Model Manager
Manage your local model machine over MCP: state, model pull/remove, service switch, LoRA training
Servidor MCP · de setheerwagen
Resumen
Model Manager es un servidor MCP publicado por setheerwagen. Marketplaces que leemos y que lo publican: 1 (Official MCP Registry). El último cambio que registramos fue el 2026-10-13. Según nuestra pasada por los marketplaces del 2026-10-21.
Qué pide
- Se ejecuta en tu equipo
- Ajustes: 6
Requiere: MM_CONTAINER_ROOT, MM_VM_HOST, MM_VM_USER
Lo que declara, pide y ejecuta, completo
Instala solo plugins de desarrolladores en los que confíes. Mostramos lo que publican los marketplaces y no probamos plugins.
Paquete
PyPI mcp-modelmanager (mcp-modelmanager en PyPI)
- Descargas de PyPI por semana: 23 (2026-10-13)
- Descargas de PyPI por mes: 227 (2026-10-13)
- Última versión en PyPI: 1.0.2, publicada el 2026-09-08
- La versión declarada 1.0.3 no figura en PyPI
Los datos de PyPI proceden de pypi.org y las descargas de PyPI de pypistats.org. Cada cifra es del propio registro y nunca se suma a otra. Un registro que no publica una cifra no muestra ninguna: sin cifra no es cero.
Funciona con
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
Según los marketplaces que lo listan y el transporte MCP que declara, tal como lo documenta cada cliente. No probamos plugins.
Conectar
Comandos y configuraciones generados solo a partir de lo que declaran sus marketplaces. No los ejecutamos por ti ni probamos plugins.
Como servidor MCP local: paquete PyPI
Generado a partir de lo que declara Official MCP Registry.
claude mcp add --env "MM_CONTAINER_ROOT=<YOUR_MM_CONTAINER_ROOT>" --env "MM_VM_HOST=<YOUR_MM_VM_HOST>" --env "MM_VM_USER=<YOUR_MM_VM_USER>" --transport stdio mcp-modelmanager -- uvx mcp-modelmanager[mcp_servers.mcp-modelmanager]
command = "uvx"
args = ["mcp-modelmanager"]
[mcp_servers.mcp-modelmanager.env]
MM_CONTAINER_ROOT = "<YOUR_MM_CONTAINER_ROOT>"
MM_VM_HOST = "<YOUR_MM_VM_HOST>"
MM_VM_USER = "<YOUR_MM_VM_USER>"{
"mcpServers": {
"mcp-modelmanager": {
"command": "uvx",
"args": [
"mcp-modelmanager"
],
"env": {
"MM_CONTAINER_ROOT": "<YOUR_MM_CONTAINER_ROOT>",
"MM_VM_HOST": "<YOUR_MM_VM_HOST>",
"MM_VM_USER": "<YOUR_MM_VM_USER>"
}
}
}
}Sustituya los valores entre corchetes angulares por los suyos. Mostramos los nombres de los ajustes, nunca valores.
Ajustes opcionales que también indica: MM_ENABLED_OPERATIONS, MM_MAX_TIER, MM_VM2_HOST.
Dónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir el registro) | Publicado | 1.0.3 | Descargas por mes (PyPI): 227 Descargas por semana (PyPI): 23 Forks (GitHub): 0 Estrellas (GitHub): 0 |
Sin marca |
Cada cifra es del propio marketplace y nunca se suma entre marketplaces. Un marketplace que no publica cifras no muestra ninguna: sin número no es cero.
Qué cambió
- Official MCP Registry: publicó la versión 1.0.3 (antes 1.0.2)
Plugins similares
Productos cuyos propios nombres, descripciones, herramientas y skills son los más cercanos a este por su significado, en todos los marketplaces que leemos. La cercanía se ordena solo dentro de esta lista.
-
replicate com.mcparmory/replicate
Run AI models, create deployments, and manage predictions via cloud API
-
Train, track and query models on a running dashAI instance. Read-oriented, no delete tools.
-
runcomfy-mcp io.github.runcomfy-com/runcomfy-mcp
Remote MCP for RunComfy: ComfyUI deployments, hosted models, LoRA training. 31 tools.
-
Hugging Face Hub MCP — models, datasets, spaces
-
Run DeepInfra inference, list models and read account rate limits.
-
Manage your Onde Inference account and models: apps, model catalog, fine-tuned GGUF deploys.
-
ModelsLab v8 generation APIs: discover models, providers and endpoints, then run them.
-
SSH Model Context Protocol Server - Enable SSH functionality for AI models
-
Model Context Protocol server for awesome-copilot agents and collections
-
Run fal.ai models, poll the inference queue and read model schemas.
Plugins similares por marketplace
La misma pregunta a cada marketplace por separado: ¿hay allí un equivalente de este plugin?
Publicado en Claude Code: claude-plugins-community (5)
-
agent-discover io.github.keshrath/agent-discover
Find, install and enable MCP servers mid-session on any host, with consent and tool pinning
-
mdk-mcp-server io.github.SAP/mdk-mcp-server
Model Context Protocol (MCP) server for AI-assisted development of MDK applications.
-
eu-ai-act-compliance-mcp io.github.CSOAI-ORG/eu-ai-act-compliance-mcp
Eu Ai Act Compliance MCP Server by MEOK AI Labs
-
Claude model selection advisor — recommends optimal model for each task via shell hook. Zero attack surface.
-
Search, browse, and install MCP servers, agents, skills, prompts, and plugins from the conduitAI catalog — directly from Claude Code.
Publicado en Claude Code: claude-plugins-official (5)
-
mdk-mcp-server io.github.SAP/mdk-mcp-server
Model Context Protocol (MCP) server for AI-assisted development of MDK applications.
-
firebase-mcp io.github.firebase/firebase-mcp
Gives AI development tools Firebase-specific capabilities and expertise.
-
Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered…
-
Build, train, and deploy AI models with deep AWS AI/ML expertise brought directly into your coding assistants, covering the surface area of Amazon SageMaker AI.
-
mcp-server io.github.cap-js/mcp-server
Model Context Protocol (MCP) server for AI-assisted development of CAP applications.
Publicado en Claude: knowledge-work-plugins (5)
-
MCP server for terminal commands, file operations, and process management
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Figma design platform integration. Access design files, extract component information, read design tokens, and translate designs into code. Bridge the gap between design and…
-
Hosted MCP server for AI-assisted Grafana Cloud observability — no local installation required.
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
Publicado en Codex: openai-curated (openai/plugins) (5)
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
Cloudflare platform plugin with curated skills for Workers, Wrangler, and Agents SDK plus the official Cloudflare API MCP server.
-
Comprehensive skill for the entire Temporal lifecycle — developing applications, using the Temporal CLI, running and managing Temporal Server, and working with Temporal Cloud.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
Publicado en Community GitHub marketplaces (5)
-
Build high-quality MCP servers for LLM integrations
-
Cloud AI inference, training, conversion, and GPU workflows.
-
Build agents, MCP servers and tool-using workflows.
-
An MCP server that stores Copilot customizations from the Awesome Copilot repository
-
Complete toolkit for building Model Context Protocol (MCP) servers in Python using the official SDK with FastMCP. Includes instructions for best practices, a prompt for generating…
Publicado en Copilot CLI: github/awesome-copilot (5)
-
Complete toolkit for building Model Context Protocol (MCP) servers in Go using the official github.com/modelcontextprotocol/go-sdk. Includes instructions for best practices, a…
-
Complete toolkit for building Model Context Protocol (MCP) servers in TypeScript/Node.js using the official SDK. Includes instructions for best practices, a prompt for generating…
-
Complete toolkit for building Model Context Protocol (MCP) servers in Kotlin using the official io.modelcontextprotocol:kotlin-sdk library. Includes instructions for best…
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
-
Figma design platform integration. Access design files, extract component information, read design tokens, and translate designs into code. Bridge the gap between design and…
Publicado en Copilot CLI: github/copilot-plugins (5)
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
mcp-apps
Generate MCP App widgets for MCP tools. Produces self-contained HTML widgets using the MCP Apps protocol.
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
-
Build and manage Microsoft Dataverse solutions using natural language. Includes table/column creation, solution lifecycle, data operations, and MCP server configuration.
Publicado en Cursor: cursor/plugins (5)
-
Let Grok Bot reach MCP servers on your private Tailscale network. On your own tailnet it joins as one tag:grokbot device; on your team's company tailnet, turned on by a team…
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
Build apps, scripts, and automations with the TypeScript SDK.
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
Publicado en Docker MCP Catalog (5)
-
A universal MCP (Model Context Protocol) server to integrate any API with Claude Desktop using only Docker configurations.
-
Seamless interaction with Novita AI platform resources.
-
Discover and connect to a curated marketplace of MCP servers for extending AI agent capabilities.
-
A unified MCP proxy that aggregates multiple MCP servers into one interface, enabling seamless tool discovery and management across all your AI interactions. Manage all your MCP…
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
Publicado en Official MCP Registry (5)
-
replicate com.mcparmory/replicate
Run AI models, create deployments, and manage predictions via cloud API
-
Train, track and query models on a running dashAI instance. Read-oriented, no delete tools.
-
runcomfy-mcp io.github.runcomfy-com/runcomfy-mcp
Remote MCP for RunComfy: ComfyUI deployments, hosted models, LoRA training. 31 tools.
-
Hugging Face Hub MCP — models, datasets, spaces
-
Run DeepInfra inference, list models and read account rate limits.
Publicado en npm registry (MCP servers) (5)
-
Browser-local and CLI static evidence for deployed AI model artifacts.
-
easytable-mcp io.github.chrischall/easytable-mcp
easyTable restaurant reservations for Claude — availability, and create/modify/cancel bookings
-
Gives AI agents eyes and hands into running React Native apps: logs, REPL, tap, screenshots
-
Read-only MCP server exposing the dsh-plugin-certification registry for DeepSeek Harness plugins.
-
devkit-for-strapi-mcp io.github.PaulRichez/devkit-for-strapi-mcp
Strapi codebase intelligence for AI agents (not content CRUD): real UIDs, schemas, refs, refactors.
Encontrados por significado, no por código ni repositorio compartidos: los plugins similares siguen siendo productos distintos, y esto no es una reseña ni una recomendación.
¿Quieres esta marca para tu plugin en nuestro catálogo?
Demuestra que lo mantienes con un archivo en su repositorio, un archivo en tu dominio o un registro DNS, y podrás mostrar esta marca en la ficha, con banners en vivo para tu web y tu README. Cómo funciona la verificación
Además recibirás avisos cuando un marketplace lo publique, lo retire, cambie su marca verificada o lo que pide, y su endpoint remoto quedará monitorizado como un servicio web.
Datos de Official MCP Registry. Las cifras proceden de nuestros propios recorridos periódicos por los marketplaces, leída por última vez el . No publicamos datos de contacto de los editores de plugins.