Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

17 plugins found

Y

aginxbrowser

yinnho/aginxbrowser

aginxbrowser plugin for DeepSeek Harness: fetch JS-rendered / Cloudflare-protected pages as clean markdown, aggregated web search (Baidu/Sogou/WeChat and 11 more), and indexed interactive sessions (click / type / scroll / eval / screenshot) against a host

272 months agoTools & CapabilitiesApache-2.0
2

dsh-read-url

2672243194/dsh-read-url

Read any page as clean main content: charset auto-detect (GBK/GB2312/UTF-8/Big5), noise stripping, compact text/Markdown, offset continuation, optional SPA rendering, batch reads and site crawling.

2416 hours agoTools & CapabilitiesMIT
M

deepspider

ma-pony/deepspider

AI 原生智能爬虫与 JavaScript 逆向工程平台,基于 DSH、Patchright/CDP 与独立语义运行时,从浏览器证据恢复参数生成逻辑并交付可验证 Solver。

183 months agoTools & Capabilities
Q

dsh-squeeze

q8atnight/dsh-squeeze

Adds a squeeze tool: the agent hands a long web page, a batch of pages, a text file or a text PDF (via pdftotext) plus one question to a helper model and gets back only the answer, so the material never enters the chat. A settings page picks up to three helper models from the DSH model list, each with a nickname, a fixed thinking level and a "when to use" note, with optional fallback and size limits taken from each model's context window.

310 days agoTools & CapabilitiesMIT
A

apify-deepseek-harness-plugin

apify/apify-deepseek-harness-plugin

Apify Actors for DeepSeek Harness: adds the Apify MCP server to your profile.

320 days agoMCP & ConnectorsApache-2.0
T

dsh-webfetch

tyeclipse/dsh-webfetch

Web reading tools for text-only agents. Five read-only tools: web_fetch (any URL rendered as clean Markdown or plain text), web_links (inventory of a page's links), web_feed (RSS 2.0 / Atom entries), web_headers (HTTP status, response headers and redirect chain without downloading the body, HEAD with automatic GET fallback), and web_table (HTML tables extracted as structured rows with header detection and colspan/rowspan grid expansion). Transport is Node fetch plus a zero-dependency HTTP proxy implementation (CONNECT tunnelling, absolute-URI requests, NO_PROXY with suffix/wildcard/IPv4-CIDR matching, Proxy-Authorization). Zero runtime dependencies.

319 days agoTools & CapabilitiesMIT
2

image-scout

2039108952x-lab/image-scout

Search Wikimedia Commons and Openverse for real photos, download them, and verify provenance, magic bytes and dimensions before they reach your agent.

29 days agoSkillsMIT
M

dsh-browser-playwright-codex

miqian-nomad/dsh-browser-playwright-codex

Browser automation for DSH: the agent fills in forms, scrapes lists and works across tabs in real pages, using the logins you already have. It drives its own visible window on your desktop — minimise it and it keeps working without stealing focus — and a sign-in, CAPTCHA or native dialog stops the run and hands the page back to you: it never confirms on your behalf. Login state persists (own profile plus session-cookie re-injection). 23 Playwright tools (20 always on, 3 gated and off by default), with a URL allowlist, dialog suspension and a CDP method allowlist that are mechanism-level and pinned by tests.

22 days agoTools & CapabilitiesMIT
F

dsh-firecrawl

firecrawl/dsh-firecrawl

Firecrawl-backed search and fetch providers for the DeepSeek Harness web capability seam (ctx.web)

23 months agoTools & CapabilitiesMIT
B

dsh-yunpa

binskyz/dsh-yunpa

Windows-only local encrypted credential vault (DPAPI-wrapped AES-256-GCM) plus a headless-Chrome login keeper: 31 agent tools log a site in once, keep the session on disk, and fetch login-walled pages (Tieba, NGA, Pixiv, one book site) with per-floor post extraction. The live page mirrors into a draggable, collapsible right-edge dock where clicks, typing and scrolling replay over CDP, so a captcha can be solved without a separate browser window. Edge/Chrome saved passwords can be migrated: the plugin reads the browser's Login Data store, decrypts v10/v11 entries in-process, and copies the store and its key blobs into its own controlled profile so the browser can autofill them (v20 app-bound entries can only be autofilled, not decrypted offline). Ships a one-command installer that repairs the DSH profile registration and a built-in self-test.

13 days agoTools & CapabilitiesMIT
U

dsh-crw

us/dsh-crw

fastCRW-backed web search and fetch providers for DeepSeek Harness (ctx.web)

13 months agoTools & CapabilitiesMIT
L

dsh-browser-use-automation

laoyingfuhuole/dsh-browser-use-automation

Fully background browser automation and browser use for DSH: an offscreen Electron window per conversation with real CDP input and screenshots, so headless-style browsing never steals focus or pops windows. Runs on Electron and keeps cookies in a persistent user-data directory, so a signed-in page stays signed in for later conversations.

03 days agoTools & CapabilitiesMIT
F

dsh-scrapling-mcp

foolfu86/dsh-scrapling-mcp

A configuration-only DSH bundle that connects the MCP server shipped with Scrapling to DeepSeek Harness over stdio, exposing its HTTP fetch and stealth-browser scraping tools for page extraction, browser actions, screenshots and network inspection. Requires Python 3.10+ with scrapling\[ai] (scrapling-mcp on PATH) and a Chromium-compatible browser (scrapling install).

06 days agoTools & Capabilities
X

prismsearch (dsh)

xiaonerner0821/prismsearch

Bundles the PrismSearch MCP server and its agent skill. Web search over Bing and Baidu with no account or API key, plus Google and Brave when API keys are set and DuckDuckGo, Sogou, 360 and Yandex when enabled in config; automatic engine fallback and an aggregate mode. Also image search, WeChat Official Account article search, and fetch_page, which returns web pages and PDFs as Markdown in segments.

03 days agoTools & CapabilitiesApache-2.0
S

specstream-tools (dsh-plugin-specstream)

specstream/specstream-tools

Registers the hosted SpecStream MCP server with the harness MCP manager and keeps the API key in the credential store. The server returns live web data as structured rows, each value with its source URL, and a run starts only after the quote's maximum is approved.

03 days agoTools & CapabilitiesMIT
K

dsh-websift

knlcxy/dsh-websift

Token-efficient web reading for DeepSeek Harness: one call fetches several pages through a real Chrome/Edge over CDP, gates them by relevance and returns a single digest, cutting context tokens by 80-98%. Real search URLs, login flow, screenshots, three proxy modes.

07 days agoTools & CapabilitiesMIT
N

hermes-web-mcp

newbeebnb/hermes-web-mcp

Keyless web powers for any MCP client: web_search, JS-rendered web_extract over dual CDP Chrome with proxy failover, and 7 real-browser page_* tools in an isolated context.

02 months agoTools & CapabilitiesMIT