fetch vs plasmate
Side-by-side comparison to help you pick between these two MCP servers.
fetch by modelcontextprotocol | plasmate by plasmate-labs | |
|---|---|---|
| Stars | ★ 85,748 | ★ 21 |
| 30d uses | — | — |
| Score | 76 | 45 |
| Official | ✓ | — |
| Categories | Web ScrapingAI / LLM ToolsProductivity | Browser AutomationWeb ScrapingAI / LLM Tools |
| Language | TypeScript | HTML |
| Last commit | this month | this month |
fetch · Summary
An MCP server that fetches web content and converts HTML to markdown, allowing LLMs to read web pages.
plasmate · Summary
Plasmate is a browser engine for agents that converts HTML to a compact Semantic Object Model (SOM) via MCP.
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
plasmate · Use cases
- Web content extraction and summarization for AI agents
- Interactive web automation through stable element identifiers
- Efficient browser rendering for token-conscious LLM applications
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"]
}
}
}plasmate · Install
Install via package manager:
cargo install plasmate # Rust
npm install -g plasmate # Node.js
pip install plasmate # PythonFor Claude Desktop integration, add to your config:
{
"mcpServers": {
"plasmate": {
"command": "plasmate",
"args": ["mcp"]
}
}
}