DeepSeek Harness 插件：论文伴读工作台 — PDF 转录 / 检索 / 原生对话伴读 + 内置阅读器页面。

Universal content reader MCP Server for 10+ platforms

A self-hosted RSS reader and personal knowledge management tool.

Keeps large tool outputs out of an agent's context window by spilling them to disk and handing back a short pointer instead. Lets the agent pull only what it needs — exact numbered line ranges read directly from disk, or verbatim relevant lines returned by a small model answering a question about the stored output, plus tools to open, list, and close documents.

Enables AI chat backends to fetch public webpages and obtain cleaned readable text, Markdown, article content, metadata, and summary-ready prompts through MCP tools.

Enables MCP clients to submit HTTPS WeChat article URLs and receive parsed title, author, timestamp, and Markdown body through an external extractor, with clear errors for invalid paths, missing tools, timeouts, or access restrictions.

Enables AI agents to read WeChat Official Account articles by fetching mp.weixin.qq.com links from the user's own machine and network and converting them into clean Markdown with title, account, author, and publish-time metadata. Provides both single-article and batch-reading tools (up to 20 URLs) with optional image handling, character limits, and JSON output.

Enables reading public WeChat articles through HTTP text extraction with metadata, pagination, and image links, automatically falling back to a visible Chrome window when a verification page appears so the user can complete any captcha manually.

Search magazine articles and public previews, with publisher attribution and subscription links.

Reads AIA G702/G703 pay applications and change orders from PDF to JSON. $0.04/page via x402.

Reads invoices and receipts from PDF to JSON and checks the math. $0.04/page via x402.

Bureau-operated public read-only MCP service for public Context Packets and Cases.

Cross-platform native desktop control tools for DeepSeek Harness (Windows first): screen_shot, screen_read (accessibility tree + pixel description for text-only models), click/type/scroll/key, and app_list/app_launch — every mutating action gated by appro

Make RSS 📰 great again with AI 🧠✨!! 数据打标请联系 glidea123 (数万并发随时狂飙)

Motion capture for any creature from one AI video: two cameras in one frame, a DINOv2 joint reader, the rig fitted in both views, a GLB out.

Air traffic control discipline for agent output. Written for a reader with ADHD.

Reviews and fixes keyboard and focus behavior, ARIA, accessible names, forms, screen-reader announcements, motion and zoom against WCAG 2.2.

Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".

Enables MCP clients to read a shared book library from the AI reader’s own position, search full texts, leave margin notes, reply to shared annotations, and review reading status and library overview without moving the human reader’s progress.

Statistics of Russian texts as tools for LLM agents, built on the ruTS library: readability with school grade and reader age, officialese, SEO metrics, verse meter and rhyme, lexical diversity, morphology, syntax, keywords, concordance, collocations and stylometric comparison. Every value comes with a description, a scale reading and warnings when it is unreliable for the text