A
licenseNot graded
qualityD
maintenanceEnables 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
MCP JinaAI Search Server
by spences10
The MCP JinaAI Search Server enables efficient web search and content retrieval optimized for LLMs using Jina.ai's API. With this server, you can:
Perform web searches using queries through Jina.ai's Search API
Retrieve clean, structured, LLM-friendly content from web pages
Control search behavior with configurable parameters (token budget, response format, caching, stream mode)
Extract content from iframes, shadow DOM, and resolve redirects
Customize content rendering based on browser locale
Gather links and images from pages with optional image captioning
Bypass cache for fresh results when needed
Benefit from seamless integration with LLM workflows through the Model Context Protocol
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP JinaAI Search Serverfind recent developments in quantum computing"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-jinaai-search
⚠️ Notice
This repository is no longer maintained.
The functionality of this tool is now available in mcp-omnisearch, which combines multiple MCP tools in one unified package.
Please use mcp-omnisearch instead.
A Model Context Protocol (MCP) server for integrating Jina.ai's Search API with LLMs. This server provides efficient and comprehensive web search capabilities, optimised for retrieving clean, LLM-friendly content from the web.
Related MCP server: Jina AI Remote MCP Server
Features
🔍 Advanced web search through Jina.ai Search API
🚀 Fast and efficient content retrieval
📄 Clean text extraction with preserved structure
🧠 Content optimised for LLMs
🌐 Support for various content types including documentation
🏗️ Built on the Model Context Protocol
🔄 Configurable caching for performance
🖼️ Optional image and link gathering
🌍 Localisation support through browser locale
🎯 Token budget control for response size
Configuration
This server requires configuration through your MCP client. Here are examples for different environments:
Cline Configuration
Add this to your Cline MCP settings:
{
"mcpServers": {
"jinaai-search": {
"command": "node",
"args": ["-y", "mcp-jinaai-search"],
"env": {
"JINAAI_API_KEY": "your-jinaai-api-key"
}
}
}
}Claude Desktop with WSL Configuration
For WSL environments, add this to your Claude Desktop configuration:
{
"mcpServers": {
"jinaai-search": {
"command": "wsl.exe",
"args": [
"bash",
"-c",
"JINAAI_API_KEY=your-jinaai-api-key npx mcp-jinaai-search"
]
}
}
}Environment Variables
The server requires the following environment variable:
JINAAI_API_KEY: Your Jina.ai API key (required)
API
The server implements a single MCP tool with configurable parameters:
search
Search the web and get clean, LLM-friendly content using Jina.ai Reader. Returns top 5 results with URLs and clean content.
Parameters:
query(string, required): Search queryformat(string, optional): Response format ("json" or "text"). Defaults to "text"no_cache(boolean, optional): Bypass cache for fresh results. Defaults to falsetoken_budget(number, optional): Maximum number of tokens for this requestbrowser_locale(string, optional): Browser locale for rendering contentstream(boolean, optional): Enable stream mode for large pages. Defaults to falsegather_links(boolean, optional): Gather all links at the end of response. Defaults to falsegather_images(boolean, optional): Gather all images at the end of response. Defaults to falseimage_caption(boolean, optional): Caption images in the content. Defaults to falseenable_iframe(boolean, optional): Extract content from iframes. Defaults to falseenable_shadow_dom(boolean, optional): Extract content from shadow DOM. Defaults to falseresolve_redirects(boolean, optional): Follow redirect chains to final URL. Defaults to true
Development
Setup
Clone the repository
Install dependencies:
pnpm installBuild the project:
pnpm run buildRun in development mode:
pnpm run devPublishing
Create a changeset:
pnpm changesetVersion the package:
pnpm versionBuild and publish:
pnpm releaseContributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
MIT License - see the LICENSE file for details.
Acknowledgments
Built on the Model Context Protocol
Powered by Jina.ai Search API
Available Tools
1 toolsearchB
Search the web and get clean, LLM-friendly content using Jina.ai Reader. Returns top 5 results with URLs and clean content.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query | |
| format | No | Response format (json or text) | text |
| no_cache | No | Bypass cache for fresh results | |
| token_budget | No | Maximum number of tokens for this request | |
| browser_locale | No | Browser locale for rendering content | |
| stream | No | Enable stream mode for large pages | |
| gather_links | No | Gather all links at the end of the response | |
| gather_images | No | Gather all images at the end of the response | |
| image_caption | No | Caption images in the content | |
| enable_iframe | No | Extract content from iframes | |
| enable_shadow_dom | No | Extract content from shadow DOM | |
| resolve_redirects | No | Follow redirect chains to final URL |
TDQS
B3.1/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It mentions the tool returns 'clean, LLM-friendly content' and 'top 5 results with URLs and clean content,' which gives some behavioral context. However, it lacks critical information about rate limits, authentication requirements, error conditions, or what constitutes 'clean' content, leaving significant gaps for a tool with 12 parameters.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is perfectly concise and front-loaded: a single sentence that communicates the core functionality, method, and output format. Every word earns its place with zero redundancy or unnecessary elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a search tool with 12 parameters and no output schema, the description provides basic purpose and output format but lacks sufficient behavioral context. Without annotations covering safety, limits, or authentication, and with no output schema to explain return values, the description should do more to compensate for these gaps, especially given the tool's complexity.
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 the schema fully documents all 12 parameters. The description doesn't add any parameter-specific information beyond what's already in the schema descriptions. According to guidelines, when schema coverage is high (>80%), the baseline score is 3 even with no parameter information in the description.
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 clearly states the tool's purpose: 'Search the web and get clean, LLM-friendly content using Jina.ai Reader.' It specifies the action (search), resource (web content), and processing method (Jina.ai Reader). However, without sibling tools, it cannot demonstrate differentiation from alternatives, preventing a score of 5.
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?
The description provides no guidance on when to use this tool versus alternatives, prerequisites, or contextual constraints. It mentions returning 'top 5 results' but doesn't explain when this limitation is appropriate or when other search tools might be better suited.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
B3.2/5.0
Disambiguation5/5
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool 'search' has a clear and singular purpose, making it impossible for an agent to misselect among non-existent alternatives.
Naming Consistency5/5
A single tool inherently has perfect naming consistency, as there are no other tools to compare against. The name 'search' follows a simple verb pattern, which is appropriate and unambiguous for its function.
Tool Count2/5
A single tool is too few for a server named 'MCP JinaAI Search Server', which suggests a broader search functionality scope. While the tool covers basic web search, the server lacks additional tools for advanced operations like filtering, pagination, or domain-specific searches, making it feel thin and under-scoped.
Completeness2/5
The server is severely incomplete for a search domain. It only offers a basic search tool without any supporting operations such as refining queries, handling multiple result pages, or accessing search history. This creates significant gaps that could lead to agent failures when more complex search tasks are required.
Maintenance
ActivityInactive
ResponsivenessSyncing
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.
Jina AI Reader/Search MCP — turn any URL into clean LLM-ready markdown, plus web search.
Web search for AI agents — one tool across 6 engines, routed to the cheapest + cached.
The best web search for your AI Agent
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceProvides access to Jina AI's web reading, search, embeddings, and reranking capabilities. Enables URL content extraction, web/arXiv/image search, document deduplication, and relevance ranking through natural language.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceProvides web content extraction, search capabilities (web, arXiv, SSRN, images), semantic deduplication, and reranking through Jina AI's Reader, Embeddings, and Reranker APIs.1Apache 2.0
- AlicenseBqualityAmaintenanceIntegrates Jina AI Search Foundation APIs to provide web page content extraction and search capabilities. It supports automatic pagination, result caching, and both standard and VIP search endpoints for enhanced information retrieval.116845MIT
Appeared in Searches
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/spences10/mcp-jinaai-search'
If you have feedback or need assistance with the MCP directory API, please join our Discord server