MCP Catalogs
Home

memory vs web-agent-protocol

Side-by-side comparison to help you pick between these two MCP servers.

memory
by modelcontextprotocol
web-agent-protocol
by OTA-Tech-AI
Stars★ 85,748★ 497
30d uses
Score7748
Official
Categories
Knowledge GraphAI / LLM ToolsProductivity
Browser AutomationWeb ScrapingAI / LLM Tools
LanguageTypeScriptPython
Last committhis month11 mo ago

memory · Summary

An MCP server implementing persistent memory using a local knowledge graph for AI models to remember user information across chats.

web-agent-protocol · Summary

Web Agent Protocol (WAP) records browser interactions and converts them into MCP servers for web automation replay.

memory · Use cases

  • Personalizing AI assistant interactions by remembering user preferences, history, and relationships
  • Building context-aware chat applications that maintain conversation history
  • Creating knowledge bases that persist across AI model sessions

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

memory · Install

Installation

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-memory"
      ]
    }
  }
}

VS Code

Use one-click installation buttons or manually configure in .vscode/mcp.json:

{
  "servers": {
    "memory": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-memory"
      ]
    }
  }
}

Docker

{
  "mcpServers": {
    "memory": {
      "command": "docker",
      "args": ["run", "-i", "-v", "claude-memory:/app/dist", "--rm", "mcp/memory"]
    }
  }
}

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-extension

For Claude Desktop integration, add to claude_desktop_config.json:

{
  "mcpServers": {
    "wap": {
      "command": "python",
      "args": ["/path/to/webagentprotocol/wap_service.py"]
    }
  }
}```
Comparison generated from public README + GitHub signals. Last updated automatically.