Huuthangntk Claude Vision Mcp Server

ai.smitheryPublished by smithery.aiOfficial publisherv1.0.0Updated Oct 24, 2026

Analyze images from multiple angles to extract detailed insights or quick summaries. Describe visu…

The publisher's own server: 222wcnm Bilistalkermcp

VerifiedStreamable HTTPWeb executableDeveloper ToolsAI & ML

Overview

AI-generated overview

Remote MCP server that sends prompts to Anthropic's Claude for deep analytical thinking and image analysis before coding.

What you can do
  • Run a deep-think analysis on new information such as errors, requirements, review feedback or architecture questions
  • Get structured insights, alternatives and best-practice suggestions before writing code
  • Analyze images from multiple angles to extract detailed insights or quick summaries
  • Describe visual content in response to a prompt
When to use it
Useful when you want an assistant to reason through a problem, error, design decision or image before it starts writing code, and you are willing to route that content through Anthropic's Claude models.
Requirements
Remote streamable HTTP endpoint; the manifest declares no authentication, but the README describes an Anthropic Claude API key (ANTHROPIC_API_KEY) and an optional model setting (CLAUDE_MODEL) for self-hosted or Docker use. A Smithery bearer token header is listed for the hosted endpoint.
Before you install
Prompts, code snippets and images are sent to Anthropic's Claude API, so avoid confidential material. The README shows the API key being passed in a URL query string, which can leak into logs; prefer environment variables. The README also advises keeping manual approval of tool calls enabled.

Installation

In SourceWeft

  1. Open Huuthangntk Claude Vision Mcp Server in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/ai.smithery%2Fhuuthangntk-claude-vision-mcp-server/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "huuthangntk-claude-vision": {
      "type": "http",
      "url": "https://server.smithery.ai/@huuthangntk/claude-vision-mcp-server/mcp"
    }
  }
}

README

Claude Deep Think MCP Server

A powerful Model Context Protocol (MCP) server that provides proactive deep analytical thinking using Anthropic's Claude Sonnet 4.5. This tool is designed to be called BEFORE writing code when new information arrives.

⚡ Core Concept: Think Before Code

Use this tool FIRST when new information arrives, BEFORE writing any code:

  • 🐛 Error messages or stack traces
  • 📝 User requirements or feature requests
  • 💬 Code review feedback
  • 🚀 Performance issues
  • 🔒 Security alerts
  • 📚 API documentation to integrate
  • 🗄️ Database problems
  • 💭 UX/UI feedback
  • 🔄 Breaking changes in dependencies
  • 🏗️ Architectural decisions

Workflow: New Info → Think Tool → Review Insights → Write Better Code

🌟 Features

Deep Think & Analysis (claude_think)

Provides intelligent insights, suggestions, and strategic guidance before code implementation. Perfect for:

  • ✅ Understanding context deeply before acting
  • ✅ Identifying potential pitfalls upfront
  • ✅ Suggesting best practices from the start
  • ✅ Offering alternative approaches
  • ✅ Extracting key information for efficient implementation
  • ✅ Strategic decision-making
  • ✅ Problem-solving and architecture planning

Result: Fewer bugs, better code quality, faster development!

📋 Prerequisites

  • Node.js 18+ or Bun
  • Anthropic Claude API key (Get one here)
  • MCP-compatible client (Cursor IDE, Claude Desktop, etc.)

🚀 Quick Start

1. Installation

bash
cd claude-vision-mcpbun install# ornpm install

2. Configuration

The API key is configured when connecting to the MCP server (see Docker or Cursor setup below).

3. Build

bash
bun run build# ornpm run build

🐳 Docker Setup (Recommended)

Quick Start

bash
cd claude-vision-mcp
# Create .env file with your API keyecho "ANTHROPIC_API_KEY=your-key-here" > .envecho "CLAUDE_MODEL=claude-sonnet-4-20250514" >> .env
# Start containerdocker-compose up -d
# Check statusdocker ps | grep claude-vision

The container will auto-restart when Docker Desktop launches.

Docker Configuration

The server runs on http://localhost:8080/mcp with the following environment variables:

  • ANTHROPIC_API_KEY - Your Claude API key (required)
  • CLAUDE_MODEL - Model to use (default: claude-sonnet-4-20250514)

🔧 Usage in Cursor IDE

Docker Connection (Recommended)

Add to your ~/.cursor/mcp.json or .cursor/mcp.json:

json
{  "mcpServers": {    "Claude Deep Think": {      "url": "http://localhost:8080/mcp?apiKey=YOUR_API_KEY&model=claude-sonnet-4-5-20250929"    }  }}

Enable Proactive Thinking

Copy the .cursorrules file from this repo to your project root. This makes Cursor AI automatically use the think tool before writing code.

bash
# From your project directorycp claude-vision-mcp/.cursorrules .cursorrules

Tool Usage Pattern

Always use this pattern when new information arrives:

Use the claude_think tool to analyze: [NEW INFORMATION]
Context: [Current situation, tech stack, constraints]

Examples:

Error Message:

Use the claude_think tool to analyze:
Error: "TypeError: Cannot read property 'map' of undefined"
Context: React component rendering users from useState hook

New Feature:

Use the claude_think tool:
Requirement: Add dark mode toggle to header
Context: Next.js 14, need to check if ThemeContext exists

Performance Issue:

Use the claude_think tool:
Issue: Homepage renders 50+ times, parent causing all children to re-render
Context: useState for theme in Header, passed via props to 20+ children

📚 Examples

Example 1: Analyzing Technical Decisions

Use the claude_think tool to analyze:
"I'm building a real-time chat application. Should I use WebSockets, SSE, or HTTP polling?"
Context: Need to support 100K concurrent users, prioritize ease of implementation

Expected Output: Comprehensive comparison with pros, cons, and recommendations

Example 2: Architecture Planning

Use the claude_think tool to evaluate:
"What's the best way to structure a multi-tenant SaaS application?"
Context: PostgreSQL database, Node.js backend, 50-100 tenants expected

Example 3: Best Practices

Use the claude_think tool:
"Review this approach to handling user sessions in a Next.js app"
Context: Using JWT tokens, storing in localStorage, concerned about security

🛠️ Development

Project Structure

claude-vision-mcp/├── src/│   └── index.ts              # Main MCP server implementation├── .smithery/│   └── index.cjs            # Built server (generated)├── package.json              # Dependencies and scripts├── tsconfig.json            # TypeScript configuration├── smithery.yaml            # Smithery deployment config├── Dockerfile               # Docker container definition├── docker-compose.yml       # Docker Compose configuration└── README.md               # This file

Available Scripts

  • bun run build / npm run build - Compile TypeScript
  • bun run dev / npm run dev - Development server with hot reload

🔒 Security Best Practices

  1. Never commit API keys - Always use environment variables
  2. Use .gitignore - Ensure .env files are ignored
  3. Rotate keys regularly - Update API keys periodically
  4. Review tool calls - Keep manual approval enabled in Cursor
  5. Use development environments - Test with non-production data

📦 Docker Management

bash
# Start containerdocker-compose up -d
# View logsdocker logs claude-vision-mcp-server -f
# Restart containerdocker-compose restart
# Stop containerdocker-compose down
# Rebuild and restartdocker-compose up -d --build

🐛 Troubleshooting

Issue: Server not connecting in Cursor

Solutions:

  1. Verify Docker container is running: docker ps | grep claude-vision
  2. Check container logs: docker logs claude-vision-mcp-server
  3. Restart Cursor IDE completely
  4. Verify API key in URL is correct

Issue: API key errors

Solutions:

  1. Ensure key starts with sk-ant-
  2. Test key at: https://console.anthropic.com/
  3. Check environment variables in container
  4. Verify URL parameter format

Issue: Container won't start

Solutions:

bash
# Check logsdocker logs claude-vision-mcp-server
# Verify .env filecat .env
# Rebuild from scratchdocker-compose down -vdocker-compose up -d --build

💡 Performance

With Bun runtime:

  • ⚡ 4x faster package installs
  • ⚡ 3-4x faster script execution
  • 📦 Smaller Docker images
  • 🚀 Faster cold starts

📖 Comprehensive Guides

💡 Why This Workflow?

Without Think Tool:

1. User reports error2. AI writes quick fix3. Fix creates new bug4. Multiple iterations needed⏱️ Total: 30 minutes, 3 iterations

With Claude_Think Tool:

1. User reports error2. AI analyzes with claude_think tool (20s)3. AI writes comprehensive fix4. Works correctly first time⏱️ Total: 5 minutes, 1 iteration

Result: 6x faster, better quality, fewer bugs! 🎉

📄 License

MIT

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

📞 Support

For issues or questions:

  • Open an issue on GitHub
  • Check the MCP Documentation
  • Read the workflow guides in this repository

🙏 Acknowledgments

Source: README.md at commit 9083e24

Tools

0
SourceWeft has not read this server's tools yet.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.

Other Smithery integrations

222wcnm Bilistalkermcp

ai.smitheryOfficial publisher

Bilibili creator analysis server that lets an assistant look up a specific user's profile, videos, dynamics, articles, subtitles, followings and comments.

Streamable HTTPWeb executable
Web Search & ScrapingNot indexed yetOct 24, 2026

Zwldarren Akshare One Mcp

ai.smitheryOfficial publisher

Remote MCP server that gives an assistant read-only access to Chinese stock market data: historical and real-time prices, news, and financial statements.

Streamable HTTPWeb executableAuth
FinanceCredential requiredOct 24, 2026

Zhaoganghao Hellomcp

ai.smitheryOfficial publisher

A small remote MCP server that lets an assistant greet people by name and share background on the origin of 'Hello, World'.

Streamable HTTPWeb executable
Not indexed yetOct 24, 2026

Zeta Chain Cli

ai.smitheryOfficial publisher

A remote MCP server that lets an assistant generate friendly, customizable greetings for any name or audience.

Streamable HTTPWeb executableAuth
Credential requiredOct 24, 2026

Yuna0x0 Hackmd Mcp

ai.smitheryOfficial publisher

An MCP server that connects an assistant to the HackMD API so it can read, create, update and delete HackMD notes and manage teams.

Streamable HTTPWeb executable
Productivity & WorkflowNot indexed yetOct 25, 2026