tokcalc MCP Server
LLM serving capacity planner: VRAM, KV cache, GPU topology, latency, and cost.
Servidor MCP · de stevecrates489-commits
Resumen
tokcalc MCP Server es un servidor MCP publicado por stevecrates489-commits. Marketplaces que leemos y que lo publican: 1 (Official MCP Registry). Lo vimos por primera vez el 2026-10-11 y desde entonces no hemos registrado cambios. Según nuestra pasada por los marketplaces del 2026-10-15.
Qué pide
- Se ejecuta en remoto
Ninguno de los marketplaces que leemos publica sus herramientas ni los ajustes que pide.
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
npm @tokcalc/mcp-server (@tokcalc/mcp-server en npm)
- Descargas de npm por semana: 122 (2026-10-12)
- Descargas de npm por mes: 3 719 (2026-10-12)
- Última versión en npm: 0.3.3, publicada el 2026-10-03
Sin vulnerabilidades conocidas en OSV para 0.3.3 (comprobado el 2026-10-13)
Los datos de npm proceden del registro público de npm (registry.npmjs.org, api.npmjs.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. Los registros de vulnerabilidades proceden de OSV.dev (CC BY 4.0) y solo se refieren a la versión declarada; un listado sin versión declarada no recibe respuesta. No analizamos código.
Funciona con
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
Un enlace de un clic abre el cliente, que pide confirmación antes de añadir el servidor.
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 remoto
Generado a partir de lo que declara Official MCP Registry.
claude mcp add --transport http tokcalc https://tokcalc.vercel.app/api/mcp[mcp_servers.tokcalc]
url = "https://tokcalc.vercel.app/api/mcp"{
"mcpServers": {
"tokcalc": {
"url": "https://tokcalc.vercel.app/api/mcp"
}
}
}Dónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir el registro) | Publicado | 0.3.3 | Descargas por mes (npm): 3 719 Descargas por semana (npm): 122 Forks (GitHub): 0 Estrellas (GitHub): 1 |
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
Nada ha cambiado en este plugin desde que lo seguimos.
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.
-
Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only.
-
Run DeepInfra inference, list models and read account rate limits.
-
Compare LLM API and cloud compute pricing, estimate workload costs, pick a model within budget.
-
Does an LLM fit on your GPU? VRAM, KV cache and GPU count for any Hugging Face model.
-
Audit an MCP config, price a model, size a GPU, explain network config drift. Key-free.
-
VMware Private AI (GPU & Model Serving)
VMware Private AI (NVIDIA): GPU inventory, vGPU profiles, utilization, model serving — 17 tools
-
Provision private AI model endpoints on dedicated GPUs (Llama, Qwen, Mistral). Pay per minute.
-
Run and compare LLMs, generate images and video, with the real yen cost returned per call.
-
Read-only: which local LLMs a GPU or Mac can run - VRAM fit, tokens/sec, model specs.
-
ToolDrift: Current AI model pricing and which models coding tools route to.
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)
-
Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered…
-
Synthetic monitoring for LLM inference endpoints. Probe TTFT, latency, throughput, and errors across OpenAI, Anthropic, Google, Azure, Bedrock, and any OpenAI-compatible server.
-
Claude model selection advisor — recommends optimal model for each task via shell hook. Zero attack surface.
-
together-ai-skills
A collection of skills that teach coding agents how to use the Together AI platform, including chat completions, image generation, video, audio, embeddings, fine-tuning, batch…
-
Arquestra — Scientific Computing Orchestration
AI orchestration for computational chemistry and HPC workflows.
Publicado en Claude Code: claude-plugins-official (5)
-
Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered…
-
AMD's verified Agent Skills in one plugin: route image/audio through local AI on Ryzen AI, serve LLMs on AMD Instinct GPUs with vLLM, optimize inference throughput with Hyperloom…
-
Agent Skills for Together AI platform — inference, training, embeddings, audio, video, images, function calling, and infrastructure. Covers serverless chat completions…
-
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.
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
Publicado en Claude: knowledge-work-plugins (5)
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
Agent skills for Qdrant vector search covering scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage across…
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Hosted MCP server for AI-assisted Grafana Cloud observability — no local installation required.
-
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 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.
-
Available for US1 customers only. Analyze, investigate, and act on your Datadog telemetry directly from ChatGPT using natural language. Ask questions about your production…
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Cloudflare platform plugin with curated skills for Workers, Wrangler, and Agents SDK plus the official Cloudflare API MCP server.
Publicado en Community GitHub marketplaces (5)
-
AI data center design engine — size, validate, and lay out AI/GPU data centers (NVIDIA Hopper / Blackwell / Vera Rubin) with deterministic rack, PUE, MVA, cost, and layout outputs…
-
Deploy LLM models to Kubernetes using the KAITO kubectl plugin. Guides you through model selection, GPU sizing, and generates ready-to-run kubectl kaito deploy commands.
-
Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered…
-
Cut LLM API spend via model routing, prompt caching, prompt compression, and per-feature cost observability. Use when AI costs are too high, choosing between models, or launching…
-
Tuning Engines - Governed AI Runtime
Govern model, agent, skill, and MCP workflows with policy, approvals, traces, and usage analytics.
Publicado en Copilot CLI: github/awesome-copilot (5)
-
Visualizes live session AI-credit usage as a Pac-Man board with pellets, ghosts, fruit milestones, and game-over limits.
-
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
-
See your local Copilot token usage by day, model, and session, and get tips to use it more efficiently.
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
-
Transform Claude into an Azure expert. This plugin integrates the Azure MCP server and specialized Azure skills to move beyond generic advice. It enables Claude to perform…
Publicado en Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
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…
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
-
mcp-apps
Generate MCP App widgets for MCP tools. Produces self-contained HTML widgets using the MCP Apps protocol.
-
workiq
Query Microsoft 365 data with natural language — emails, meetings, documents, Teams messages, and more.
Publicado en Cursor: cursor/plugins (5)
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
Let Grok Bot reach MCP servers on your private Tailscale network. Sign in to Tailscale to connect your tailnet; Grok Bot joins it as one tagged device and only reaches the hosts…
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Build apps, scripts, and automations with the TypeScript SDK.
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
Publicado en Docker MCP Catalog (5)
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
Discover and connect to a curated marketplace of MCP servers for extending AI agent capabilities.
-
Seamless interaction with Novita AI platform resources.
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
A universal MCP (Model Context Protocol) server to integrate any API with Claude Desktop using only Docker configurations.
Publicado en Official MCP Registry (5)
-
Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only.
-
Run DeepInfra inference, list models and read account rate limits.
-
Compare LLM API and cloud compute pricing, estimate workload costs, pick a model within budget.
-
Does an LLM fit on your GPU? VRAM, KV cache and GPU count for any Hugging Face model.
-
Audit an MCP config, price a model, size a GPU, explain network config drift. Key-free.
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.