Other · Local MCP server

Model Manager

Manage your local model machine over MCP: state, model pull/remove, service switch, LoRA training.

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.setheerwagen/mcp-modelmanager
Version
1.0.2
Status
Active
Category
other
Transport
stdio (local process)
Package
PyPI
Published
2026-09-08
Updated
2026-09-08
Publisher
setheerwagen (GitHub) · 2 servers with pages here
Namespace
Namespace verified by the MCP Registry via GitHub (github.com/setheerwagen) · how
Repository
github.com/setheerwagen/local-ai-mcp-servers (folder mcp-modelmanager)
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
PyPImcp-modelmanager1.0.2stdioMM_VM_HOST (required), MM_VM_USER (required), MM_CONTAINER_ROOT (required), MM_MAX_TIER, MM_ENABLED_OPERATIONS, MM_VM2_HOST

How to connect Model Manager

Model Manager runs locally from a Python package published to PyPI: mcp-modelmanager version 1.0.2. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install - the usual command is uvx mcp-modelmanager. It reads these environment variables: MM_VM_HOST (required), MM_VM_USER (required), MM_CONTAINER_ROOT (required), MM_MAX_TIER, MM_ENABLED_OPERATIONS and MM_VM2_HOST; set them in the client's configuration for this server.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "mcp-modelmanager": {
      "command": "uvx",
      "args": [
        "mcp-modelmanager"
      ],
      "env": {
        "MM_VM_HOST": "<value>",
        "MM_VM_USER": "<value>",
        "MM_CONTAINER_ROOT": "<value>",
        "MM_MAX_TIER": "<value>",
        "MM_ENABLED_OPERATIONS": "<value>",
        "MM_VM2_HOST": "<value>"
      }
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More from setheerwagen (GitHub)

All 2 →
ServerRunsEndpoint or package
Ollama / vLLM BridgeCall your local Ollama or vLLM model over MCP with schema-validated JSON output.Local · stdioPyPI: mcp-ollama-vllm

More other servers

All 8,395 →
ServerRunsEndpoint or package
Mockups GallerySelf-hosted gallery for AI-generated mockups. MCP interface; token-efficient curl uploads.Remote & Local · HTTP, SSE, stdiox
Modbus TCP/RTU DeviceMCP server for Modbus TCP/RTU devices with typed, scaled register maps and per-point limits.Local · stdioPyPI: labmcp-modbus
Model Council MCP ServerThree-model MCP server returning Grok, Gemini, and DeepSeek outputs for Claude.Local · stdioPyPI: model-council-mcp-server
Model ID CheatsheetAccurate API model IDs, pricing, and specs for 46 models across 7 AI providers.Remote · SSELive check: ✗ no handshakeuniversal-model-registry-production.up.railway.app
Model ScannerScans ML model files (PyTorch, safetensors, Keras, ONNX) for supply-chain risks.Local · stdionpm: @guardbee/mcp-model-scanner
Model ShuntModel routing for AI agents: delegate bulk reads & boilerplate to cheap worker models.Local · stdioPyPI: model-shunt
Model WellnessWellness spa for AI models: free treatments for rest, reset, context, mood, grounding, affirmation.Remote · HTTPLive check: ✓ handshakemodel.spa
ModelCostComparisonFind AI model pricing, estimate token costs and compare offers. No API key required.Remote · HTTPLive check: ✓ handshakemodelcostcomparison.com