io.github.radoxtech/deepseek-search-everywhere-mcp

deepseek-search-everywhere-mcp

MCP server: web search, page fetch to Markdown, data extraction, cited deep research via DeepSeek.

GitHub PyPI

No known CVEs

MIT license

Actively maintained

Last commit 1d ago

Works with most clients

Transport: stdio, sse, http

0 tools

Grade F

MCPpedia last refreshed this data 23h ago

Edit this pageView history

io.github.radoxtech/deepseek-search-everywhere-mcp is an MCP server that MCP server: web search, page fetch to Markdown, data extraction, cited deep research via DeepSeek. Its tool list has not been published yet over stdio, sse and http, requires no API key, and scores 61/100 on MCPpedia's security, maintenance and efficiency rubric.

AI / ML Search

Step 1

Install in your client

Config is the same across clients - only the file and path differ.

Supported in Claude Desktopstdio, sse, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "deepseek-search-everywhere": {
      "env": {
        "DEEPSEEK_API_KEY": "sk-..."
      },
      "args": [
        "deepseek-search-everywhere-mcp"
      ],
      "command": "uvx"
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/io-github-radoxtech-deepseek-search-everywhere-mcp)](https://mcppedia.org/s/io-github-radoxtech-deepseek-search-everywhere-mcp)

Read me

What io.github.radoxtech/deepseek-search-everywhere-mcp does

MCP server: web search, page fetch to Markdown, data extraction, cited deep research via DeepSeek.

Test This Server

Run this in your terminal to verify the server starts. Then let us know if it worked - your result helps other developers.

uvx 'deepseek-search-everywhere-mcp' 2>&1 | head -1 && echo "✓ Server started successfully"

After testing, let us know if it worked:

Loading README…

Scored, not listed

Why this score

Five weighted categories - click any category to see the underlying evidence.

Score breakdown

61/100across 5 weighted dimensions

How we score →

0255075100

−39

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked deepseek-search-everywhere-mcp against OSV.dev.

Community

Reviews

Be the first to review

Have you used this server?

Share your experience - it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is io.github.radoxtech/deepseek-search-everywhere-mcp safe to use?: io.github.radoxtech/deepseek-search-everywhere-mcp has no known CVEs as of the latest MCPpedia security scan. It requires authentication to connect, which limits unauthorized access. Licensed under MIT.
How do I install io.github.radoxtech/deepseek-search-everywhere-mcp?: io.github.radoxtech/deepseek-search-everywhere-mcp supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What AI clients work with io.github.radoxtech/deepseek-search-everywhere-mcp?: io.github.radoxtech/deepseek-search-everywhere-mcp is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.
Is io.github.radoxtech/deepseek-search-everywhere-mcp actively maintained?: io.github.radoxtech/deepseek-search-everywhere-mcp is actively maintained - last commit was 1 day ago.

Similar servers

Others in ai-ml / search

View all →

Crw95

Open-source web scraper for AI agents with scrape, crawl, and map tools

1.3k 3

Vibe Assistant95

A cross-platform desktop application for managing AI Agents and MCP Servers. 一款用于管理AI智能体与MCP服务器的跨平台桌面应用程序。

169 3

Codebase Memory Mcp95

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

48.6k 6

Gemini Cli95

An open-source AI agent that brings the power of Gemini directly into your terminal.

108.8k 8

MCP Security Weekly

Get CVE alerts and security updates for io.github.radoxtech/deepseek-search-everywhere-mcp and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

{ "mcpServers": { "deepseek-search-everywhere": { "env": { "DEEPSEEK_API_KEY": "sk-..." }, "args": [ "deepseek-search-everywhere-mcp" ], "command": "uvx" } } }

DeepSeek Search Everywhere MCP

DeepSeek Search Everywhere is a Model Context Protocol (MCP) server that gives AI agents web search, page fetch (web scraping to clean Markdown), structured data extraction and deep research with numbered citations, all through the DeepSeek Search & Fetch API. It runs over stdio or authenticated HTTP and works with Claude Code, Claude Desktop, Cursor, Cline, Windsurf, Zed, OpenCode and any other MCP client.

You need one credential, a DeepSeek API key, and you pay DeepSeek directly per request: there is no separate subscription. It is an alternative to Tavily, Perplexity, Firecrawl and Exa for agents that need live web access, and about 10x cheaper than Tavily for basic search; see Comparison for the numbers.

Not affiliated with DeepSeek. This is an independent, community-maintained project.

Key features

Web search with snippets or full page text, domain and date filters, language selection and optional query rewrite.

Page fetch to Markdown for one URL or up to 10 in parallel, with section, snippet, offset and find-text selectors for long pages.

Structured extraction: pull named fields or a JSON schema from a page; each value must be backed by a verbatim quote from the page or it is returned as null.

Deep research with citations: four depth tiers (low, medium, high, max) produce a report with [n] citations that map to a sources array. Long runs continue in the background and are collected with deepseek_check_research.

Cost reporting: every response carries cost_usd and, where an LLM is involved, cost_breakdown; an optional daily budget blocks overspending.

Hardened against prompt injection: hidden Unicode stripped, markdown images and unsafe links neutralized, an egress guard for secret-like data, static SSRF filtering and no telemetry. See Security.

Small footprint: pure Python, no local browser, uvx zero-install, 9 tools.

Frequently Asked Questions

Is io.github.radoxtech/deepseek-search-everywhere-mcp safe to use?

io.github.radoxtech/deepseek-search-everywhere-mcp has no known CVEs as of the latest MCPpedia security scan. It requires authentication to connect, which limits unauthorized access. Licensed under MIT.

How do I install io.github.radoxtech/deepseek-search-everywhere-mcp?

io.github.radoxtech/deepseek-search-everywhere-mcp supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.

What AI clients work with io.github.radoxtech/deepseek-search-everywhere-mcp?

io.github.radoxtech/deepseek-search-everywhere-mcp is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.

Is io.github.radoxtech/deepseek-search-everywhere-mcp actively maintained?

io.github.radoxtech/deepseek-search-everywhere-mcp is actively maintained - last commit was 1 day ago.