jina-ai/MCP

A remote Model Context Protocol (MCP) server for the Jina Reader, Search, Embeddings and Reranker APIs:
## Usage
> [!WARNING]
> Some clients do not support env variable, so you may need to replace ${JINAAPIKEY} below to a hardcoded real API key jinaxxx.
For client that supports remote MCP server:
json
"mcpServers": {
"jina-mcp-server": {
"url": "https://mcp.jina.ai/v1",
"headers": {
"Authorization": "Bearer ${JINAAPIKEY}" // optional
For Claude Code:
bash
claude mcp add -s user --transport http jina https://mcp.jina.ai/v1 \
--header "Authorization: Bearer ${JINAAPIKEY}"
For OpenAI Codex: find ~/.codex/config.toml and add the following:
toml
[mcpservers.jina-mcp-server]
command = "npx"
args = [
"-y",
"mcp-remote",
"https://mcp.jina.ai/v1",
"--header",
"Authorization: Bearer ${JINAAPIKEY}"]
For client that does not support remote MCP server yet, you need mcp-remote a local proxy to connect to the remote MCP server.
json
"mcpServers": {
"jina-mcp-server": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.jina.ai/v1",
"--header",
"Authorization: Bearer ${JINAAPIKEY}"
## Available tools
| Tool | Description | Is Jina API Key Required? |
| primer | Get current contextual information for localized, time-aware responses | No |
| readurl | Read a web page or PDF as markdown. Pass question for passages instead of the full body via Reader API | Optional |
| capturescreenshoturl | Capture a screenshot of a web page via Reader API | Optional |
| guessdatetimeurl | Guess a page's publish or last-update datetime, with a confidence score | No |
| searchweb | Search the web. Returns titles, URLs and engine snippets via Reader API | Yes |
| searcharxiv | Search academic papers and preprints on arXiv repository via Reader API | Yes |
| searchssrn | Search academic papers on SSRN (Social Science Research Network) via Reader API | Yes |
| searchimages | Search the web for images via Reader API | Yes |
| searchjinablog | Search Jina AI news and blog posts at jina.ai/news | No |
| sortbyrelevance | Rerank documents by relevance to a query via Reranker API | Yes |
| deduplicatestrings | Get top-k semantically unique strings via Embeddings API and submodular optimization | Yes |
| extractpdf | 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 at rate limits. Use a key for higher limits. Free keys: https://jina.ai
## Tool Filtering before Registering
Registering a tool costs context tokens for its name, description and schema whether or not it is called. With 12 tools, that budget is spent before the first request.
Filtering server-side through query parameters on the endpoint URL (/v1?...) excludes tools before registration, so the client never sees them.
### Query Parameters
| Parameter | Description | Example |
| excludetools | Comma-separated tool names to exclude | excludetools=searchweb,searcharxiv |
| includetools | Comma-separated tool names to include | includetools=readurl,searchweb |
| excludetags | Comma-separated tags to exclude | excludetags=search,rerank |
| includetags | Comma-separated tags to include | includetags=search,read |