dsh-mcp-firecrawl
by PyModel
Firecrawl MCP 桥接:托管 Firecrawl MCP server 的免 key 搜索、抓取与解析;填 API key 解锁含 crawl 与 map 的完整工具面
Firecrawl MCP bridge: hosted Firecrawl MCP server with keyless search, scrape and parse; an API key unlocks the full tool surface including crawl and map.
安装
dsh plugin --profile web add github:PyModel/dsh-research-plugins#path:/packages/dsh-mcp-firecrawlGitHub 源码安装:首次需按提示配置 allowBuilds 构建授权后重试
安装与环境配置指引、插件开发教程见 DSH 中文社区文档 ↗
安装即在你的机器上以你的权限运行第三方代码——它可读写文件、使用凭据、访问网络,DSH 的工具审批不会为插件代码加沙箱。「检测到 manifest」仅代表发现 dsh.bundle / dsh.plugin 清单,不构成兼容性或安全审查;安装前请审阅源码,不熟悉的插件先在不含密钥的环境试用。
README
Firecrawl MCP for DeepSeek Harness. Connects the official hosted Firecrawl MCP server through the harness's @deepseek-ai/dsh-mcp-client bridge and exposes its tools as mcp__firecrawl__*. Works keyless out of the box (search, scrape, parse within daily limits); a Firecrawl API key unlocks the full tool surface — scrape, crawl, map, and more.
Install
dsh plugin --profile web add dsh-mcp-firecrawl
dsh web
Or follow GitHub (latest commit):
dsh plugin --profile web add github:pymodel/dsh-research-plugins#path:packages/dsh-mcp-firecrawl
API key (optional)
Keyless needs no setup: the row is always enabled and starts with firecrawl_search, firecrawl_scrape, and firecrawl_parse at daily keyless limits.
For the full tool surface and higher limits, get a Firecrawl API key at firecrawl.dev (format fc-...) and make it visible to the launch environment in one of:
export FIRECRAWL_API_KEY=fc-...
or a project .env / $DSH_HOME/.env:
FIRECRAWL_API_KEY=fc-...
The key goes into the Authorization: Bearer header at load time — never into the MCP URL and never into YAML. A key added to .env needs a dsh web restart.
Tools
After connecting, the model sees the Firecrawl tools under the firecrawl namespace: mcp__firecrawl__firecrawl_search, mcp__firecrawl__firecrawl_scrape, and mcp__firecrawl__firecrawl_parse keyless, plus the full surface such as mcp__firecrawl__firecrawl_crawl and mcp__firecrawl__firecrawl_map once an API key is set.
Remove
dsh plugin --profile web remove dsh-mcp-firecrawl
Do not commit real keys. If you already run your own Firecrawl MCP row, remove it first to avoid a duplicate serverName conflict.
原始 README: https://github.com/PyModel/dsh-research-plugins/blob/main/packages/dsh-mcp-firecrawl/README.md ↗
同类插件
查看全部 →
agent-vision-toolkit
为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode

api-relay-audit
从 DeepSeek Harness 对 AI API 中转站和 LLM 代理运行本地安全审计,生成 Markdown 报告,覆盖提示词注入、模型替换信号、工具调用改写、错误泄漏、流完整性和按 profile 启用的 Web3 风险。

OpenStory
✨ OpenStory 现已支持 DeepSeek Harness 插件! 现在可以通过 dsh-openstory 将 OpenStory 多智能体推演接入 DeepSeek Harness,让 agent 直接启动模拟、查看角色、下达指令并逐回合推进故事。查看 DSH 插件配置与使用指南。

phi
pi的编码代理 ∞ 提供者、子代理、hashline编辑和权限门

anysearch-dsh
DeepSeek Harness(DSH)的 AnySearch 网络搜索提供方与高级搜索工具。

codex-switch
Codex Switch 是一个 macOS 工具,一键配置 Codex 的自定义 API,同时保留官方 OpenAI 登录。保存后 Codex 的模型选择器里只会出现你选的那个 provider 的模型。也支持 Claude Code 的官方 / 自定义 API 切换。Codex Switch is a lightweight helper for configuring multiple coding-agent API routes. For Codex, it keeps Official OpenAI and a custom API provider configured in parallel, registers the custom model in Codex's mod