SkillAgentSearch skills...

SearXNG-MCP

一个基于 FastMCP 实现的 SearXNG 搜索 MCP 服务

Install / Use

claude mcp add muzihuaner -- npx -y github:muzihuaner/SearXNG-MCP

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

71/100

Supported Platforms

Claude Code
Claude Desktop

Tags

Our assessment of SearXNG-MCP

SearXNG-MCP scores 71/100 on our quality scale, 3819th of 4,658 Development & Engineering skills we index.

Its MCP Server is 2.6 KB long, well organised into 16 sections with 10 code examples: a solid amount of guidance for an agent.

It has 3 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
26/30
Structure
20/20
Description
8/15
Adoption
3/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so SearXNG-MCP is actively maintained.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 87/100, with 2 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

SearXNG-MCP compared with similar skills

All 4 of these similar skills score higher than SearXNG-MCP; compare them before choosing.

SkillScoreStarsUpdatedFormat
SearXNG-MCP (this skill)by muzihuaner7132mo agoMCP Server
Agent-Reachby Panniantong100106.6k5d agoCLAUDE.md
taste-skillby Leonxlnx100106.0ktodayCLAUDE.md
headroomby headroomlabs-ai10078.3ktodayCLAUDE.md
ai-job-searchby ai-job-search-dev10067.6k3d agoCLAUDE.md

Frequently asked questions

How do I install SearXNG-MCP?
Run claude mcp add muzihuaner -- npx -y github:muzihuaner/SearXNG-MCP. The install tabs above show the steps for each supported agent.
Which AI agents does SearXNG-MCP work with?
It is written for Claude Code and Claude Desktop, as a MCP Server file. Other agents that read the same format can often use it too.
Is SearXNG-MCP safe to use?
It is MIT-licensed and scores 87/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is SearXNG-MCP still maintained?
The repository was last updated about 2 months ago, so SearXNG-MCP is actively maintained.

SearXNG MCP Server

一个基于 FastMCP 实现的 SearXNG 搜索 MCP 服务,使用 Streamable HTTP 传输,支持本地运行与 Docker 部署。

SearXNG相关链接:

官方文档:https://docs.searxng.org/

在线示例:https://searx.space/

功能

  • 暴露 MCP 工具 search(query):根据关键字调用 SearXNG 实例并返回搜索结果摘要。
  • 通过 HTTP 端点 http://<host>:<port>/mcp 提供 MCP 服务,便于远程 / 跨域调用。
  • 采用 无状态(stateless) Streamable HTTP 模式,客户端无需维护 Mcp-Session-Id,可直接并发调用。
  • 支持通过环境变量自定义 SearXNG 实例地址,方便私有化部署。

环境变量

| 变量名 | 默认值 | 说明 | | ------------- | -------------------- | ----------------------------------------------------- | | SEARXNG_URL | https://searxng.abc.com | SearXNG 实例根地址(要求开启JSON) | | HOST | 0.0.0.0 | 服务监听地址 | | PORT | 9000 | 服务监听端口 |

本地运行

# 安装依赖(建议使用虚拟环境)
pip install -r requirements.txt

# 可选:自定义 SearXNG 实例(只需填根地址)
export SEARXNG_URL="https://your-searxng-instance"

# 启动服务
python Server.py

启动后,MCP 端点为:

http://localhost:9000/mcp

Docker 部署

构建镜像

docker build -t searxng-mcp .

运行容器

docker run -d \
  --name searxng-mcp \
  -p 9000:9000 \
  -e SEARXNG_URL="https://searxng.abc.com" \
  searxng-mcp

如需修改端口,可同时覆盖容器内外端口与 PORT:

docker run -d \
  --name searxng-mcp \
  -p 8080:8080 \
  -e PORT=8080 \
  searxng-mcp

使用在线镜像

docker run -d \
  --name searxng-mcp \
  -p 9000:9000 \
  -e SEARXNG_URL="https://searxng.abc.com" \
  muzihuaner/searxng-mcp:latest

访问地址

部署完成后,MCP 端点格式为:

http://<你的服务器域名或IP>:<端口>/mcp

例如:http://localhost:9000/mcp 或 https://mcp.your-domain.com/mcp

客户端配置

在支持 Streamable HTTP 的 MCP 客户端中,将服务地址填写为上面的 /mcp 端点即可,例如:

{
  "mcpServers": {
    "searxng": {
      "url": "http://localhost:9000/mcp"
    }
  }
}

工具说明

search(query: str) -> str

根据关键字调用 SearXNG 搜索,返回各结果条目的 content 文本,以换行拼接。

  • query:搜索关键字。
  • 返回:搜索结果的文本内容;请求失败时返回 False。

并发与性能

测试结果示例(局域网 / 上游 `so.xxx.cn`):

总请求数 : 100 并发 worker : 50 成功 : 100 失败 : 0 总耗时(秒) : 67.68 吞吐(QPS) : 1.48 平均延迟(秒) : 27.284 最小延迟(秒) : 7.203 最大延迟(秒) : 44.418


> 注意:端到端延迟主要取决于 SearXNG 上游实例的响应速度(本例平均约 27s 来自上游 `so.xxx.cn` 较慢),服务本身可稳定承载并发且零失败。若需提升吞吐,可:
> - 换用响应更快 / 自托管的 SearXNG 实例(通过 `SEARXNG_URL` 指定);

常见问题

Q: 客户端报错 Missing session ID? A: 本服务已启用 stateless_http=True,无需 session。若仍报该错,请确认客户端指向的是 /mcp 端点。

Q: 如何在生产环境收紧 CORS? A: 编辑 Server.py 中的 CORSMiddleware,将 allow_origins=["*"] 改为具体来源列表,如 ["https://your-domain.com"]。

Related Skills

View on GitHub
GitHub Stars3
CategoryDevelopment
Updated2mo ago
Forks0

Languages

Python

Trust signals

87/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

2 low
SearXNG-MCP — MCP Server: Install & Safety Check | SkillAgent