SaaSHub helps you find the best software and product alternatives Learn more →
Top 23 HTML mcp Projects
-
ai-berkshire
AI 时代的伯克希尔:基于 Claude Code / Codex 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built for Claude Code / Codex. 4 masters' methodologies + multi-agent adversarial analysis.
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
awesome-openclaw-agents
197 production-ready AI agent templates for OpenClaw. SOUL.md configs across 24 categories. Submit yours!
Project mention: 📬 Claude Code Finds 500 Zero-Days, Meta Redefines "Open," CISA Deadline Hits | dev.to | 2026-04-08Source: GitHub | GitHub (awesome-openclaw-agents) | DEV Community
-
second-brain-os
Guides and resources for AI engineers: an agents course, five handbooks, a hands-on second-brain project and a vetted reading list.
Project mention: Open Source Radar · 2026-11-02: Agent infrastructure is splitting into replaceable parts | dev.to | 2026-11-01GitHub: https://github.com/undefined-ui/second-brain-os
-
agent-skills-hub
AgentSkillsHub (agentskillshub.top) — security-graded directory of open-source Claude skills, MCP servers & AI agent tools, refreshed every 8 hours
-
openaccountants
Open tax skills for AI: 2,000+ skills for 190+ countries and states, every figure cited to the law. Works in ChatGPT, Claude, Cursor and any MCP client.
Project mention: Open-source tax rules for 100 countries that your LLM can use | news.ycombinator.com | 2026-10-18 -
LazyOwn
837 CLI commands. Multi-operator C2. 153 MCP tools for AI agents. The First OSS C2 with Linux native c BOF support + built-in YARA/Nuclei marketplaces.
Hello Hacker News friends, I love your work and I love building things. Passionate about cybersecurity, I built LazyOwn a few years ago as a notebook of techniques I was learning. It's been over two years now, and I think sharing it is the right thing to do since it represents a lot of knowledge acquired over time. https://github.com/grisuno/LazyOwn
-
awesome-ai-gateway
⚡ Awesome AI Gateway — pick an AI gateway from 240+ (LiteLLM, OpenRouter, Portkey, Kong, Higress, new-api, Bifrost) by cost, security & compliance, see what consolidated in 2026, learn how they actually work from an 8-chapter handbook, and verify every number yourself. Reproducible benchmarks, bilingual; stars & releases refreshed daily.
Project mention: I spent $788 on an AI coding agent in one day. Here's the breakdown. | dev.to | 2026-06-13github.com/cuihuan/awesome-ai-gateway
-
awesome-openid-connect
OpenID Connect, the authentication protocol and identity layer on top of OAuth 2.0 used in many SSO and adopted in many social logins (Apple, Facebook, Google, ...etc). Find this curated list of providers, services, libraries, and resources to adopt it and know more about existing specs.
OpenID Connect
-
tapilot
Control your Android phone with natural language. No computer required. Powered by Midscene, with Skills and a Codex plugin.
Project mention: Running a screenshot-based automation agent on an Android phone | dev.to | 2026-11-02Demo and setup: https://tapilot.lifeos.md Source: https://github.com/tapilot-ai/tapilot
-
platform-engineering
A centralized hub for platform engineering teams, providing resources, best practices, and automation tools. Includes IaC templates, blueprints, and operational guides to help build scalable, secure, and efficient platforms for cloud-native environments and DevSecOps workflows.
-
Fast-LLM-Agent-MCP
This repo covers LLM, Agents, MCP Tools, Skills concepts with sample codes: LangChain & LangGraph, AWS Strands Agents, Google Agent Development Kit, Fundamentals.
Project mention: Simple DEV Blog Post Writer with LangGraph Multi Agents with Memory, AWS Bedrock Nova: Generator & Evaluator Pattern | dev.to | 2026-05-10 -
Everything below about HyperFrames comes from its README and its own HyperFrames vs Remotion guide, read on November 12, 2026.
-
ios-agent-skill
Swift source, Apple guides and MCP tools for AI coding agents. Review iOS code, scaffold apps, and build/run/preview with Xcode Simulator.
Installation and client-specific setup are on the project website. Start with a small project and follow the setup for your coding client. The source is MIT licensed; no hosted simulator is included.
-
plasmate
The browser engine for agents. HTML in, Semantic Object Model out. 10x token compression, V8 JS rendering, CDP compatible. Apache-2.0.
Project mention: Show HN: Plasmate, an agent-native headless browser engine in Rust (Apache-2.0) | news.ycombinator.com | 2026-04-15 -
Project mention: Show HN: Backlog – tasks and contexts manager for AI coding agents | news.ycombinator.com | 2026-07-07
-
OpenTrustBench
Trust & security scanner for AI agents and MCP servers — OWASP-mapped findings, Trust Cards (A–F grades), SARIF + CI gate. Free CLI, zero telemetry.
Project mention: Show HN: AgentTrust – A–F trust scores for MCP servers (50 graded, open source) | news.ycombinator.com | 2026-09-09 -
I'm the maker of Thumbly, a free, open-source Mac app that lets MCP agents see and operate a real iPhone. Version 0.1.0 is available now.
-
mcp-demo
URL MCP is a proof of concept stateless MCP server builder that allows users to build MCP servers without writing or hosting code. It's intended for protocol and security experimentation rather than for building real world MCP integrations.
-
causari
AI-written code has no author. It has causes. Causari records them. How many lines from AI-tagged commits are still alive in your repo? One command, any git repo, no setup. A count, not a grade.
Project mention: Validating snapshots before restoring an AI coding workspace | news.ycombinator.com | 2026-09-09What should an AI coding tool guarantee before restoring your files?
I’m the creator of Causari, an open-source tool for recording AI coding actions and connecting code changes to their session context.
While stress-testing its recovery code, we found a failure worth discussing: restoring a snapshot could overwrite some workspace files before discovering that a later object was missing. The recovery operation itself could leave the project partially modified.
The proposed fix validates the complete target snapshot and destination paths before writing. It also adds a dry run and changes bisect to restore the actual starting workspace, including unrecorded edits, after success or ordinary errors.
We added regression tests and a reproducible synthetic lab. The local suite passes 116 tests. This is still not an atomic transaction: concurrent writers, forced termination and disk failures remain outside the guarantee.
Implementation and tests: https://github.com/croviatrust/causari/pull/44
For people building developer tools: would you run this kind of historical testing exclusively in a separate worktree, or support in-place recovery with a persistent recovery journal? I’m interested in the failure cases that shaped your choice.
-
anansi
Open-source personal web memory for developers and AI agents. Capture browser saves, keep a searchable library, and query it over MCP. (by jojomensah89)
That is why I started building Anansi. Anansi is an open-source personal web memory for developers and AI agents. The browser extension captures what I already save, the library keeps it searchable, and the same library is exposed through a read-focused MCP server so a coding agent can search and pull a saved reference into context.
-
canlicapital
canli-mcp: 369 free finance tools for Claude, Cursor and any MCP client, behind five (SEC filings, insider trades, 13F and 13D/G holders, options, FOMC, macro data, quant analytics, backtest validation). MIT, no API key, runs locally. Plus Canli Capital's open quant research, where every number links to its source.
Project mention: 35 more published signals took our backtest to Sharpe 3.2 in-sample and 0.46 out of sample | dev.to | 2026-10-22The protocol, amendments and result files are in github.com/arhancanli/alphac, and the validation tools (deflated Sharpe, placebo tests) are in github.com/arhancanli/canlicapital. canli-mcp is a free MCP server (MIT, no API key, runs locally): npx -y canli-mcp.
-
impri
Human-in-the-loop approval inbox for AI agents. An agent proposes an action, a human approves or rejects it, then it runs. Watchers + approval inbox, MCP + REST, self-hostable (MIT).
Project mention: How to put a real human approval step between your AI agent and any real-world action | dev.to | 2026-07-12 -
FaviconDL
Find and download the best-quality favicon of any website (SVG/PNG/ICO). Bulk download, free no-key API, MCP server, image-to-favicon generator.
HTML mcp discussion
HTML mcp related posts
-
Describe your agent, get the cheapest sourced infra stack
-
The OWASP MCP Top 10, and what your server's catalog tells a model
-
Test MCP workspace isolation with Next.js and Dendra
-
Twelve videos in four days. Nobody picked up a camera.
-
I built an open-source personal web memory for coding agents
-
We rated 200 Japanese SaaS products on AI-agent readiness. Only 41 passed.
-
Agent memory and context that never leaves your machine
-
A note from our sponsor - SaaSHub
www.saashub.com | 16 Nov 2026
Index
What are some of the best open-source mcp projects in HTML? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | ai-berkshire | 17,149 |
| 2 | awesome-openclaw-agents | 4,067 |
| 3 | second-brain-os | 1,580 |
| 4 | agent-skills-hub | 502 |
| 5 | openaccountants | 492 |
| 6 | LazyOwn | 301 |
| 7 | awesome-ai-gateway | 158 |
| 8 | awesome-openid-connect | 135 |
| 9 | tapilot | 138 |
| 10 | platform-engineering | 103 |
| 11 | Fast-LLM-Agent-MCP | 94 |
| 12 | hyperframes | 47 |
| 13 | ios-agent-skill | 41 |
| 14 | plasmate | 19 |
| 15 | backlog | 17 |
| 16 | OpenTrustBench | 14 |
| 17 | thumbly | 12 |
| 18 | mcp-demo | 10 |
| 19 | causari | 9 |
| 20 | anansi | 8 |
| 21 | canlicapital | 6 |
| 22 | impri | 6 |
| 23 | FaviconDL | 5 |