Skip to main content
Glama
Sign In
deeneskoruzh
Jina AI MCP Tools

Jina AI MCP Tools

by PsychArch
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Jina AI MCP 工具

一个与 Jina AI Search Foundation API 集成的模型上下文协议 (MCP) 服务器。

功能

此 MCP 服务器提供对以下 Jina AI API 的访问：

  • Web Reader - 使用 r.jina.ai 提取网页内容

  • Web Search - 使用 s.jina.ai 或 svip.jina.ai 进行网页搜索（可通过 --search-endpoint 配置）

Related MCP server: Jina Web Search MCP

先决条件

  1. Jina AI API Key（可选）- 从 https://jina.ai/?sui=apikey 获取免费 API 密钥以使用增强功能

  2. Node.js - 16 或更高版本

MCP 服务器

使用 stdio 传输（默认）

适用于由其他进程（例如 Claude Desktop、VS Code、Cursor）启动的本地集成：

{
  "mcpServers": {
    "jina-mcp-tools": {
      "command": "npx",
      "args": [
        "jina-mcp-tools",
        "--transport", "stdio",
        "--tokens-per-page", "15000",
        "--search-endpoint", "standard"
      ],
      "env": {
        "JINA_API_KEY": "your_jina_api_key_here_optional"
      }
    }
  }
}

使用 HTTP 传输

适用于可通过 HTTP 访问的远程服务器部署：

启动服务器：

# With API key
JINA_API_KEY=your_api_key npx jina-mcp-tools --transport http --host 127.0.0.1 --port 3000

# Without API key (reader tool only, binds to 127.0.0.1 by default)
npx jina-mcp-tools --transport http --port 3000

从 MCP 客户端连接：

  • MCP Inspector: npx @modelcontextprotocol/inspector → http://localhost:3000/mcp

  • Claude Code: claude mcp add --transport http jina-tools http://localhost:3000/mcp

  • VS Code: code --add-mcp '{"name":"jina-tools","type":"http","url":"http://localhost:3000/mcp"}'

CLI 选项：

  • --transport - 传输类型：stdio 或 http（默认：stdio）

  • --host - HTTP 模式下绑定的主机/接口（默认：127.0.0.1）

  • --port - HTTP 服务器端口（默认：3000，仅适用于 HTTP 传输）

  • --tokens-per-page - 分页的每页 Token 数（默认：15000）

  • --search-endpoint - 使用的搜索端点：standard (s.jina.ai) 或 vip (svip.jina.ai)（默认：standard）

  • --cache-size - Reader 缓存大小（以 URL 数量计，默认：50）

  • --help - 显示内置的 CLI 帮助

代理环境变量

出站 HTTP 请求现在遵循标准的代理环境变量。这适用于 jina_reader、jina_search 和 jina_search_vip。

  • 支持的代理变量：HTTP_PROXY, HTTPS_PROXY, ALL_PROXY

  • 也支持小写变体：http_proxy, https_proxy, all_proxy

  • 通过 NO_PROXY / no_proxy 遵循排除规则

示例：

HTTPS_PROXY=http://proxy.internal:8080 npx jina-mcp-tools --transport stdio

可用工具

jina_reader

提取并读取网页内容。

参数：

  • url - 要读取的 URL（必填）

  • page - 分页内容页码（默认：1）

  • customTimeout - 超时覆盖（以秒为单位，可选）

功能：

  • 大型文档自动分页

  • LRU 缓存（50 个 URL），用于即时后续页面请求

  • GitHub 文件 URL 自动转换为原始内容 URL

  • 优先尝试 Accept: text/markdown 以获取维护的 Markdown 兼容文档/博客主机列表，如果获取失败或响应为空，则回退到 r.jina.ai

jina_search / jina_search_vip

搜索网页。返回部分内容；使用 jina_reader 获取完整内容。需要 API 密钥。

注册的工具取决于 --search-endpoint：

  • jina_search → standard (s.jina.ai, 默认)

  • jina_search_vip → vip (svip.jina.ai)

参数：

  • query - 搜索查询（必填）

  • count - 结果数量（默认：5）

  • siteFilter - 限制特定域名（例如 "github.com"）

许可证

MIT

链接

Available Tools

1 tool
jina_readerJina Web ReaderC

Read and extract content from web page.

NameRequiredDescriptionDefault
urlYesURL of the webpage to read and extract content from
pageNoPage number for paginated content (1-indexed)
customTimeoutNoOverride timeout in whole seconds (1-2147483) for slow sites

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden, but it discloses nothing about authentication requirements, rate limits, JavaScript rendering, truncation/pagination behavior, or error handling. The presence of customTimeout implies slow sites exist but the description never explains that tradeoff.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a single short sentence that is front-loaded with the core action, with zero filler. However, the extreme brevity is under-specification rather than true efficiency for a tool this thin on context.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations and no output schema, the description must explain what comes back and how pagination and timeouts behave; it does neither. An agent cannot tell whether the response is raw HTML, markdown, or plain text, nor how paginated content is returned.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so url, page, and customTimeout are each documented in the schema itself; baseline 3 applies. The description adds no extra meaning beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb pair (read/extract) and resource (web page), so an agent knows this fetches and parses page content. With no sibling tools to distinguish from, there is nothing more to disambiguate, but it does not clarify output form (markdown vs HTML vs text).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no mention of alternatives, and no conditions under which this tool should be preferred or avoided. The description is purely a statement of function.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev1.3.0
    • Changedjina_reader8 fields changed
      • changedInput schema / $schema
        Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
      • changedInput schema / properties / customTimeout / description
        Previous value: -"Override timeout in seconds for slow sites"New value: +"Override timeout in whole seconds (1-2147483) for slow sites"
      • addedInput schema / properties / customTimeout / exclusiveMinimum
        Added value: +0
      • addedInput schema / properties / customTimeout / maximum
        Added value: +2147483
      • changedInput schema / properties / customTimeout / type
        Previous value: -"number"New value: +"integer"
      • addedInput schema / properties / page / exclusiveMinimum
        Added value: +0
      • addedInput schema / properties / page / maximum
        Added value: +9007199254740991
      • changedInput schema / properties / page / type
        Previous value: -"number"New value: +"integer"
  2. 1 tool updatev1.2.4
    • Changedjina_reader1 field changed
      • removedInput schema / additionalProperties
        Removed value: -false
  3. 1 tool updatev1.2.0
    • First observedjina_reader
Deploy Server
Let your AI agent see the webWeb-to-screenshot MCP for Claude, Cursor and Codex. No cookie banners. Free to start.snap-render.comAd

TDQS

B3/5.0

Scored across 1 tool

Disambiguation5/5

There is only one tool, so there is no possibility of confusion or misselection. Its purpose is clearly distinct.

Naming Consistency5/5

With a single tool named jina_reader, consistency is trivially satisfied. It follows a readable snake_case pattern.

Tool Count2/5

A server branded as 'Jina AI MCP Tools' with only one tool seems too few for the apparent scope. Jina AI typically offers multiple capabilities (search, embeddings, reranking), so one tool feels under-provisioned.

Completeness1/5

The surface only covers web page reading, with no search, embedding, reranking, or other operations implied by the Jina AI brand. This is a severely incomplete toolset for the stated purpose.

Maintenance

ActivityMaintained
ResponsivenessLimited data

Resources

Related MCP Connectors

Related MCP Servers

  • MCP JinaAI Search Server

    spences10
    A
    license
    B
    quality
    F
    maintenance
    Enables efficient web search integration with Jina.ai's Search API, offering clean, LLM-optimized content retrieval with support for various content types and configurable caching.
    1
    25 npm
    3
    MIT

  • Jina Web Search MCP

    hypersniper05
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables web content retrieval and semantic search capabilities through the Jina AI API. Provides tools to fetch content from URLs and perform intelligent web searches with natural language queries.
    3
    MIT

  • Jina AI Remote MCP Server

    zhijiew
    A
    license
    Not graded
    quality
    C
    maintenance
    Provides web content extraction, search capabilities (web, arXiv, SSRN, images), semantic deduplication, and reranking through Jina AI's Reader, Embeddings, and Reranker APIs.
    1
    Apache 2.0