Jina AI MCP Tools

Web search and page reading for coding agents. Two tools, no tool-catalog buffet.

jina-mcp-toolsis an unofficial, deliberately smallModel Context Protocol (MCP)server built onJina AI Reader and Search.

[!NOTE] This is an unofficial community project. It is not affiliated with or endorsed by Jina AI, and it uses Jina AI APIs rather than replacing them.

Jina already provides an excellentofficial MCP serverandofficial CLI. They are designed to expose a broad range of Jina capabilities. This project makes a different tradeoff: it treats context space and tool-selection attention as resources worth saving.

- Node.js 20 or later.
- AJina AI API keyfor web search. The reader works without a key, subject to Jina's unauthenticated rate limits.

codex mcp add jina-web --env JINA_API_KEY="$JINA_API_KEY" -- npx -y jina-mcp-tools

claude mcp add --scope user \ --env JINA_API_KEY="$JINA_API_KEY" \ --transport stdio jina-web -- npx -y jina-mcp-tools

{ "inputs": [ { "type": "promptString", "id": "jina-api-key", "description": "Jina AI API key", "password": true } ], "servers": { "jina-web": { "type": "stdio", "command": "npx", "args": ["-y", "jina-mcp-tools"], "env": { "JINA_API_KEY": "${input:jina-api-key}" } } } }

Open the user configuration withMCP: Open User Configuration, or save the file as.vscode/mcp.jsonto share the server configuration with a workspace. Removeenvandinputsfor reader-only mode.

For a reader-only user-profile installation from the command line:

code --add-mcp "{\"name\":\"jina-web\",\"type\":\"stdio\",\"command\":\"npx\",\"args\":[\"-y\",\"jina-mcp-tools\"]}"

Claude Desktop, Cursor, and Other MCP Clients

For clients that use themcpServersJSON format:

{ "mcpServers": { "jina-web": { "command": "npx", "args": [ "-y", "jina-mcp-tools" ], "env": { "JINA_API_KEY": "your_jina_api_key_here" } } } }

The default transport is stdio. Remove theenvblock for reader-only mode.

Extract and read content from a web page.

- url— URL to read (required).
- page— Page number for paginated content (default:1).
- customTimeout— Timeout override in seconds (optional).

- Automatically paginates large documents instead of returning one oversized response.
- Keeps an LRU cache so later pages of the same URL are available immediately.
- Converts GitHub file URLs to raw content URLs.
- Tries directAccept: text/markdownretrieval for a maintained allowlist of documentation and blog hosts, then falls back tor.jina.aiif the response fails or is empty.

The default cache holds 50 URLs, and each page is limited to approximately 15,000 tokens. Both values are configurable.

Search the web and return a lightweight shortlist. Usejina_readerto retrieve the full content of promising results. A Jina API key is required.

Only one search tool is registered, depending on--search-endpoint:

- jina_searchusess.jina.ai(standard, the default).
- jina_search_vipusessvip.jina.ai(vip).

- query— Search query (required).
- count— Number of results (default:5).
- siteFilter— Limit results to a domain such asgithub.com.

The small default result count is intentional: search first, read selectively, and leave some context for the repository you were working on in the first place.

Usage: jina-mcp-tools [options] Options: --transport <stdio|http> Transport type (default: stdio) --host <host> Host/interface in HTTP mode (default: 127.0.0.1) --port <1-65535> HTTP port (default: 3000) --tokens-per-page <positive-int> Tokens per reader page (default: 15000) --search-endpoint <standard|vip> Search endpoint (default: standard) --cache-size <positive-int> Reader cache size in URLs (default: 50) -h, --help Show the built-in help

HTTP mode is intended for self-hosted deployments or clients that cannot spawn a local stdio process.

# Search and reader JINA_API_KEY=your_api_key npx -y jina-mcp-tools \ --transport http \ --host 127.0.0.1 \ --port 3000 # Reader only npx -y jina-mcp-tools --transport http --port 3000

- Codex:codex mcp add jina-web --url http://localhost:3000/mcp
- Claude Code:claude mcp add --transport http jina-web http://localhost:3000/mcp
- MCP Inspector:npx -y @modelcontextprotocol/inspector
- VS Code:code --add-mcp "{\"name\":\"jina-web\",\"type\":\"http\",\"url\":\"http://localhost:3000/mcp\"}"

HTTP mode binds to127.0.0.1by default. For a remote deployment, put the server behind TLS and require a bearer token:

JINA_MCP_HTTP_AUTH_TOKEN=change-me \ npx -y jina-mcp-tools --transport http --host 0.0.0.0 --port 3000

Browser-origin requests are limited to localhost by default. SetJINA_MCP_ALLOWED_ORIGINSto a comma-separated allowlist for browser-based remote clients.

Running the MCP process locally does not make Jina requests offline: search and most reader requests still call Jina AI services. Some allowlisted markdown hosts and GitHub file URLs may be fetched directly.

To route outbound requests through a proxy, enable Node's proxy environment support and provide the proxy URLs:

NODE_USE_ENV_PROXY=1 \ HTTP_PROXY=http://127.0.0.1:7890 \ HTTPS_PROXY=http://127.0.0.1:7890 \ NO_PROXY=localhost,127.0.0.1,::1 \ npx -y jina-mcp-tools

For MCP clients that use themcpServersconfiguration format, include the same environment variables:

{ "mcpServers": { "jina-web": { "command": "npx", "args": ["-y", "jina-mcp-tools"], "env": { "JINA_API_KEY": "your_jina_api_key_here", "NODE_USE_ENV_PROXY": "1", "HTTP_PROXY": "http://127.0.0.1:7890", "HTTPS_PROXY": "http://127.0.0.1:7890", "NO_PROXY": "localhost,127.0.0.1,::1" } } } }

Alternatively, start Node withNODE_OPTIONS=--use-env-proxy. Proxy URLs are only used when proxy environment support is enabled.

This project intentionally does not aim to expose every Jina API. It is not the right choice when you need embeddings, reranking, classification, screenshots, image or academic search, query expansion, deduplication, or structured PDF extraction. Use the officialMCP serverorCLIfor those jobs.

- GitHub:github.com/PsychArch/jina-mcp-tools
- Issues:github.com/PsychArch/jina-mcp-tools/issues

Enhances LLM responses with factual, real-time web content using Jina AI's grounding capabilities.