DDGS Metasearch via local MCP — DDGS Meta搜索 via local MCP

DDGS 网页 搜索 设置up: 安装 ddgs, 运行 MCP server (SSE), optionally keep it as a daemon

It is recommended to enable built-in mcporter 技能.

安装 the Python package python3 -m pip 安装 -U ddgs

运行 the DDGS MCP server (SSE)

Foreground (good for 调试ging):

ddgs API --host 127.0.0.1 --port 8000

Detached/background mode (convenient on a dev machine):

ddgs API -d --host 127.0.0.1 --port 8000

停止 the detached server:

ddgs API -s

Optional: 系统d user 服务 (always avAIlable)

创建 ~/.config/系统d/user/ddgs.服务:

[Unit] Description=DDGS MCP SSE server After=network-online.tar获取

[服务] Type=simple Exec启动=%h/.local/bin/ddgs API --host 127.0.0.1 --port 8000 Re启动=on-失败 Re启动Sec=2

[安装] WantedBy=default.tar获取

Then:

系统ctl --user daemon-reload 系统ctl --user enable --now ddgs 系统ctl --user 状态 ddgs --no-pager

添加 the MCP server to mcporter

添加 a named server pointing at the DDGS SSE 端点:

mcporter config 添加 ddgs http://127.0.0.1:8000/sse --allow-http

验证 it shows up:

mcporter config 列出 ddgs

Then you can call 工具s as ddgs.<工具> (examples below).

Key idea:

DDGS 运行s an MCP SSE 端点 at http://127.0.0.1:8000/sse mcporter connects to that 端点 and exposes 工具s like ddgs.搜索_text_搜索_text_post Defaults (use unless user says otherwise) backend="duckduckgo" (most reliable) max_结果s=10 (“SERP page 1”) region="us-en", safe搜索="moderate" 工作流 0) Preconditions / sanity Confirm DDGS server is up: curl -s http://127.0.0.1:8000/健康 Confirm mcporter can see the server: mcporter config 列出 ddgs

If the server is down, either:

启动/恢复 it (if you have 权限), or use fallback (网页_搜索). 1) Execution examples

Use mcporter to call DDGS 工具s and 解析 JSON.

Text 搜索:

mcporter call ddgs.搜索_text_搜索_text_post \ 查询="<查询>" max_结果s=10 backend="duckduckgo" region="us-en" safe搜索="moderate" --json

News 搜索:

mcporter call ddgs.搜索_news_搜索_news_post \ 查询="<查询>" max_结果s=10 backend="bing" timelimit="w" --json

Images:

mcporter call ddgs.搜索_images_搜索_images_post \ 查询="<查询>" max_结果s=10 backend="duckduckgo" region="us-en" safe搜索="moderate" --json

Videos:

mcporter call ddgs.搜索_videos_搜索_videos_post \ 查询="<查询>" max_结果s=10 backend="duckduckgo" region="us-en" safe搜索="moderate" --json

Books:

mcporter call ddgs.搜索_books_搜索_books_post \ 查询="<查询>" max_结果s=10 backend="annas归档" --json

AvAIlable 工具s (via mcporter) ddgs.搜索_text_搜索_text_post ddgs.搜索_images_搜索_images_post ddgs.搜索_news_搜索_news_post ddgs.搜索_videos_搜索_videos_post ddgs.搜索_books_搜索_books_post 工具 parameters

Common parameters (most 端点s):

查询 — the 搜索 string. max_结果s — cap 结果s; default 10 (fast, “page 1”). backend — engine selector. Prefer duckduckgo for reliability; bing as second choice; avoid google on servers (403/captcha risk) region — locale for 结果s (e.g. us-en, uk-uk). safe搜索 — content 过滤器ing (off|moderate|strict); default moderate.

News-specific:

timelimit — recency 过滤器 (commonly d, w, m, y).

Books-specific:

recommended backend is annas归档.

Tip: when you need reproducibility, explicitly pass backend, region, safe搜索, max_结果s even if they match defaults.

Troubleshooting

mcporter says server not found → you’re using a different config file; if you use a non-default config, pass --config path from your 系统 (default is ~/.OpenClaw/workspace/config/mcporter.json).

backend="google" often returns HTTP 403 in server 环境s → use another backend, e.g. duckduckgo/bing.

Full API docs avAIlable locally at http://localhost:8000/docs.