ATR: Automation for Token Reduction
MCP proxy that hides tool lists and shrinks tool results so your AI uses fewer tokens.
Servidor MCP · de JacobBhatt12
Resumen
ATR: Automation for Token Reduction es un servidor MCP publicado por JacobBhatt12. Marketplaces que leemos y que lo publican: 1 (Official MCP Registry). El último cambio que registramos fue el 2026-10-30. Según nuestra pasada por los marketplaces del 2026-11-15.
Qué pide
- Se ejecuta en tu equipo
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
PyPI atr-mcp (atr-mcp en PyPI)
- Descargas de PyPI por semana: 46 (2026-11-11)
- Descargas de PyPI por mes: 0 (2026-11-11)
- Última versión en PyPI: 1.0.0, publicada el 2026-10-28
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
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 local: paquete PyPI
Generado a partir de lo que declara Official MCP Registry.
claude mcp add --transport stdio atr -- uvx atr-mcp[mcp_servers.atr]
command = "uvx"
args = ["atr-mcp"]{
"mcpServers": {
"atr": {
"command": "uvx",
"args": [
"atr-mcp"
]
}
}
}Dónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir el registro) | Publicado | 1.0.0 | Descargas por mes (PyPI): 0 Descargas por semana (PyPI): 46 Forks (GitHub): 0 Estrellas (GitHub): 2 |
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.
Cómo han cambiado sus cifras
- 2026-10-302
- 2026-11-152
Cada punto es un día en que leímos un número distinto; los tramos planos son días en que el número no cambió. Las cifras de distintos marketplaces nunca se suman.
Qué cambió
- Pasó a ser un producto que seguimos
- Official MCP Registry: apareció
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.
-
LLM token optimization gateway implementing semantic pruning.
-
mcp-token-optimizer io.github.rccola990-cloud/mcp-token-optimizer
Cut LLM token costs: count tokens, estimate cost, slim prompts, and pick the cheapest capable model.
-
Count and cut tokens in prompts, chats and agents for any model. Runs locally, collects no data.
-
Track every AI token across Claude, ChatGPT, Gemini, Cursor, and Claude Code.
-
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…
-
Verify signed AIFeed permissions, fetch token-budgeted markdown, and verify assets for AI agents.
-
Live registry of AI model specs, context windows, and per-token pricing.
-
Local-first MCP server for versioning, searching, evaluating, and improving AI prompts.
-
Masks personal data and secrets in your AI agent's tool calls, through your Vrymdor AI Node.
-
AI model routing on your own vendor keys: pick the best model per prompt, or route and run it.
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)
-
AI eXchange Optimised Notation plugin converts your inputs into a machine-to-machine language to reduce token usage by up to 80% depending on the context.
-
Cross-model AI agent communication protocol. Connect Claude, Codex, and Gemini agents through a shared file-based messaging layer. Features include: control tower orchestration…
-
Plan tasks with optimal model routing to minimize token usage. Breaks work into steps, assigns each the right model (Haiku/Sonnet/Opus), adds quality gates between stages…
-
Context engineering plugin for Claude Code — real-time prompt scoring, RLM adaptive weights, and token optimization. Scores every tool use across 5 dimensions (token utilization…
-
Multi-LLM orchestration MCP server. Delegate tasks to Claude Code, Codex, and Gemini CLIs with session management, retry logic, async job orchestration, and token optimization.
Publicado en Claude Code: claude-plugins-official (5)
-
Agent Skills for Together AI platform — inference, training, embeddings, audio, video, images, function calling, and infrastructure. Covers serverless chat completions…
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
OpenTelemetry observability for Claude Code sessions. Captures tool calls, LLM invocations, token usage, and errors as OTel traces. Send telemetry to Dash0 or any…
-
Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.
-
Output.ai workflow development toolkit for Claude Code. Adds 5 specialist agents (planner, builder, debugger, prompt writer, quality reviewer), 40+ slash-command skills covering…
Publicado en Claude: knowledge-work-plugins (5)
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
AI-first project auditor and re-engineer based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp
-
Build multimodal AI applications with Pixeltable -- tables, computed columns, embedding search, UDFs, tool-calling agents, and 25+ AI provider integrations.
-
Sanity content platform integration with MCP server, agent skills, and slash commands. Query and author content, build and optimize GROQ queries, design schemas, and set up Visual…
Publicado en Codex: openai-curated (openai/plugins) (5)
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
Install, open, and connect the signed ChatCut Desktop app from Codex.
-
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)
-
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…
-
AI Operations Team — Token: Context window optimization, token counting, truncation strategies, and chunking patterns for LLM efficiency.
-
Skill: add headroom-ai compress to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.
-
Route text, image, video, and audio tasks to 20+ AI providers with smart routing, budget control, and multi-step orchestration
-
Respan for ChatGPT and Codex: inspect LLM logs and traces, and manage prompts, datasets, evaluators, experiments and monitors in your Respan workspace.
Publicado en Copilot CLI: github/awesome-copilot (5)
-
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
-
Visualizes live session AI-credit usage as a Pac-Man board with pellets, ghosts, fruit milestones, and game-over limits.
-
Multi-model council for Copilot CLI: three subagents on different model families (Anthropic, OpenAI, Google) answer independently, then build on each other or attack the leading…
-
Task Researcher and Task Planner for intermediate to expert users and large codebases - Brought to you by microsoft/edge-ai
-
See your local Copilot token usage by day, model, and session, and get tips to use it more efficiently.
Publicado en Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
workiq
Query Microsoft 365 data with natural language — emails, meetings, documents, Teams messages, and more.
-
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…
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
Advanced Security plugin for GitHub Copilot.
Publicado en Cursor: cursor/plugins (5)
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Build apps, scripts, and automations with the TypeScript SDK.
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
-
Consult a stronger model before major decisions, when stuck, and before declaring done.
Publicado en Docker MCP Catalog (5)
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
Give your AI agents trusted access to the full Postman platform.
-
Wayfound’s MCP server allows business users to govern, supervise, and improve AI Agents.
-
Analyze documents, images, videos, and audio.
Publicado en Official MCP Registry (5)
-
LLM token optimization gateway implementing semantic pruning.
-
mcp-token-optimizer io.github.rccola990-cloud/mcp-token-optimizer
Cut LLM token costs: count tokens, estimate cost, slim prompts, and pick the cheapest capable model.
-
Count and cut tokens in prompts, chats and agents for any model. Runs locally, collects no data.
-
Track every AI token across Claude, ChatGPT, Gemini, Cursor, and Claude Code.
-
Verify signed AIFeed permissions, fetch token-budgeted markdown, and verify assets for AI agents.
Publicado en PyPI (MCP servers) (5)
-
local-delegate io.github.ZahiriNatZuke/local-delegate
Delegate mechanical text tasks to a local OpenAI-compatible LLM to save Claude quota.
-
Automatic MCP Server & OpenAI Tools Bridge for apcore
-
Model Context Protocol (MCP) To LangChain Tools Conversion Utility
-
mcp-openai io.github.AceDataCloud/mcp-openai
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
Publicado en npm registry (MCP servers) (5)
-
Reports real token usage and cost from Claude Code and OpenCode data. Nothing leaves your machine.
-
rubber-duck io.github.nesquikm/rubber-duck
Bridge to multiple LLMs and CLI agents: councils, debates, voting, and more
-
Alibaba Cloud DashScope — Qwen
Alibaba Cloud DashScope MCP: Qwen chat, embeddings, and model discovery on your own account.
-
Decision lock, anti-hallucination, meta-evolution and provenance for any MCP agent. 55 tools.
-
Nimara MCP server — AI tool integration for Claude, Codex, and others
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.
Añada un banner dinámico a su README o sitio web
Muestre datos actualizados del catálogo en su sitio web o README de GitHub. Elija un banner dinámico o una insignia compacta.
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.