dsh-research-plugins
其他 活跃维护

dsh-research-plugins

PyModel/dsh-research-plugins

pnpm monorepo架构构建,提供网页搜索与MCP协议桥接能力,可快速集成至AI研究工具链,支持网页抓取、实时内容获取等操作,开箱即用。

1
Stars 标星
0
Forks 分支
1
Watchers 关注
0
Open Issues
JavaScript
主要语言
MIT
开源协议
71 KB
仓库大小
1 个月前
最后推送
一键安装扩展 / 插件指令
dsh plugin --profile web add github:PyModel/dsh-research-plugins
git clone https://github.com/PyModel/dsh-research-plugins.git
git clone git@github.com:PyModel/dsh-research-plugins.git
README.md main

dsh-research-plugins

Research plugins for DeepSeek Harness — a pnpm monorepo adding web search and MCP (Model Context Protocol) bridges for AI research, web scraping, and live documentation to your DSH agent.

GitHub stars GitHub forks @pymodel/dsh-tavily on npm dsh-mcp-firecrawl on npm dsh-mcp-context7 on npm MIT license visitors

What this is · Install · API keys · Repo layout · License


What this is

dsh-research-plugins gives your DeepSeek Harness (DSH) agent three research superpowers it does not have out of the box:

  • Web search via the Tavily Search API — a settings toggle that swaps the built-in DeepSeek search for Tavily, with keyless search support.
  • Web scraping & crawling via the Firecrawl MCP server — scrape, crawl, map, and search the open web inside tool calls.
  • Up-to-date library docs via the Context7 MCP server — on-demand documentation and code examples for any library or framework.

Everything is delivered as drop-in DSH plugins — no vendor lock-in, no forks, just a dsh plugin add away.

Package What it adds
@pymodel/dsh-tavily Tavily Search API as a web search provider (settings toggle, keyless search) + a Tavily MCP bridge (tavily-search / tavily-extract keyless; crawl / map with a key)
dsh-mcp-firecrawl Firecrawl MCP: keyless search / scrape / parse; full tool surface with an API key
dsh-mcp-context7 Context7 MCP: mcp__context7__* up-to-date library docs and code examples

Install

Each package installs independently into a DSH profile:

dsh plugin --profile web add @pymodel/dsh-tavily
dsh plugin --profile web add dsh-mcp-firecrawl
dsh plugin --profile web add dsh-mcp-context7
dsh web

Or follow GitHub (this repo, latest commits):

dsh plugin --profile web add github:PyModel/dsh-research-plugins#path:packages/dsh-tavily
dsh plugin --profile web add github:PyModel/dsh-research-plugins#path:packages/dsh-mcp-firecrawl
dsh plugin --profile web add github:PyModel/dsh-research-plugins#path:packages/dsh-mcp-context7

API keys

The MCP bridges use the harness's shipped @deepseek-ai/dsh-mcp-client. They read keys from the launch environment (a real env var, the project .env, or $DSH_HOME/.env) — not from $DSH_HOME/.credentials.yaml:

Plugin Env var Required Endpoint
dsh-tavily (MCP part) TAVILY_API_KEY no (keyless MCP: search + extract; crawl/map need a key) https://mcp.tavily.com/mcp/
dsh-mcp-firecrawl FIRECRAWL_API_KEY no (keyless: search/scrape/parse; full surface with a key) https://mcp.firecrawl.dev/v2/mcp
dsh-mcp-context7 CONTEXT7_API_KEY no (keyless works) https://mcp.context7.com/mcp

Keys are sent as an Authorization: Bearer header at load time — never in the URL and never in plain YAML. Without a key the bridges run in each vendor's documented keyless mode (X-Tavily-Access-Mode: keyless for Tavily), so every row works out of the box. A key added to .env needs a dsh web restart.


Repo layout

packages/
  dsh-tavily/          # web-search provider + settings card + Tavily MCP row
  dsh-mcp-firecrawl/   # pure-config Firecrawl MCP bundle
  dsh-mcp-context7/    # pure-config Context7 MCP bundle

The Firecrawl and Context7 packages are pure-config bundles (package.json + cordis.patch.yml) with no build step. The Tavily package keeps its prebuilt lib/ and browser client.


Contributing

Issues and pull requests are welcome. Please open a discussion on GitHub before starting large changes.


Author

elkaix · pymodel


License

MIT © elkaix