Provides search capabilities for academic papers and preprints on the arXiv repository, including parallel search functionality for comprehensive research coverage.
Enables searching of academic papers on SSRN (Social Science Research Network), with support for parallel searches for comprehensive social science research coverage.
Jina AI Remote MCP Server
A remote Model Context Protocol (MCP) server that provides access to Jina Reader, Embeddings and Reranker APIs with a suite of URL-to-markdown, web search, image search, and embeddings/reranker tools:
Tool | Description | Is Jina API Key Required? |
| Get current contextual information for localized, time-aware responses | No |
| Extract clean, structured content from web pages as markdown via Reader API | Optional* |
| Capture high-quality screenshots of web pages via Reader API | Optional* |
| Analyze web pages for last update/publish datetime with confidence scores | No |
| Search the entire web for current information and news via Reader API | Yes |
| Search academic papers and preprints on arXiv repository via Reader API | Yes |
| Search academic papers on SSRN (Social Science Research Network) via Reader API | Yes |
| Search for images across the web (similar to Google Images) via Reader API | Yes |
| Search Jina AI news and blog posts at jina.ai/news | No |
| Expand and rewrite search queries based on the query expansion model via Reader API | Yes |
| Read multiple web pages in parallel for efficient content extraction via Reader API | Optional* |
| Run multiple web searches in parallel for comprehensive topic coverage and diverse perspectives via Reader API | Yes |
| Run multiple arXiv searches in parallel for comprehensive research coverage and diverse academic angles via Reader API | Yes |
| Run multiple SSRN searches in parallel for comprehensive social science research coverage via Reader API | Yes |
| Rerank documents by relevance to a query via Reranker API | Yes |
| Get top-k semantically unique strings via Embeddings API and submodular optimization | Yes |
| Get top-k semantically unique images via Embeddings API and submodular optimization | Yes |
| Extract figures, tables, and equations from PDF documents (arXiv papers or any PDF URL) using layout detection | Yes |
Optional tools work without an API key but have rate limits. For higher rate limits and better performance, use a Jina API key. You can get a free Jina API key from https://jina.ai
Usage
Some clients do not support env variable, so you may need to replace${JINA_API_KEY} below to a hardcoded real API key jina_xxx.
The server usesStreamable HTTP transport (MCP spec 2025-03-26). The /sse endpoint is kept as an alias for backward compatibility. See FAQ for details.
For client that supports remote MCP server:
For client that does not support remote MCP server yet, you need mcp-remote a local proxy to connect to the remote MCP server.
For Claude Code:
Upgrading from If you previously added with --transport sse, remove it first with claude mcp remove -s user jina, then re-add using the command below.
For OpenAI Codex: find ~/.codex/config.toml and add the following:
Related MCP server: Jina AI MCP Server
Tool Filtering before Registering
Every MCP tool requires the LLM to pre-allocate tokens in its context window for the tool's name, description, and schema. For LLMs with limited context windows, registering all 18 tools can consume significant space before any actual work begins.
By filtering tools server-side via query parameters on the endpoint URL (/v1?...), excluded tools are never registered with the MCP client. The client and LLM never see them, saving context window for what matters.
Query Parameters
Parameter | Description | Example |
| Comma-separated tool names to exclude |
|
| Comma-separated tool names to include |
|
| Comma-separated tags to exclude |
|
| Comma-separated tags to include |
|
Available Tags
Tag | Tools |
| search_web, search_arxiv, search_ssrn, search_images, search_jina_blog |
| parallel_search_web, parallel_search_arxiv, parallel_search_ssrn, parallel_read_url |
| read_url, parallel_read_url, capture_screenshot_url |
| primer, show_api_key, expand_query, guess_datetime_url, extract_pdf |
| sort_by_relevance, deduplicate_strings, deduplicate_images |
Precedence
Filters are applied in this order (highest to lowest priority):
exclude_tools- Always excludes specified toolsexclude_tags- Excludes tools in specified tagsinclude_tools- Includes specified toolsinclude_tags- Starts with only tools in specified tags
Examples
Exclude parallel tools (saves ~4 tools worth of context tokens):
Only include search and read tools:
Exclude specific tools:
Troubleshooting
I got stuck in a tool calling loop - what happened?
This is a common issue with LMStudio when the default context window is 4096 and you're using a thinking model like gpt-oss-120b or qwen3-4b-thinking. As the thinking and tool calling continue, once you hit the context window limit, the AI starts losing track of the beginning of the task. That's how it gets trapped in this rolling context window.
The solution is to load the model with enough context length to contain the full tool calling chain and thought process.
I can't see all tools.
Some MCP clients have local caching and do not actively update tool definitions. If you're not seeing all the available tools or if tools seem outdated, you may need to remove and re-add the jina-mcp-server to your MCP client configuration. This will force the client to refresh its cached tool definitions. In LMStudio, you can click the refresh button to load new tools.
Claude Desktop says "Server disconnected" on Windows
Cursor and Claude Desktop (Windows) have a bug where spaces inside args aren't escaped when it invokes npx, which ends up mangling these values. You can work around it using:
Cursor shows a red dot on this MCP status
Likely a UI bug from Cursor, but the MCP works correctly without any problem. You can toggle off/on to "restart" the MCP if you find the red dot annoying (fact is, since you are using this as a remote MCP, it's not a real "server restart" but mostly a local proxy restart).
My LLM never uses some tools
Assuming all tools are enabled in your MCP client but LLM still never uses some tools or favors some over others, this is pretty common when an LLM is trained with a specific set of tools. For example, we rarely see parallel_* tools being used organically by LLMs unless they are explicitly instructed to do so. Some research says LLMs must be trained to use . Models like Qwen3-Next natively prefer to call the singleton version but with multiple queries in an array to achieve parallelism (which our MCP also support now). Either way, in Cursor, you can add the following rule to your .mdc file:
Why is my content truncated?
Claude Code, Claude Desktop, and Cursor enforce a fixed 25k token limit on MCP tool responses. To prevent these clients from rejecting large responses entirely, this server applies a token guardrail specifically for read_url and parallel_read_url tools when connecting from these clients. For a single large content item, the text is truncated proportionally to fit within the token budget. For responses containing multiple items, the server keeps items in order until adding the next item would exceed the limit, then stops there. This ensures the response always fits within client constraints while preserving as much content as possible. Other clients like OpenAI Codex have configurable limits (tool_output_token_limit in config) so no server-side truncation is applied.
Using parallel tools vs singleton tools with arrays
Claude Code recently started preferring parallel_* tools (like parallel_search_web, parallel_read_url) for concurrent operations. However, models like Qwen3-Next prefer calling singleton tools with multiple queries in an array. Both approaches work: the singleton versions (search_web, search_arxiv, search_ssrn, read_url) accept either a single string or an array of strings for the query/url parameter. When given an array, these tools automatically execute all queries in parallel internally, producing the same concurrent behavior as explicitly calling parallel_* tools. Use whichever style your model prefers.
Why is the endpoint called /sse but using Streamable HTTP?
The /sse endpoint URL is kept for backward compatibility with existing users. The recommended endpoint is now /v1. Both use the same Streamable HTTP transport (the new MCP standard from spec 2025-03-26), not the deprecated SSE transport.
This works seamlessly because:
Claude Desktop, Cursor, Windsurf use
mcp-remotewhich defaults tohttp-firststrategy (tries Streamable HTTP first)Claude Code has native support for both transports
LM Studio supports direct connection to Streamable HTTP endpoints
The response streaming still uses SSE format (Content-Type: text/event-stream), but the protocol layer (session management, initialization) follows Streamable HTTP spec. All major MCP clients are compatible.
Client-side tool filtering with mcp-remote
If you're using mcp-remote as a local proxy, you can also filter tools client-side using its --ignore-tool flag:
This approach filters tools at the proxy level before they reach the MCP client. However, server-side filtering via query parameters (see Tool Filtering) is more efficient as it reduces token usage from the source.
Developer Guide
Local Development
Deploy to Cloudflare Workers
This will deploy your MCP server to a URL like: jina-mcp-server.<your-account>.workers.dev/v1