Memory (Knowledge Graph) vs Outsource MCP
A side-by-side comparison of two AI, Data & Knowledge servers — tools, transport, auth, maintenance, and copy-paste config for each.
| Memory (Knowledge Graph) Official MCP server providing persistent, file-backed knowledge-graph memory across sessions. Verified stdio (local) No auth TypeScript | Outsource MCP Give your AI assistant its own AI assistants — outsource text and image generation to 20+ model providers. Unverified stdio (local) API key Stale Python | |
|---|---|---|
| Category | AI, Data & Knowledge | AI, Data & Knowledge |
| Language | TypeScript | Python |
| Transport | stdio (local) | stdio (local) |
| Auth | None | API key |
| GitHub stars | 74k | 30 |
| Last commit | 7 months ago | 1 year ago |
| Verified | ||
| Actively maintained | ||
| Install | npx -y @modelcontextprotocol/server-memory | uvx --from git+https://github.com/gwbischof/outsource-mcp.git outsource-mcp |
| Repo | Open | Open |
Verdict
Pick Memory (Knowledge Graph) if you want the official, vendor-maintained server, and you prefer the more popular, battle-tested option.
Pick Outsource MCP if you prefer its approach (give your ai assistant its own ai assistants — outsource text and image generation to 20+ model providers).
Add Memory (Knowledge Graph)
npx -y @modelcontextprotocol/server-memoryPaste into ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"memory-knowledge-graph": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-memory"
],
"env": {
"MEMORY_FILE_PATH": "/absolute/path/to/memory.jsonl"
}
}
}
}Add Outsource MCP
uvx --from git+https://github.com/gwbischof/outsource-mcp.git outsource-mcpPaste into ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"outsource-mcp": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/gwbischof/outsource-mcp.git",
"outsource-mcp"
],
"env": {
"OPENAI_API_KEY": "your-openai-key",
"ANTHROPIC_API_KEY": "your-anthropic-key",
"GOOGLE_API_KEY": "your-google-key",
"GROQ_API_KEY": "your-groq-key",
"DEEPSEEK_API_KEY": "your-deepseek-key",
"XAI_API_KEY": "your-xai-key",
"PERPLEXITY_API_KEY": "your-perplexity-key",
"COHERE_API_KEY": "your-cohere-key",
"FIREWORKS_API_KEY": "your-fireworks-key",
"HUGGINGFACE_API_KEY": "your-huggingface-key",
"MISTRAL_API_KEY": "your-mistral-key",
"NVIDIA_API_KEY": "your-nvidia-key",
"OLLAMA_HOST": "http://localhost:11434",
"OPENROUTER_API_KEY": "your-openrouter-key",
"TOGETHER_API_KEY": "your-together-key",
"CEREBRAS_API_KEY": "your-cerebras-key",
"DEEPINFRA_API_KEY": "your-deepinfra-key",
"SAMBANOVA_API_KEY": "your-sambanova-key"
}
}
}
}Requires `uv` (the Python package runner). Install it from https://docs.astral.sh/uv/ if `uvx` is not found.
FAQ
Memory (Knowledge Graph) or Outsource MCP — which is better?
Pick Memory (Knowledge Graph) if you want the official, vendor-maintained server, and you prefer the more popular, battle-tested option. Pick Outsource MCP if you prefer its approach (give your ai assistant its own ai assistants — outsource text and image generation to 20+ model providers).
Can I use both Memory (Knowledge Graph) and Outsource MCP?
Yes — MCP clients let you enable multiple servers at once. Add both configs to your client's mcpServers and use whichever tool fits the task.
Do Memory (Knowledge Graph) and Outsource MCP work with Claude, Cursor and Windsurf?
Both do. Copy the per-client config below into Claude Desktop, Cursor, or Windsurf.