tokcalc MCP Server
LLM serving capacity planner: VRAM, KV cache, GPU topology, latency, and cost.
Servidor MCP · de stevecrates489-commits
Resumo
tokcalc MCP Server é um servidor MCP publicado por stevecrates489-commits. Marketplaces que lemos e que o listam: 1 (Official MCP Registry). Vimos pela primeira vez em 2026-10-11 e não registramos mudanças desde então. Conforme nossa passagem pelos marketplaces em 2026-10-15.
O que pede
- Roda remotamente
Nenhum dos marketplaces que lemos publica as ferramentas ou as configurações que ele pede.
O que declara, pede e executa, por completo
Instale apenas plugins de desenvolvedores em quem você confia. Mostramos o que os marketplaces publicam e não testamos plugins.
Pacote
npm @tokcalc/mcp-server (@tokcalc/mcp-server no npm)
- Downloads do npm por semana: 122 (2026-10-12)
- Downloads do npm por mês: 3 719 (2026-10-12)
- Última versão no npm: 0.3.3, publicada em 2026-10-03
Nenhuma vulnerabilidade conhecida no OSV para 0.3.3 (verificado em 2026-10-13)
Os dados do npm vêm do registro público do npm (registry.npmjs.org, api.npmjs.org). Cada número é do próprio registro e nunca é somado a outro. Um registro que não publica um número não mostra nenhum: sem número não é zero. Os registros de vulnerabilidades vêm do OSV.dev (CC BY 4.0) e dizem respeito apenas à versão declarada; uma listagem sem versão declarada não recebe resposta. Não analisamos código.
Funciona com
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
Um link de um clique abre o cliente, que pede confirmação antes de adicionar o servidor.
Pelos marketplaces que o listam e pelo transporte MCP que declara, conforme cada cliente documenta. Não testamos plugins.
Conectar
Comandos e configurações gerados apenas a partir do que os marketplaces declaram. Não os executamos por você e não testamos plugins.
Como servidor MCP remoto
Gerado a partir do que Official MCP Registry declara.
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"
}
}
}Onde está publicado
| Marketplace | Status | Versão | Números | Verificado | Visto pela primeira vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir o registro) | Listado | 0.3.3 | Downloads por mês (npm): 3 719 Downloads por semana (npm): 122 Forks (GitHub): 0 Estrelas (GitHub): 1 |
Sem marcação |
Cada número é do próprio marketplace e nunca é somado entre marketplaces. Um marketplace que não publica números não mostra nenhum: sem número não é zero.
O que mudou
Nada mudou neste plugin desde que começamos a acompanhá-lo.
Plugins semelhantes
Produtos cujos próprios nomes, descrições, ferramentas e skills são os mais próximos deste pelo significado, em todos os marketplaces que lemos. A proximidade é ordenada apenas dentro desta 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 semelhantes por marketplace
A mesma pergunta feita a cada marketplace separadamente: existe lá um equivalente deste plugin?
Listado em 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.
Listado em 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.
Listado em 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…
Listado em 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.
Listado em 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.
Listado em 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…
Listado em 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.
Listado em 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.
Listado em 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.
Listado em 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 pelo significado, não por código ou repositório em comum: plugins semelhantes continuam sendo produtos distintos, e isto não é uma avaliação nem uma recomendação.
Quer esta marca no seu plugin em nosso catálogo?
Prove que o mantém com um arquivo no repositório, um arquivo no seu domínio ou um registro DNS, e você poderá mostrar esta marca na ficha, com banners ao vivo para o seu site e o README. Como funciona a verificação
Você também recebe alertas quando um marketplace o publica, o remove, muda a marca de verificado ou o que ele pede, e o endpoint remoto passa a ser monitorado como um serviço web.
Dados de Official MCP Registry. Os números vêm das nossas próprias passagens regulares pelos marketplaces, última leitura em . Não publicamos dados de contato dos editores de plugins.