MCP Server for Veryfi Document Processing

A Model Context Protocol server that provides access to Redis databases. This server enables LLMs to interact with Redis key-value stores through a set of standardized tools.

Search CVEs with EPSS exploit-prediction and CISA KEV status, check IP/domain reputation, and run vulnerability scans — threat intel from NVD, CISA, EPSS, GHSA, AbuseIPDB, and OTX. - **Tools (8):** search_cve, cve_detail, check_ip, check_domain, vulnerability_scan, threat_feed, daily_brief, mint_info

基于七牛云产品构建的 Model Context Protocol (MCP) Server，支持用户在 AI 大模型客户端的上下文中通过该 MCP Server 来访问七牛云存储资源、利用 Dora 服务进行图片操作等。 如果有什么需求欢迎在下方评论，您也可以在 github 仓库中提 issue。

Repository management, file operations, and GitHub API integration

The project tracker for teams of humans and AI agents — in plain files. MCP server + CLI, zero dependencies.

Create a remote sandbox that can execute code/run commands/upload and download files. 创建远程沙盒，可以执行代码/运行命令/上传下载文件

Tlaloc's MCP server connects Claude, ChatGPT, and any AI assistant to official Mexican data: validate CURP (RENAPO) and RFC (SAT), look up postal codes (SEPOMEX) and phone carriers (IFT), and download/verify SPEI payment receipts (CEP, Banxico). 7 tools, Streamable HTTP, Bearer auth. Pay-per-call via SPEI — no card, no subscription. Si el campo es corto, usa la versión meta (~160c): Validate CURP, RFC, postal codes, phone numbers, and SPEI receipts (CEP) from official Mexican sources. Pay-per-call via SPEI, plus an MCP server for your AI assistant.

A Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.

Channel management and messaging capabilities

MCP Advisor & Installation - Use the right MCP server for your needs

A hosted MCP server that turns PDFs into clean, LLM-ready Markdown, so AI agents can convert documents as a built-in tool: real Markdown tables, formulas as LaTeX, and OCR for scans. The same engine is also a REST API, a web app, a Chrome extension and a ChatGPT Custom GPT. It runs its own engines (MinerU + Docling), not an LLM wrapper. Connect at https://pdf2md.dev/api/v2/mcp with a Bearer API key; docs at https://pdf2md.dev/developers/#mcp

Create, search, update, and manage data in OnePageCRM.

Read, search, send, organize, draft and schedule email across your inboxes from any MCP client.

BlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.

基于Anduin2017 / HowToCook （程序员在家做饭指南）的mcp server，帮你推荐菜谱、规划膳食，解决“今天吃什么“的世纪难题； Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"

Read-only database access with schema inspection

Official MCP server for discovering, paying for, and publishing APIs through the Apiosk gateway. AI agents can browse the API catalog, execute any listing through a uniform contract or API-specific tools, and settle paid calls automatically over USDC (x402 on Base), no manual payment step needed.

Grist is a flexible spreadsheet-database. The Grist MCP server lets agents work across your team sites and documents: list and query records, add or update rows, create new docs and tables. Universal URL with OAuth 2.0. Works in Claude, ChatGPT, and any MCP client that supports remote HTTP servers.

BrainTube turns everything you save — YouTube, articles, podcasts, PDFs, Notion, Obsidian, and any URL — into a persistent, semantically searchable knowledge base your AI can query. Connect it to Claude, Cursor, Windsurf, ChatGPT, or any MCP client and search by meaning, not keywords. 52 tools, AI-agnostic, hosted.

The official Control Plane MCP server. Deploy, operate, troubleshoot, and migrate containerized workloads — plus secrets, networking, and stateful storage across AWS, GCP, Azure, OCI, and your own hardware, in natural language.

A Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.

An MCP server implementation for retrieving information from the AWS Knowledge Base using the Bedrock Agent Runtime.

AI image generation using various models

15 production-ready x402 execution primitives for AI agents. Pay per call with USDC on Base. EXEC PRIMITIVES ($0.01–$1.00/call): cross-chain routing (XRPL/Hedera/Base), browser automation, EU AI Act + DSA + MiCA compliance audit, web search (Bing RSS), page extraction, DNS/SSL audit, Workers KV storage, R2 object storage. CF PRIMITIVES ($0.0005–$0.01/call): LLM inference, Whisper STT, embeddings, image generation, cached LLM, headless browser, code execution in isolated Cloudflare Dynamic Workers (JS + Python, network blocked). Connect via MCP at https://api.zuluworksai.com/mcp — tools/list is free, tools/call requires x402 payment. Self-hosted facilitator. Built for production agent workloads.

AgentBrush is an MCP server that lets AI coding agents automate image generation inside their workflows: the agent calls and chains the tools (generate, remove-background, save-as-reference) without leaving the editor. Feed it your brand once (colors, fonts, reference images) and every product shot, app icon, OG card, game sprite or mascot lands on-brand and drops straight into your repo. Includes style presets, reference-image consistency, a mask editor for region edits, legible multilingual text, and free local background removal. For Claude Code, Cursor, Windsurf and any MCP client.

Web content fetching and conversion for efficient LLM usage

The Custom Website Editor lets a pastor manage and update their church's professionally-built website using plain English — no code, no logins, no technical knowledge required. It connects directly to the live website's GitHub repository, so any change you describe is made for you and ships to the real, public site within about 30 seconds. Editing your site. Ask for any wording change — fix a typo, reword a welcome message, update a service time, swap a heading, add a paragraph or a whole new section — and it finds the right page, makes the exact edit, and publishes it. It can read any page before changing it, search your site's content for a phrase you remember ("Sunday morning," "What to Expect," a pastor's name), browse your pages and files, and even create brand-new pages. Every change is saved with a clear, human-readable note so you always know what was done. Photos and videos. Send a photo and it adds it to your site; send a video or a large image and it's hosted on fast permanent storage and dropped onto the page you want. It can list the images already on your site so the right photo always shows up — no broken pictures. Undo and history. Ask "what did I change today?" and it shows your recent updates in plain language. Say "undo that" or "go back" and it safely rolls the live site back to how it was — nothing is ever lost. Knowing it worked. After any change it can confirm the site rebuilt successfully, and if something ever breaks the build, it explains what went wrong in plain English and fixes it — you never see raw errors. Your own domain. Bought a domain like yourchurch.org? It connects that domain to your site and gives you the exact, simple settings to enter at your domain registrar, including a warning if the change could affect email on that domain. Hosting, chat, analytics, and more. It can start your monthly hosting subscription, set up a live website chat widget so visitors can message you, and report how your site is doing — total traffic, your most-viewed pages, where visitors are coming from, and day-by-day trends. It can also score any church website against the Church Website Score rubric to show where it stands.

Yapp turns "build me a page and publish it" into a live URL. Connect once (browser OAuth, or a token for terminal clients) and your AI can publish HTML, PDFs, ZIP sites, images and landing pages to a public slug.yapp.page URL in seconds.