MCP Catalogs
Home

bgpt-mcp vs memory

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

bgpt-mcp
by connerlambden
memory
by modelcontextprotocol
Stars★ 20★ 85,748
30d uses
Score4377
Official
Categories
AI / LLM ToolsresearchDatabase
Knowledge GraphAI / LLM ToolsProductivity
LanguageJavaScriptTypeScript
Last commit1 mo agothis month

bgpt-mcp · Summary

A remote MCP server for searching scientific papers with full-text experimental data extraction.

memory · Summary

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

bgpt-mcp · Use cases

  • Literature reviews with real experimental data analysis
  • Evidence synthesis by grounding AI responses in actual study findings
  • Research assistance by finding papers based on methodology or outcomes

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

bgpt-mcp · Install

Installation Options

**Option A: Remote Connection (Recommended)**

For Claude Desktop, add to claude_desktop_config.json:

{
  "mcpServers": {
    "bgpt": {
      "url": "https://bgpt.pro/mcp/sse"
    }
  }
}

For other MCP clients like Cursor, add to .cursor/mcp.json or equivalent config file using the same structure.

**Option B: Via npx**

{
  "mcpServers": {
    "bgpt": {
      "command": "npx",
      "args": ["-y", "bgpt-mcp"]
    }
  }
}

**Option C: Install Globally**

npm install -g bgpt-mcp

Then add to MCP config:

{
  "mcpServers": {
    "bgpt": {
      "command": "bgpt-mcp"
    }
  }
}

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"]
    }
  }
}
Comparison generated from public README + GitHub signals. Last updated automatically.