MCP server for JinaAI reader
Mcp jinaai reader mcp server lets Claude, Cursor and other MCP clients work with MCP Jinaai Reader directly. MCP server for JinaAI reader.
The functionality of this tool is now available in mcp-omnisearch, which combines multiple MCP tools in one unified package.
Once connected, the assistant can call these 3 tools directly:
read_url — The read_url tool exposed by this serverSetup — The Setup tool exposed by this serverPublishing — The Publishing tool exposed by this serverThe server is distributed via npm as mcp-jinaai-reader, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.
Before the server will start you need to supply one environment variable: JINAAI_API_KEY. Keep credentials in your client's env block or a secrets manager rather than committing them.
Search and scraping servers exist to fix the single most common failure of any assistant: answering from stale training data instead of what is on the web today. MCP Jinaai Reader sits in that group, and the shape of its toolset — read_url, Setup, Publishing — tells you what it is really for. Worth comparing against the other search web scraping servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.
| Tool | What it does |
|---|---|
| read_url | The read_url tool exposed by this server. |
| Setup | The Setup tool exposed by this server. |
| Publishing | The Publishing tool exposed by this server. |
{
"mcpServers": {
"jinaai-reader": {
"command": "node",
"args": ["-y", "mcp-jinaai-reader"],
"env": {
"JINAAI_API_KEY": "your-jinaai-api-key"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| JINAAI_API_KEY | Credential the server authenticates with. | Yes |
The simplest web tool that matters — fetch any URL and get model-ready markdown back.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Put 6,000+ pre-built scrapers at your assistant's fingertips through one MCP endpoint.