Jina AI MCP Tools
This server provides web content extraction and search capabilities through Jina AI's APIs via the Model Context Protocol (MCP).
Web Content Extraction (
jina_reader): Extract content from any webpage by URL, with support for specifying page numbers and custom timeouts for slow sites.Automatic Pagination: Large documents are split into pages (default 15,000 tokens/page), letting you navigate lengthy content incrementally.
LRU Caching: Recently read URLs (up to 50) are cached for faster subsequent page requests.
GitHub File Support: GitHub file URLs are automatically converted to raw content URLs.
Web Search (
jina_search/jina_search_vip): Search the web using Jina AI's standard or VIP endpoints, with options to limit result counts and filter by domain (requires a Jina AI API key).Flexible Deployment: Run locally via
stdiotransport (for Claude Desktop, VS Code, Cursor) or remotely viahttptransport with configurable host/port.Proxy Support: All outbound requests can be routed through proxies via standard environment variables (
HTTP_PROXY,HTTPS_PROXY,ALL_PROXY,NO_PROXY).Configuration Options: Customize tokens per page, search endpoint, and cache size via command-line options. Basic web reading works without an API key; search features require one.
Enables searching of GitHub repositories and provides specialized support for reading GitHub file URLs by automatically converting them to raw content URLs for improved extraction.
Click on "Install 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., "@Jina AI MCP Toolssearch for the latest news on AI safety regulations"
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.
Jina AI MCP Tools
A Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
Features
This MCP server provides access to the following Jina AI APIs:
Web Reader - Extract content from web pages using r.jina.ai
Web Search - Search the web using s.jina.ai or svip.jina.ai (configurable via
--search-endpoint)
Prerequisites
Jina AI API Key (Optional) - Get a free API key from https://jina.ai/?sui=apikey for enhanced features
Node.js - Version 16 or higher
MCP Server
Using stdio Transport (Default)
For local integrations spawned by another process (e.g., Claude Desktop, VS Code, Cursor):
{
"mcpServers": {
"jina-mcp-tools": {
"command": "npx",
"args": [
"jina-mcp-tools",
"--transport", "stdio",
"--tokens-per-page", "15000",
"--search-endpoint", "standard"
],
"env": {
"JINA_API_KEY": "your_jina_api_key_here_optional"
}
}
}
}Using HTTP Transport
For remote server deployments accessible via HTTP:
Start the server:
# With API key
JINA_API_KEY=your_api_key npx jina-mcp-tools --transport http --host 127.0.0.1 --port 3000
# Without API key (reader tool only, binds to 127.0.0.1 by default)
npx jina-mcp-tools --transport http --port 3000Connect from MCP clients:
MCP Inspector:
npx @modelcontextprotocol/inspector→http://localhost:3000/mcpClaude Code:
claude mcp add --transport http jina-tools http://localhost:3000/mcpVS Code:
code --add-mcp '{"name":"jina-tools","type":"http","url":"http://localhost:3000/mcp"}'
CLI Options:
--transport- Transport type:stdioorhttp(default: stdio)--host- Host/interface to bind in HTTP mode (default:127.0.0.1)--port- HTTP server port (default: 3000, only for HTTP transport)--tokens-per-page- Tokens per page for pagination (default: 15000)--search-endpoint- Search endpoint to use:standard(s.jina.ai) orvip(svip.jina.ai) (default: standard)--cache-size- Reader cache size in URLs (default: 50)--help- Show the built-in CLI help
Proxy Environment Variables
Outbound HTTP requests now honor standard proxy environment variables. This applies to jina_reader, jina_search, and jina_search_vip.
Supported proxy variables:
HTTP_PROXY,HTTPS_PROXY,ALL_PROXYLowercase variants are also supported:
http_proxy,https_proxy,all_proxyExclusions are respected via
NO_PROXY/no_proxy
Example:
HTTPS_PROXY=http://proxy.internal:8080 npx jina-mcp-tools --transport stdioAvailable Tools
jina_reader
Extract and read web page content.
Parameters:
url- URL to read (required)page- Page number for paginated content (default: 1)customTimeout- Timeout override in seconds (optional)
Features:
Automatic pagination for large documents
LRU cache (50 URLs) for instant subsequent page requests
GitHub file URLs automatically converted to raw content URLs
jina_search / jina_search_vip
Search the web. Returns partial content; use jina_reader for full content. Requires API key.
Tool registered depends on --search-endpoint:
jina_search→standard(s.jina.ai, default)jina_search_vip→vip(svip.jina.ai)
Parameters:
query- Search query (required)count- Number of results (default: 5)siteFilter- Limit to specific domain (e.g., "github.com")
License
MIT
Links
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Tools
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/PsychArch/jina-mcp-tools'
If you have feedback or need assistance with the MCP directory API, please join our Discord server