Frequently Asked Questions about Jina AI MCP Server
Q: What is the Jina AI MCP Server? A: The Jina AI MCP Server is a tool that enhances the capabilities of Large Language Models (LLMs) like Claude by providing them access to Jina AI’s web services, including web content extraction, web search, and fact-checking.
Q: How does the MCP Server work?
A: The server implements three main tools: read_webpage (extracts content from web pages), search_web (performs web searches), and fact_check (verifies statements using Jina AI’s grounding engine).
Q: What is MCP? A: MCP stands for Model Context Protocol. It is an open protocol that standardizes how applications provide context to LLMs.
Q: What are the prerequisites for using the Jina AI MCP Server? A: You need a Jina AI API key, which you can get for free at https://jina.ai/.
Q: How can I install the Jina AI MCP Server?
A: You can install it via Smithery using the command npx -y @smithery/cli install jina-ai-mcp-server --client claude or through a local installation by cloning the repository, installing dependencies, and building the server.
Q: Where is the Claude Desktop config file located?
A: On MacOS, it’s located at ~/Library/Application Support/Claude/claude_desktop_config.json. On Windows, it’s located at %APPDATA%/Claude/claude_desktop_config.json.
Q: How can I debug the MCP server?
A: Use the MCP Inspector by running npm run inspector. This will provide a URL to access debugging tools in your browser.
Q: What type of responses does the API return? A: The tools return structured JSON responses that include status codes, metadata, formatted content, usage information (token counts), images, links, and additional metadata.
Q: Can I customize the output format of the extracted web content?
A: Yes, the read_webpage tool supports multiple output formats, including Default, Markdown, HTML, Text, Screenshot, and Pageshot.
Q: What is UBOS and how does it relate to the Jina AI MCP Server? A: UBOS is a full-stack AI Agent Development Platform that helps you orchestrate AI Agents, connect them with your enterprise data, build custom AI Agents with your LLM model and Multi-Agent Systems. The Jina AI MCP Server can be integrated into UBOS to enhance the capabilities of your AI agents.
Q: Can the search_web tool retain images from the web search results?
A: Yes, the search_web tool supports image retention and alt text generation.
Q: What does the fact_check tool provide?
A: The fact_check tool provides factuality scores, supporting evidence, and optional deep-dive mode for a more thorough analysis of statements.
Jina AI
Project Details
- joeBlockchain/mcp-jina-ai
- MIT License
- Last Updated: 5/12/2025
Recomended MCP Servers
AI-powered FastMCP server for intelligent stock photo search, download, and attribution management from Unsplash
Ancestry MCP server made with Python that allows interactability with .ged (GEDCOM) files
Интеграция Strava API с Model Context Protocol SDK
An example MCP server using Typescript
Fast and free zeroshot lipsync MCP server
MCP server for Israel Government Data
3D Maps for OpenSceneGraph / C++14
A nomad MCP Server (modelcontextprotocol)





