fetch vs web-agent-protocol
Side-by-side comparison to help you pick between these two MCP servers.
fetch by modelcontextprotocol | web-agent-protocol by OTA-Tech-AI | |
|---|---|---|
| Stars | ★ 85,748 | ★ 497 |
| 30d uses | — | — |
| Score | 76 | 48 |
| Official | ✓ | — |
| Categories | Web ScrapingAI / LLM ToolsProductivity | Browser AutomationWeb ScrapingAI / LLM Tools |
| Language | TypeScript | Python |
| Last commit | this month | 11 mo ago |
fetch · Summary
An MCP server that fetches web content and converts HTML to markdown, allowing LLMs to read web pages.
web-agent-protocol · Summary
Web Agent Protocol (WAP) records browser interactions and converts them into MCP servers for web automation replay.
fetch · Use cases
- LLMs reading news articles and blogs
- Content analysis of web pages
- Retrieving information from public websites
- Chunked reading of large web documents
web-agent-protocol · Use cases
- Automating repetitive web tasks by recording and replaying user interactions
- Creating MCP servers from browser workflows for AI agent automation
- Testing web applications by replaying exact user interaction sequences
fetch · Install
Installation
**Using uv (recommended)** No specific installation needed. Use uvx to run the server directly:
uvx mcp-server-fetch**Using PIP** Install via pip:
pip install mcp-server-fetchThen run as:
python -m mcp_server_fetchClaude Desktop Configuration
{
"mcpServers": {
"fetch": {
"command": "uvx",
"args": ["mcp-server-fetch"]
}
}
}web-agent-protocol · Install
# Install dependencies
conda create -n WAP python=3.11
conda activate WAP
pip install -r requirements.txt
# Set environment variables
set PYTHONPATH=/path/to/webagentprotocol # Windows
export PYTHONPATH=/path/to/webagentprotocol # Linux
# Create .env file with API keys
OPENAI_API_KEY=sk-proj-...
DEEPSEEK_API_KEY=sk-...
# Install Chrome extension
# See https://github.com/OTA-Tech-AI/webagentprotocol/tree/main/chrome-extensionFor Claude Desktop integration, add to claude_desktop_config.json:
{
"mcpServers": {
"wap": {
"command": "python",
"args": ["/path/to/webagentprotocol/wap_service.py"]
}
}
}```