dataeyes-mcp-server
OfficialClick on "Deploy 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., "@dataeyes-mcp-server search for latest breakthroughs in renewable energy"
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.
DataEyes MCP Server
An MCP server that provides web search and page reading capabilities through the DataEyes API.
Tools
search — Search the web and get structured results.
read — Fetch a web page and extract its content.
Related MCP server: MCP Search & Fetch
Getting Your API Key
Register at shuyanai.com (中国站) or dataeyes.ai (Global) to obtain your API key.
Usage
stdio
For local MCP clients (Cursor, Claude Desktop, etc.) using uvx:
Global
{
"mcpServers": {
"dataeyes": {
"command": "uvx",
"args": ["dataeyes-mcp-server"],
"env": {
"DATAEYES_API_KEY": "your-api-key"
}
}
}
}中国站
{
"mcpServers": {
"dataeyes": {
"command": "uvx",
"args": ["dataeyes-mcp-server"],
"env": {
"DATAEYES_API_KEY": "your-api-key",
"DATAEYES_API_BASE_URL": "https://api.shuyanai.com"
}
}
}
}Environment Variable | Default | Description |
| — | API key (required) |
|
| API base URL |
Streamable HTTP
No installation required. Connect directly to the hosted MCP endpoint:
Global
{
"mcpServers": {
"dataeyes": {
"url": "https://mcp.dataeyes.ai/mcp",
"headers": {
"Authorization": "Bearer your-api-key"
}
}
}
}中国站
{
"mcpServers": {
"dataeyes": {
"url": "https://mcp.shuyanai.com/mcp",
"headers": {
"Authorization": "Bearer your-api-key"
}
}
}
}License
This project is licensed under the MIT License.
Available Tools
2 toolsreadARead-onlyIdempotent
Read and extract content from a web page URL.
Fetches the page, extracts the main content, and returns it in the requested format (markdown by default). Includes metadata such as title, description, and status code.
Inputs: params (required). Returns: Structured reader response.
searchARead-onlyIdempotent
Search the web using DataEyes search engine.
Returns a list of web page results including title, URL, snippet, and relevance score. Useful for finding information, research, and discovering relevant web pages on any topic.
Inputs: params (required). Returns: Structured search response.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have completely different purposes: one extracts content from a given URL, the other searches for URLs. There is no overlap or ambiguity.
Both tools use single-word imperative verbs ('read' and 'search') in lowercase, following a consistent and predictable pattern.
With only two tools, the server is minimal but covers the basic web interaction workflow (search then read). It is on the lower end of the typical range but not inappropriate for a focused purpose.
The server provides a complete workflow for finding and reading web content. A minor gap is the lack of tools for batch processing or advanced content extraction, but core needs are met.
Maintenance
Related MCP Connectors
Web search and page-reading for AI agents. One-click OAuth connect, or a Caesar API key.
Web search and page reading for AI agents, including JSON APIs, RSS feeds and YouTube.
Web search, read any page, verify or find emails, screenshots, keyword data. One key, pay per call.
Web data for agents. Extract web pages, crawl websites, discover URLs, and search the web.
Related MCP Servers
- FlicenseDqualityDmaintenanceProvides web connectivity tools for searching the web via DuckDuckGo or SerpAPI, fetching URL content, and extracting readable text from web pages.33-
- AlicenseNot gradedqualityFmaintenanceProvides web search and page fetching capabilities using Ollama's API.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to read webpages and perform web searches using DuckDuckGo.MIT
- AlicenseNot gradedqualityDmaintenanceProvides web search and content extraction for AI agents.MIT