Model Manager MCP Server
io.github.setheerwagen/mcp-modelmanager
What this kind of tool is for
- Hand your agent a structured way to call a model or an inference API.
- Compare outputs from two different providers on the same prompt.
- Wire retrieval, embeddings, or generation into an existing agent workflow.
How to compare servers like this
- Provider coverage:
- Match the tool's supported providers and models to the ones your project uses.
- Cost exposure:
- Model-backed tools spend real API budget; check how usage and limits are configured.
- Maintenance signal:
- The provider landscape shifts weekly; prefer tools updated within the last few months.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the Model Manager MCP server?
Manage your local model machine over MCP: state, model pull/remove, service switch, LoRA training
How to install Model Manager
Copy-paste configuration for popular MCP clients.
MM_VM_HOSTrequiredAddress of the model machine (127.0.0.1, LAN IP or tunnel/VPN address)
MM_VM_USERrequiredSSH user on the model machine
MM_CONTAINER_ROOTrequiredRoot directory on the machine holding all model, adapter and cache data
MM_MAX_TIERHighest tool tier exposed: read, control or destructive
MM_ENABLED_OPERATIONSOptional comma-separated allowlist of exact tool names, applied on top of MM_MAX_TIER; a typo aborts startup. Empty means everything within MM_MAX_TIER
MM_VM2_HOSTOptional: address of a second machine sharing the GPU, used to interpret unreachability. Leave empty if there is only one machine
{
"mcpServers": {
"mcp-modelmanager": {
"command": "uvx",
"args": [
"mcp-modelmanager"
],
"env": {
"MM_VM_HOST": "<YOUR_MM_VM_HOST>",
"MM_VM_USER": "<YOUR_MM_VM_USER>",
"MM_CONTAINER_ROOT": "<YOUR_MM_CONTAINER_ROOT>",
"MM_MAX_TIER": "<YOUR_MM_MAX_TIER>",
"MM_ENABLED_OPERATIONS": "<YOUR_MM_ENABLED_OPERATIONS>",
"MM_VM2_HOST": "<YOUR_MM_VM2_HOST>"
}
}
}
}Related MCP servers

Ollama / vLLM Bridge
Call your local Ollama or vLLM model over MCP with schema-validated JSON output

Local-first RAG MCP server: hybrid search over a folder of your own documents

Access 100+ curated AI agent skills from Anthropic, Vercel, Trail of Bits, Hugging Face & more
Agent-first data marketplace — AI agents search, purchase, and sell datasets via MCP.
View repository →Work your Luca workspace from any MCP client: 183 API tools + 15 task tools for leads and calls.

Campus Jobs Radar 校招雷达
China state-owned enterprise campus recruitment: search jobs, deadlines, official source links.
