Ferris search setup

Skill lispking/ferris-search/skills/ferris-search-setup

CRITICAL: Use for ferris-search installation and configuration. Triggers on: ferris-search install, mcp add ferris-search, setup ferris-search, DEFAULT_SEARCH_ENGINE, ALLOWED_SEARCH_ENGINES, BRAVE_API_KEY, EXA_API_KEY, FIRECRAWL_API_KEY, JINA_API_KEY, TAVILY_API_KEY, USE_PROXY, ferris-search config, ferris-search build, ferris-search Docker, 安装ferris-search, 配置搜索引擎, MCP服务器配置, 代理设置From its SKILL.md

Install

npx -y skills add lispking/ferris-search --skill ferris-search-setup

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

3.7 KB, as published. Nobody here has run it

ferris-search Setup & Configuration Skill

Version: ferris-search 0.1.0 | Last Updated: 2026-03-30

You are an expert at installing and configuring the ferris-search MCP server. Help users by:

Setup: Guide through build, install, and MCP registration
Configuration: Explain env vars and their effects

Documentation

Refer to the local files for detailed documentation:

./references/configuration.md - All environment variables and their effects

IMPORTANT: Documentation Completeness Check

Before answering questions, Claude MUST:

Read ./references/configuration.md
If file read fails: still answer based on SKILL.md patterns

Key Patterns

Build & register with Claude Code

cargo build --release
claude mcp add ferris-search ./target/release/ferris-search

With environment variables

claude mcp add ferris-search ./target/release/ferris-search \
  -e DEFAULT_SEARCH_ENGINE=bing \
  -e ALLOWED_SEARCH_ENGINES=bing,duckduckgo,brave

Claude Desktop / Cursor (mcp-config.json)

{
  "mcpServers": {
    "ferris-search": {
      "command": "/path/to/ferris-search",
      "env": {
        "DEFAULT_SEARCH_ENGINE": "bing",
        "ALLOWED_SEARCH_ENGINES": "bing,duckduckgo,brave,baidu",
        "EXA_API_KEY": "your-key-here"
      }
    }
  }
}

With proxy

claude mcp add ferris-search ./target/release/ferris-search \
  -e USE_PROXY=true \
  -e PROXY_URL=http://127.0.0.1:7890

Docker

docker build -t ferris-search .
docker run -e DEFAULT_SEARCH_ENGINE=bing ferris-search

Configuration Reference

Env Var	Default	Description
`DEFAULT_SEARCH_ENGINE`	`bing`	Engine used when `engines` param is omitted
`ALLOWED_SEARCH_ENGINES`	all 14 engines	Comma-separated allow-list
`BRAVE_API_KEY`	—	Required only for `brave` engine
`EXA_API_KEY`	—	Required only for `exa` engine
`FIRECRAWL_API_KEY`	—	Required only for `firecrawl` engine
`JINA_API_KEY`	—	Required only for `jina` engine
`TAVILY_API_KEY`	—	Required only for `tavily` engine
`GITHUB_TOKEN`	—	Optional for `github`/`github_code` engines (60→5000 req/hr)
`USE_PROXY`	`false`	Enable HTTP/SOCKS5 proxy
`PROXY_URL`	`http://127.0.0.1:7890`	Proxy address
`ENABLE_HTTP_SERVER`	`false`	Enable HTTP/SSE transport alongside stdio
`MODE`	`stdio`	Transport mode: `stdio`, `http`, or `both`
`RUST_LOG`	`info`	Log level: `debug`, `info`, `warn`, `error`

When Writing Code

Always build with --release for production use (~8 MB binary, <10 ms startup)
Set ALLOWED_SEARCH_ENGINES to only the engines you need — reduces attack surface
Never commit EXA_API_KEY, FIRECRAWL_API_KEY, JINA_API_KEY, TAVILY_API_KEY, BRAVE_API_KEY, or GITHUB_TOKEN to source control — use env var injection
For Chinese content workflows, include baidu, csdn, juejin, zhihu in allow-list

When Answering Questions

claude mcp add is the recommended path for Claude Code users
JSON config is needed for Claude Desktop / Cursor
Proxy support works for all engines including those behind GFW
ALLOWED_SEARCH_ENGINES acts as an allow-list — engines not listed are silently filtered out