Dochost

An MCP server implementation that provides a tool for dynamic and reflective problem-solving through a structured thinking process.

Connect AI agents to your ZERNO product backlog over a secure remote MCP endpoint. Read project briefs, list and open tasks, retrieve compiled project memory, patch task status, submit triage proposals, and file agent-intake tasks. OAuth 2.1 (PKCE), per-project authorization. 8 tools, no resources or prompts.

An MCP server that lets an AI agent deploy a web game to a playable multiplayer URL — rooms, live state sync, and leaderboards — in one conversation.

Long-term memory system for AI agents with semantic search, context management, and multi-format storage. Hierarchical memory architecture (STM → LTM → Deduction), FAISS vector retrieval, SQLite persistence.

Real-time web search and clean page extraction, in one drop-in MCP server. - 🔎 search_web_pages: Ask a question in plain language, get back the most relevant pages from Keenable's search index. Fresh results, ranked, ready to act on. - 📄 fetch_page_content: Hand it a URL, get back clean, parsed, agent-ready text. The boilerplate, ads, and markup are gone; the signal stays.

Cross-source attribution across 37+ business tools. True ROAS in 14 seconds. Not a dashboard. A decision.

Uphealth Signal turns federally-sourced (CDC/NIH/MedlinePlus) health facts, lists, and tips into agent-callable cued-stream tools. Every cue is provenance-backed, audience-safety-checked, and sequenced on the patient's last response, so your AI health agent never fabricates health content. Free sandbox (Display mode): no PHI, no BAA. Not medical advice.

A local-first cognitive substrate for neurodivergent professionals. Gives Claude memory, a sense of time, a translator for corporate ambiguity, and a guardrail that refuses to amplify rumination, hyperfocus, or sycophancy. MCP-native. No telemetry. AGPL-3.0-or-later. Self-ID sufficient — no diagnosis gating.

Publish Markdown or HTML to a clean, shareable link straight from your AI assistant. Hosted remote MCP server (Streamable HTTP) with OAuth sign-in — no API keys. Two tools: publish (Markdown/HTML → URL, with optional password, custom slug, and unlisted/public) and list_my_pages. Connect: claude mcp add --transport http dochost https://dochost.io/api/mcp . Homepage: https://dochost.io

Open-source MCP server that gives Claude persistent memory. Your AI keeps your standards, decisions, and reasons across sessions. Recalled by meaning, not keywords. Runs fully local: on-device semantic search, no cloud, no API keys. macOS, Windows, Linux. MIT.

Write notes to Flomo

Secure file operations with configurable access controls

Official Firecrawl MCP Server - Adds powerful web scraping to Cursor, Claude and any other LLM clients.

Zhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.

A Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.

AI image generation using various models

InferBench's MCP server lets coding agents run, serve and benchmark local LLMs (text + image, llama.cpp + Stable Diffusion) on your own hardware on demand. Measures real tokens/sec, picks the optimal quant for your GPU, and exposes a 124-model catalog. Local-first, no cloud required.

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。

An MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.

XGR.Network MCP is a remote MCP server that gives AI agents access to the XGR stack. It supports XDaLa workflow preparation, XGRChain evidence lookup, Explorer data access and programmable process automation through a public streamable HTTP endpoint.

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.

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.

GPT Image 2 AI Image Editor MCP is a remote MCP server that lets AI agents and MCP-compatible clients generate and edit images through GPT Image 2. It supports text-to-image, image-to-image, model listing, and generation status queries via a Streamable HTTP JSON-RPC endpoint. Users can connect with an API key and call image generation tools directly from Claude, Cursor, ChatGPT, or other agent workflows.

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

Orbit is an MCP-connected operations layer for Claude and other AI Agents. Connect once and every session — chats, Claude Cowork/Code/ChatGPT Codex and other agents automatically log outputs, reports and decisions to a shared dashboard. Agents read from and write to Orbit's knowledge layer, so context persists across sessions and tools without re-explaining. Includes live agent visibility, trust-weighted memory, broadcast to all agents, and agent creation. Free to start.

Channel management and messaging capabilities

Capability Example request Search availability "Is coolstartup.io available, and what does it cost?" Register a domain "Register it for two years with WHOIS privacy." Manage DNS "Point it at 192.0.2.10 and add my email records." Renew and transfer "Renew everything expiring in the next 30 days." Provision a VPS "Spin up a 2 vCPU server in Frankfurt running Ubuntu."

Web and local search using Brave's Search API