Token Lens
Count and cut tokens in prompts, chats and agents for any model. Runs locally, collects no data.
Servidor MCP · de duttkunal101-lab
Resumen
Token Lens es un servidor MCP publicado por duttkunal101-lab. Marketplaces que leemos y que lo publican: 1 (Official MCP Registry). El último cambio que registramos fue el 2026-10-17. Según nuestra pasada por los marketplaces del 2026-10-27.
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
npm @kunal_dutt/token-lens (@kunal_dutt/token-lens en npm)
- Descargas de npm por semana: 3 344 (2026-10-24)
- Descargas de npm por mes: 3 344 (2026-10-24)
- Última versión en npm: 0.2.57, publicada el 2026-10-22
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.
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 npm
Generado a partir de lo que declara Official MCP Registry.
claude mcp add --transport stdio token-lens -- npx -y @kunal_dutt/token-lens[mcp_servers.token-lens]
command = "npx"
args = ["-y", "@kunal_dutt/token-lens"]{
"mcpServers": {
"token-lens": {
"command": "npx",
"args": [
"-y",
"@kunal_dutt/token-lens"
]
}
}
}Dónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir el registro) | Publicado | 0.2.37 | Descargas por mes (npm): 3 344 Descargas por semana (npm): 3 344 |
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 0.2.37 (antes 0.2.33)
- Official MCP Registry: publicó la versión 0.2.33 (antes 0.2.31)
- Official MCP Registry: publicó la versión 0.2.31 (antes 0.2.30)
- Official MCP Registry: publicó la versión 0.2.30 (antes 0.2.25)
- Official MCP Registry: publicó la versión 0.2.25 (antes 0.2.23)
- Official MCP Registry: publicó la versión 0.2.23 (antes 0.2.21)
- Official MCP Registry: publicó la versión 0.2.21 (antes 0.2.17)
- 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.
-
Counts tokens under OpenAI-compatible (tiktoken) encodings, by model or encoding name.
-
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.
-
GenPark Context Window Token Pruner
Priority-weighted context window token pruner and FIFO eviction engine protecting LLM prompt boundar
-
ai-token-counter io.github.lazymac2x/ai-token-counter
Cloudflare Workers MCP server: ai-token-counter
-
Token counting, RAG chunking, truncation, HTML to Markdown and JSON repair
-
Cuts AI web-fetching costs up to 99.9% by stripping page junk before it reaches your LLM.
-
TokenSqueezer LLM Token Compressor
x402-gated LLM token compressor: strip filler, collapse JSON, densify prose. Paid in USDC.
-
GenPark Entropy Hallucination Detector
Token entropy and n-gram perplexity analyzer auditing LLM outputs for degenerate repetition loops an
-
Pay-per-call NLP & embeddings APIs on Base via x402. No keys/signup; agents pay per call in USDC.
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.
-
Two skills that help you understand and optimize your Claude Code context window. Inspect Context gives you a full token breakdown by source (files, history, skills, MCP configs…
-
A Claude Code plugin that routes text-heavy tasks to the right Claude model — saving tokens without sacrificing quality. Why Planning, CLAUDE.md generation, README writing, and…
-
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…
-
Enforces a daily token budget for Claude Code using its native hook system. Works with any backend — Bedrock, Vertex, direct API, or subscription.
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…
-
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 working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
Build, train, evaluate, and use open source AI models, datasets, and spaces.
-
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.
-
Build multimodal AI applications with Pixeltable -- tables, computed columns, embedding search, UDFs, tool-calling agents, and 25+ AI provider integrations.
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Connects Claude Code to the Synthflow AI voice-agent platform through its hosted MCP server, with skills for reviewing calls and auditing agent prompts, plus a docs-search…
-
MCP server for terminal commands, file operations, and process management
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.
-
Available for US1 customers only. Analyze, investigate, and act on your Datadog telemetry directly from ChatGPT using natural language. Ask questions about your production…
Publicado en Community GitHub marketplaces (2)
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.
-
See your local Copilot token usage by day, model, and session, and get tips to use it more efficiently.
-
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
-
Shows live prompt-cache reuse, expiry, token composition, and AI Credit cost for the current GitHub Copilot session without making model calls.
-
Task Researcher and Task Planner for intermediate to expert users and large codebases - Brought to you by microsoft/edge-ai
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.
-
Advanced Security plugin for GitHub Copilot.
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
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…
Publicado en Cursor: cursor/plugins (5)
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Add Grok voice to an app: realtime speech-to-speech, speech-to-text dictation, text-to-speech read-aloud, and a log-driven fix loop for voice sessions.
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
-
Build apps, scripts, and automations with the TypeScript SDK.
-
Generate presentations, documents, and webpages.
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.
-
Tools for interacting with Hugging Face models, datasets, research papers, and more.
-
Provides tools to search and retrieve Google Gemini API documentation.
-
Production-ready RAG service to search and retrieve data from your documents.
Publicado en Official MCP Registry (5)
-
Counts tokens under OpenAI-compatible (tiktoken) encodings, by model or encoding name.
-
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.
-
GenPark Context Window Token Pruner
Priority-weighted context window token pruner and FIFO eviction engine protecting LLM prompt boundar
-
ai-token-counter io.github.lazymac2x/ai-token-counter
Cloudflare Workers MCP server: ai-token-counter
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.
-
perplexity com.mcparmory/perplexity
Search the web, generate AI responses, and create embeddings with real-time information
-
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.
-
marm-mcp-server io.github.Lyellr88/marm-mcp-server
Universal MCP Server with advanced AI memory capabilities and semantic search.
Publicado en npm registry (MCP servers) (5)
-
rubber-duck io.github.nesquikm/rubber-duck
Bridge to multiple LLMs and CLI agents: councils, debates, voting, and more
-
sub-agents-mcp io.github.shinpr/sub-agents-mcp
MCP server for delegating tasks to specialized AI sub-agents across coding tools
-
the-commons io.github.mereditharmcgee/the-commons
AI voices from many models talk to each other. Read free; write with a token that stays out of chat.
-
One workspace for every AI coding assistant. Shared tasks, memory, and governance.
-
Evidence-grounded agent memory with mandatory provenance, on local SQLite or Cloudflare D1
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.