deepseek-search-mcp
Click 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., "@deepseek-search-mcp 搜 2026 年新发布的 MCP 服务器,用 site:github.com,并抓取第一个的 README"
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.
deepseek-search-mcp
把 DeepSeek 2026-10-17 开放的自研搜索引擎(Search / Fetch API)接进 Claude Code、Codex、Cursor 等任何支持 MCP 的 AI 工具。
为什么用它
我们在 2026-10-19 拿 27 个真实查询,对比了它和 Claude Code 内置的 WebSearch(方法和局限见 docs/benchmarks.md):
场景 | DeepSeek | 内置 WebSearch |
中文检索(12 题,满分 10/题) | 88 分 | 60 分 |
英文 / 技术 / GitHub 找轮子(15 题平均) | 7.5 | 5.2 |
近期动态(10 月新发布) | 能命中官方原文 | 索引停在 9 月 |
政策制度类、英文临床指南、经典论文 | 偏弱 | 更好 |
结论:中文、开源项目、近期动态用它更好;政策和英文经典文献建议与内置搜索交叉使用。
Related MCP server: svipall
和同类封装的区别
本项目 | |
防误扣费 | 每日 / 每月调用上限(默认 500 / 5000 次),多个会话共享计数;超时等“可能已计费”的请求保守计入 |
防提示注入 | 网页内容放在每次随机生成的围栏里并标为不可信;网页里伪造的围栏、结果条目会被中和 |
输出可控 | 单次输出硬上限 2 万字符,不会撑爆模型上下文;同一网页的分块结果合并去重 |
结果清洗 | 默认过滤 book118 / 人人文库 / 豆丁 / 道客巴巴 / 百度文库等转卖文档站;修复 Fetch 正文的反斜杠转义 |
稳定性 | 只对超时、网络错误、408/429/5xx 重试;遵守 Retry-After;总时限是硬上限;格式异常的响应不会让工具崩溃 |
已知限制提前告知 | 知乎 / 小红书 / X / Wikipedia / PDF 等 Fetch 抓不了的站点,直接提示改用别的工具,不白花钱 |
质量 | 97 个自动测试,CI 覆盖 Linux / macOS / Windows;两轮独立代码审查 |
安装
需要 uv 和一个 DeepSeek API key。如果你的环境只有 uv 没有 uvx,把下面的 uvx 换成 uv tool run。
Claude Code
claude mcp add -s user deepseek-search -e DEEPSEEK_API_KEY=sk-你的key -- uvx --from git+https://github.com/Taosheng777/deepseek-search-mcp deepseek-search-mcpCodex(~/.codex/config.toml)
[mcp_servers.deepseek-search]
command = "uvx"
args = ["--from", "git+https://github.com/Taosheng777/deepseek-search-mcp", "deepseek-search-mcp"]
env = { DEEPSEEK_API_KEY = "sk-你的key" }Cursor / Claude Desktop / 其他 MCP 客户端
{
"mcpServers": {
"deepseek-search": {
"command": "uvx",
"args": ["--from", "git+https://github.com/Taosheng777/deepseek-search-mcp", "deepseek-search-mcp"],
"env": { "DEEPSEEK_API_KEY": "sk-你的key" }
}
}
}macOS 更安全的做法:不把 key 写进配置文件,而是存进钥匙串,配置里去掉 DEEPSEEK_API_KEY 即可:
security add-generic-password -U -a "$USER" -s deepseek-api-key -w sk-你的key工具
工具 | 作用 | 费用 |
| 搜索网页。支持 | 每次 0.005 元,与条数无关 |
| 抓取单个网页为 Markdown,长页面分页读取(15 分钟内翻页不重复计费) | 每次 0.005 元 |
| 查看本机调用次数和估算花费 | 免费 |
实用写法:中文检索加 lang:zh;找开源项目加 site:github.com;include_content=true 一次拿到正文,比逐条抓取省钱。
配置
环境变量 | 默认 | 说明 |
| — | 未设置时在 macOS 上读取钥匙串服务 |
| 500 | 每日计费调用上限(约 2.5 元) |
| 5000 | 每月计费调用上限(约 25 元) |
|
| 用量计数文件位置 |
注意
查询词和网址会发送给 DeepSeek;DeepSeek 文档未说明数据留存政策。
不建议把
deepseek_fetch加入客户端的“免确认”列表:网页内容可能诱导模型去抓取带敏感参数的网址。搜索结果只是线索。医学、法律等专业结论请回原始来源核对。
本项目与 DeepSeek 官方无关。
开发
uv sync
uv run pytest -qEnglish
An MCP server for DeepSeek's self-built web search engine (Search / Fetch API, opened 2026-10-17). Works with Claude Code, Codex, Cursor and any MCP client.
Why: in our 27-query comparison against Claude Code's built-in WebSearch (2026-10-19, see benchmarks), DeepSeek scored 88 vs 60 on Chinese queries and 7.5 vs 5.2 (per-query average) on English / technical / GitHub queries. It is weaker on policy documents, English clinical guidelines and classic papers — cross-check those with your client's built-in search.
What's different: spend caps shared across sessions (conservative accounting for timed-out calls), per-call random fences against prompt injection from web content, a hard 20k-character output cap, de-duplication and doc-farm filtering, retries only where they are safe, upfront hints for sites DeepSeek Fetch cannot read, 97 tests with CI on Linux / macOS / Windows.
Install (Claude Code):
claude mcp add -s user deepseek-search -e DEEPSEEK_API_KEY=sk-... -- uvx --from git+https://github.com/Taosheng777/deepseek-search-mcp deepseek-search-mcpTools: deepseek_search, deepseek_fetch, deepseek_usage. Pricing: CNY 0.005 per successful call. Tool messages are in Chinese; models read them fine. Not affiliated with DeepSeek.
License: MIT
Available Tools
3 toolsdeepseek_fetchARead-only
Fetch one web page as Markdown via DeepSeek. 用 DeepSeek 抓取单个网页,返回 Markdown 正文。按次计费(每次 0.005 元),同一网址 15 分钟内翻页不重复计费。
不支持本机、内网、带账号密码的网址。长网页分页读取,返回末尾会提示下一页的 start_index。
正文不含超链接和图片;需要链接或图片时用客户端自带的网页抓取工具。
知乎/小红书/X、Wikipedia、GitHub raw、PDF、NEJM/Lancet 会直接提示改用的工具(不发请求、不计费)。
Inputs: url (required), max_chars, start_index.
deepseek_searchARead-only
Search the web with DeepSeek's own search engine. 用 DeepSeek 自研搜索引擎搜索网页。按次计费(每次 0.005 元,与 count 无关)。
query 支持语法:site:github.com(多个用 OR 连接)、-site:x.com、"精确短语"(弱约束)、
-关键词、lang:zh 或 lang:en、after:2026-01-01、before:2026。
实用写法:中文检索加 lang:zh 防混入外文;找轮子加 site:github.com;找经验可加 -site:edu.cn 避开高校新闻稿。
include_content:同时返回正文,比逐条 fetch 省钱省时;总输出约 2 万字,条数越多每条正文越短,建议 count≤10。
exclude_doc_farms:默认过滤 book118/人人文库/豆丁/道客巴巴/百度文库等转卖文档站。
结果顺序沿用 DeepSeek 排序;score 与 authority 只作参考,不代表内容可靠。缺日期的结果标为"日期未知"。
Inputs: query (required), count, include_content, exclude_doc_farms.
deepseek_usageARead-only
查看本机 DeepSeek 搜索/抓取的计费调用次数、估算花费和防误扣上限。
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
The three tools cover clearly distinct purposes: cost/quota inspection (deepseek_usage), web search (deepseek_search), and single-page retrieval (deepseek_fetch). An agent can unambiguously select the right tool for each task.
All tools share the deepseek_ prefix, giving a predictable namespace. The suffixes mix verbs (search, fetch) with a noun (usage), a minor deviation, but overall it reads consistently.
Three tools is well-scoped for a search/retrieval server, and each earns its place: one to search, one to fetch, one to monitor billing. No redundant or filler tools.
The surface fully covers the search lifecycle: discovery via search, content retrieval via fetch with pagination hints, and cost control via usage. No obvious gaps for the stated purpose.
Maintenance
Related MCP Connectors
Live AI-native web search with citations. One tool for every MCP client. Flat per-request pricing.
Free web search for AI agents. No API key required. Hosted MCP in active development.
Web search API and MCP server for developers building AI agents.
A hosted MCP suite providing workflow primitives: web search, content fetching, compression, deduplication, cost/budget management, and agent memory pipelines.
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceMCP server enabling local-first web search, fetch, extract, and caching with citeable excerpts, no API key required. Supports research workflows for agents and apps.96 npm1MIT
- AlicenseAqualityBmaintenanceA local-first MCP server that lets AI agents read any webpage as clean Markdown, crawl whole sites within configured limits, search without API keys, and solve supported captchas locally — all without cloud services or third-party keys.1221AGPL 3.0
- AlicenseAqualityCmaintenanceGives MCP-capable agents live web access: search the web, scrape pages into Markdown (including JavaScript-heavy and bot-protected sites), and extract named fields as JSON, with job polling, token-aware content offloading, and built-in research guidance. Ships as a self-hostable stdio or HTTP service with spend caps and per-request key support.7MIT
- AlicenseBqualityBmaintenanceEnables AI coding assistants to perform real-time web searches for technical documentation and deep-fetch web pages, returning clean structured results. It supports integration with MCP clients such as Cursor, Claude, and CodeBuddy.3194 npm1MIT