F
licenseNot graded
qualityD
maintenanceWraps the Kimi Coding Search and Fetch APIs into MCP tools for web searching and content retrieval. It enables LLMs to perform targeted searches and crawl web pages using standardized interfaces.
1
-
kimi-search-mcp
by SqrtLeaves
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., "@kimi-search-mcp今天有什么科技新闻？"
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.
Kimi Code + MiniMax Web Search MCP Server
让本地 Kimi Code 调用 MiniMax 原生的 web_search Server Tool 实现联网搜索。
背景
Kimi Code 内置的 WebSearch 工具只能接 Moonshot/Kimi 的搜索服务（services.moonshot_search），无法直接复用 MiniMax 的模型侧搜索能力。MiniMax 的 web_search 是一个 Server Tool，只有直接调用 MiniMax 的 Anthropic Messages API 并传入 tools: [{"type": "web_search_20250305", "name": "web_search"}] 时才会触发。
本项目作为一个 MCP Server，把 MiniMax 的联网搜索能力桥接到 Kimi Code，让 Agent 可以通过 mcp__minimax-web-search__web_search 工具进行搜索。
Related MCP server: MiniMax Search MCP Server
目录结构
kimi-minimax-websearch-mcp/
├── minimax_web_search.py # MCP Server 主脚本
├── requirements.txt # Python 依赖
├── mcp.json.example # Kimi Code MCP 配置示例
├── .gitignore # 忽略 venv 和 minimax_key
└── README.md # 本文件前置条件
Python 3.10+
一个有效的 MiniMax API key
已安装并配置好 Kimi Code CLI
安装步骤
1. 克隆/复制本文件夹到目标电脑
例如放到：
~/tools/kimi-minimax-websearch-mcp2. 创建虚拟环境并安装依赖
cd ~/tools/kimi-minimax-websearch-mcp
python -m venv .venv
.venv/bin/pip install -r requirements.txtWindows 上 Python 路径为
.venv\\Scripts\\python.exe。
3. 放入 MiniMax API Key
在本文件夹根目录创建一个 minimax_key 文件，把 key 放进去（不要引号、不要空行）：
echo 'sk-你的-minimax-key' > minimax_key或者设置环境变量：
export MINIMAX_API_KEY='sk-你的-minimax-key'脚本会按以下优先级读取：
MINIMAX_API_KEY环境变量本文件夹下的
minimax_key文件运行时的当前工作目录下的
minimax_key文件
minimax_key 已被 .gitignore 忽略，不会误提交。
4. 配置 Kimi Code
把 mcp.json.example 复制为 ~/.kimi-code/mcp.json（如果已有该文件，则合并 mcpServers 部分），并把里面的路径改成你本机的绝对路径。
{
"mcpServers": {
"minimax-web-search": {
"command": "/Users/你的用户名/tools/kimi-minimax-websearch-mcp/.venv/bin/python",
"args": [
"/Users/你的用户名/tools/kimi-minimax-websearch-mcp/minimax_web_search.py"
],
"cwd": "/Users/你的用户名/tools/kimi-minimax-websearch-mcp",
"env": {
"MINIMAX_MODEL": "MiniMax-M3"
}
}
}
}参数说明：
command：虚拟环境中的 Python 解释器绝对路径。args：MCP Server 脚本的绝对路径。cwd：本文件夹的绝对路径，确保minimax_key能被找到。env.MINIMAX_MODEL：触发搜索时使用的 MiniMax 模型，默认MiniMax-M3，可改为MiniMax-M2.5等。
5. 添加权限规则（可选但推荐）
在 ~/.kimi-code/config.toml 末尾追加：
[[permission.rules]]
decision = "allow"
pattern = "mcp__minimax-web-search__*"
scope = "user"
reason = "Allow MiniMax native web search MCP tool"这样每次搜索不会弹 approval 确认。
6. 重启 Kimi Code
MCP Server 只在 Kimi Code 启动时加载。退出并重新进入 TUI，或在 TUI 里执行：
/reload然后执行：
/mcp应能看到 minimax-web-search 已连接，工具列表里有 web_search。
使用
在 Kimi Code 中直接问需要联网的问题即可，例如：
今天有什么科技新闻？Agent 会自动调用 mcp__minimax-web-search__web_search，返回答案和来源。
故障排查
/mcp 里看不到 minimax-web-search
确认
~/.kimi-code/mcp.json路径是否正确且为绝对路径。确认
minimax_key存在且有效。在终端手动运行：
/你的路径/.venv/bin/python /你的路径/minimax_web_search.py如果没有报错并显示 FastMCP 启动信息，说明脚本本身正常。
调用搜索时报 401/403
检查
minimax_key是否有效、是否有多余空格或换行。检查该 key 是否有权限调用 MiniMax Anthropic Messages API。
搜索没有返回结果
MiniMax 的
web_search是模型自主决定的 Server Tool，某些问题可能不会触发搜索。换更明确的查询词再试。检查
env.MINIMAX_MODEL是否填写正确。
迁移到另一台电脑
复制整个
kimi-minimax-websearch-mcp文件夹。在新电脑上执行「安装步骤」的 2~5 步。
重启 Kimi Code。
许可证
按项目现有约定使用。
This server cannot be deployed
Maintenance
ActivitySlowing
ResponsivenessNo issues
Related MCP Connectors
Docs: https://docs.keenable.ai/mcp-server Keenable is a free, remote MCP server that gives agents access to the web index. Search the web with ranked results and date/site filters, then fetch any indexed page as clean markdown. Works out of the box with no account or API key.
Web search, scraping, RAG answers with citations, and translation as MCP tools.
Live AI-native web search with citations. One tool for every MCP client. Flat per-request pricing.
Your agent needs the open web — searched by more than one engine, and read as clean markdown rather than raw HTML. **What you can ask for** • "Search this question with two providers and tell me where they disagree." • "Scrape these 40 URLs into markdown, in one batch." • "Crawl this documentation site and give me every page." • "Do deep research on this topic and cite the sources." • "Find the academic papers behind this claim." **How to use it** Point any MCP client at https://mcp.aisa.one/search/mcp and sign in with OAuth — there is no key to create or paste. 30 tools across several independent providers: Tavily and Exa search, answers, contents and agent runs; Firecrawl scrape, batch scrape, crawl, map and search; Perplexity Sonar, Sonar Pro, reasoning and deep research; Oxylabs AI search and LLM jobs; OpenAI and Anthropic web search; and scholarly search. **Why this rather than the source** Several independent indexes behind one account, because one engine's blind spot is not visible from inside it. **It is also a door to the rest** The same login reaches 26 sources and 580+ operations. Find the page here, then ask the same agent who links to it or how much traffic it gets — without adding a second server. **What it costs** Finding and inspecting an operation is free. Running one is billed per call at API prices, with no seat and no monthly minimum, and every call takes max_price_usd so an agent cannot overspend by accident. **Where else it reaches** https://mcp.aisa.one/seo-serp/mcp for the Google results page itself, https://mcp.aisa.one/seo-serp-other-engines/mcp for Bing, Baidu and Naver.
Related MCP Servers
- FlicenseAqualityFmaintenanceMCP server enabling parallel web search and batch browsing with intelligent content understanding via MiniMax LLM.257-
- AlicenseAqualityDmaintenanceMCP server that bridges OpenAI's Agents SDK with Claude Code, enabling web search, file search, and computer use capabilities directly in your development environment.29 npm1MIT
- AlicenseCqualityDmaintenanceMCP server integrating the Kagi Search API to perform web searches using the kagi_search tool.1MIT
