sqz-cli
Pre-injection context compression and session deduplication for AI coding agents: squeeze tool output, code, JSON and logs before they reach the LLM
Servidor MCP · de ojuschugh1
Resumen
sqz-cli es un servidor MCP publicado por ojuschugh1. Marketplaces que leemos y que lo publican: 1 (npm registry (MCP servers)). El último cambio que registramos fue el 2026-11-02. Según nuestra pasada por los marketplaces del 2026-11-04.
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
- Descargas de npm por semana: 103 (2026-11-02)
- Descargas de npm por mes: 898 (2026-11-02)
- Última versión en npm: 2.1.1, publicada el 2026-10-11
Sin vulnerabilidades conocidas en OSV para 2.1.1 (comprobado el 2026-11-02)
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.
Conectar
No hay datos para un comando automático: lo que declaran sus marketplaces no dice de forma inequívoca cómo conectarlo.
Dónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| npm registry (MCP servers) (Abrir en npm) | Publicado | 2.1.1 | Descargas por mes (npm): 898 Descargas por semana (npm): 103 Forks (GitHub): 43 Estrellas (GitHub): 675 |
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
- 2026-10-1744
- 2026-10-2043
- 2026-11-0343
- 2026-10-17649
- 2026-10-18651
- 2026-10-19652
- 2026-10-20656
- 2026-10-22660
- 2026-10-24662
- 2026-10-27666
- 2026-10-28671
- 2026-10-30673
- 2026-10-31674
- 2026-11-01675
- 2026-11-03675
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
Nada ha cambiado en este plugin desde que lo seguimos.
Posiblemente el mismo plugin
Fichas que comparten una señal con esta, pero no lo suficiente para tratarlas como el mismo producto.
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.
-
Pre-injection context compression for coding agents. Zero LLM calls, zero telemetry, offline-safe.
-
air io.github.10iii/air
AI-optimized tool output compression for read, grep, diff, bash, test, web, search, and more
-
Automatically compresses verbose CLI output (git, docker, npm, terraform, kubectl, etc.) to save tokens in Claude Code sessions. 21 specialized processors with content-aware…
-
Compress coding-agent context ~64%. Hosted Neural Keep MCP for Cursor/Claude/Codex.
-
Persistent memory and session intelligence for AI coding assistants. Zero config.
-
Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search
-
Read-only semantic filtering, code search, log triage and traceable evidence for AI agents.
-
Deterministic dev tools for AI agents over MCP: hashing, encoding, formatting, codegen, and more.
-
Local context compression for Claude Code workflows, including structured data and debug-heavy output.
-
prompt-squeeze builds prompt-cost discipline into Claude Code via three surfaces: /squeeze skill that compresses a verbose prompt into a token-efficient equivalent and renders a…
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)
-
Automatically compresses verbose CLI output (git, docker, npm, terraform, kubectl, etc.) to save tokens in Claude Code sessions. 21 specialized processors with content-aware…
-
prompt-squeeze builds prompt-cost discipline into Claude Code via three surfaces: /squeeze skill that compresses a verbose prompt into a token-efficient equivalent and renders a…
-
Automatic context window monitoring and smart compaction for Claude Code. Zero dependencies. Context Guardian (cg) watches your context window usage in real time via a statusline…
-
Audit and optimize Claude Code context window usage. Runs a 9-phase analysis covering plugins, hooks, CLAUDE.md cascade, MCP servers, environment settings, zombie process…
-
Context optimization + safe code execution - Query docs (90% token reduction), orchestrate multi-round exploration, and execute code with Docker isolation using RLM Runtime
Publicado en Claude Code: claude-plugins-official (5)
-
OpenTelemetry observability for Claude Code sessions. Captures tool calls, LLM invocations, token usage, and errors as OTel traces. Send telemetry to Dash0 or any…
-
Langfuse observability plugin for Claude Code — captures and exports traces, spans, and session telemetry from Claude Code to Langfuse for LLM monitoring, debugging, and evaluation
-
MCP server for terminal commands, file operations, and process management
-
New Relic observability intelligence for Claude Code. Investigate APM performance, analyze cloud costs, debug Kubernetes, write NRQL queries, and respond to alerts — all from your…
-
Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain
Publicado en Claude: knowledge-work-plugins (5)
-
MCP server for terminal commands, file operations, and process management
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
Bring Qodo's codebase intelligence, coding standards, and code review into your coding agent.
-
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF…
-
Use Datadog directly in Claude Code through a preconfigured Datadog MCP server. Query logs, metrics, traces, dashboards, and more through natural conversation. This plugin is in…
Publicado en Codex: openai-curated (openai/plugins) (5)
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
AI-powered code review in Codex, powered by CodeRabbit.
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
Inspect repositories, triage pull requests and issues, debug CI, and publish changes through a hybrid GitHub connector and CLI workflow.
Publicado en Community GitHub marketplaces (5)
-
Automatically compresses verbose CLI output (git, docker, npm, terraform, kubectl, etc.) to save tokens in Claude Code sessions. 21 specialized processors with content-aware…
-
Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search
-
Local context compression for Claude Code workflows, including structured data and debug-heavy output.
-
Flightdeck observability for Claude Code sessions — streams every LLM call, tool use, and MCP event to a self-hosted dashboard.
-
Filter noisy command output before it reaches the model; raw output stays recoverable. Skill + MCP server.
Publicado en Copilot CLI: github/awesome-copilot (5)
-
Shows live prompt-cache reuse, expiry, token composition, and AI Credit cost for the current GitHub Copilot session without making model calls.
-
Use Datadog directly in Copilot / VS Code through a preconfigured Datadog MCP server. Query logs, metrics, traces, dashboards, and more through natural conversation.
-
Model, visualize, and deploy applications with Radius from the GitHub Copilot app and CLI.
-
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.
Publicado en Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
Advanced Security plugin for GitHub Copilot.
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
-
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)
-
Build apps, scripts, and automations with the TypeScript SDK.
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
Skills for building on the Cursor Origin API. Fetch the live spec first, then follow the Origin rules for credentials, scopes, webhooks, paging, and errors. Includes a skill that…
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
Publicado en Docker MCP Catalog (5)
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
Giving Claude ability to run code with E2B via MCP (Model Context Protocol).
-
Give your AI agents trusted access to the full Postman platform.
-
Stop stitching context for Copilot and Cursor. With Sequa MCP, your AI tools know your entire codebase and docs out of the box.
Publicado en Official MCP Registry (5)
-
Pre-injection context compression for coding agents. Zero LLM calls, zero telemetry, offline-safe.
-
air io.github.10iii/air
AI-optimized tool output compression for read, grep, diff, bash, test, web, search, and more
-
Compress coding-agent context ~64%. Hosted Neural Keep MCP for Cursor/Claude/Codex.
-
Persistent memory and session intelligence for AI coding assistants. Zero config.
-
Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search
Publicado en PyPI (MCP servers) (5)
-
Let one coding-agent CLI consult another: Codex, Claude Code, OpenCode, Copilot or Antigravity.
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
Gives AI agents the function they asked for, not the file. Commercial use needs a license.
-
Hanzo MCP Server - Unified tool surface with AI, cloud control, vector search, and multi-framework UI
-
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)
-
Run, watch, and meter coding agents — Claude Code, OpenCode, Kiro, Codex CLI, Gemini CLI, Prime Agent — with normalized events, cost accounting, A/B experiment/variant comparison…
-
Reports real token usage and cost from Claude Code and OpenCode data. Nothing leaves your machine.
-
13 years of Microsoft hyperscale engineering, packaged as a harness for your AI coding agent.
-
Deploy Claude Code, Codex & Antigravity (agy) CLI agents to demolish your work before users do. Real file analysis. Brutal honesty. Per-call model pinning, conversation…
-
140 deterministic tools for your AI: logs, tests, SQL, diagrams, SPARQL. Local, no network.
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 npm registry (MCP servers). 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.