statements with factuality scores, supporting evidence, and optional deep-dive analysis.
Jina AI MCP Server
An MCP server that provides access to Jina AI's powerful web services through Claude. This server implements three main tools:
Web page reading and content extraction
Web search
Fact checking/grounding
Features
Tools
read_webpage
Extract content from web pages in a format optimized for LLMs
Supports multiple output formats (Default, Markdown, HTML, Text, Screenshot, Pageshot)
Options for including links and images
Ability to generate alt text for images
Cache control options
search_web
Search the web using Jina AI's search API
Configurable number of results (default: 5)
Support for image retention and alt text generation
Multiple return formats (markdown, text, html)
Returns structured results with titles, descriptions, and content
fact_check
Fact-check statements using Jina AI's grounding engine
Provides factuality scores and supporting evidence
Optional deep-dive mode for more thorough analysis
Returns references with key quotes and supportive/contradictory classification
Related MCP server: JIRA MCP Tools
Setup
Prerequisites
You'll need a Jina AI API key to use this server. Get one for free at https://jina.ai/
Installation
There are two ways to use this server:
Installing via Smithery
To install Jina AI for Claude Desktop automatically via Smithery:
Option 1: NPX (Recommended)
Add this configuration to your Claude Desktop config file:
Option 2: Local Installation
Clone the repository
Install dependencies:
Build the server:
Add this configuration to your Claude Desktop config:
Config File Location
On MacOS:
On Windows:
Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector:
The Inspector will provide a URL to access debugging tools in your browser.
API Response Types
All tools return structured JSON responses that include:
Status codes and metadata
Formatted content based on the requested output type
Usage information (token counts)
When applicable: images, links, and additional metadata
For detailed schema information, see schemas.ts.