houtini-lm vs everything
Side-by-side comparison to help you pick between these two MCP servers.
houtini-lm by houtini-ai | everything by modelcontextprotocol | |
|---|---|---|
| Stars | ★ 88 | ★ 85,748 |
| 30d uses | — | — |
| Score | 48 | 77 |
| Official | — | ✓ |
| Categories | AI / LLM ToolsDeveloper ToolsProductivity | Developer ToolsAI / LLM ToolsOther |
| Language | JavaScript | TypeScript |
| Last commit | 1 mo ago | this month |
houtini-lm · Summary
MCP server that offloads bounded tasks from Claude Code to local/cloud LLMs to reduce token consumption.
everything · Summary
Official MCP test server exercising all protocol features for client builders.
houtini-lm · Use cases
- Offloading code review and test generation to local LLMs while Claude handles architectural planning
- Using cloud APIs like DeepSeek for boilerplate code generation to save Claude's expensive tokens
- Generating commit messages and documentation from diffs using cheaper local models
everything · Use cases
- Testing MCP client implementations against all protocol features
- Learning MCP protocol capabilities through a reference server
- Validating client compatibility with different transport methods
houtini-lm · Install
# For Claude Code
claude mcp add houtini-lm -- npx -y @houtini/lm
# For Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"houtini-lm": {
"command": "npx",
"args": ["-y", "@houtini/lm"],
"env": {
"HOUTINI_LM_ENDPOINT_URL": "http://localhost:1234"
}
}
}
}everything · Install
NPX (recommended)
{
"mcpServers": {
"everything": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-everything"]
}
}
}On Windows, use cmd /c:
{
"mcpServers": {
"everything": {
"command": "cmd",
"args": ["/c", "npx", "-y", "@modelcontextprotocol/server-everything"]
}
}
}Docker
{
"mcpServers": {
"everything": {
"command": "docker",
"args": ["run", "-i", "--rm", "mcp/everything"]
}
}
}Global install
npm install -g @modelcontextprotocol/server-everything@latest
npx @modelcontextprotocol/server-everything