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
Resumo
sqz-cli é um servidor MCP publicado por ojuschugh1. Marketplaces que lemos e que o listam: 1 (npm registry (MCP servers)). A última mudança que registramos foi em 2026-11-02. Conforme nossa passagem pelos marketplaces em 2026-11-04.
O que pede
- Roda na sua máquina
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
- Downloads do npm por semana: 103 (2026-11-02)
- Downloads do npm por mês: 898 (2026-11-02)
- Última versão no npm: 2.1.1, publicada em 2026-10-11
Nenhuma vulnerabilidade conhecida no OSV para 2.1.1 (verificado em 2026-11-02)
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.
Conectar
Sem dados para um comando automático: o que os marketplaces declaram não diz de forma inequívoca como conectá-lo.
Onde está publicado
| Marketplace | Status | Versão | Números | Verificado | Visto pela primeira vez |
|---|---|---|---|---|---|
| npm registry (MCP servers) (Abrir no npm) | Listado | 2.1.1 | Downloads por mês (npm): 898 Downloads por semana (npm): 103 Forks (GitHub): 43 Estrelas (GitHub): 675 |
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.
Como os números mudaram
- 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 ponto é um dia em que lemos um número diferente; os trechos planos são dias em que o número não mudou. Números de marketplaces diferentes nunca são somados.
O que mudou
Nada mudou neste plugin desde que começamos a acompanhá-lo.
Possivelmente o mesmo plugin
Listagens que compartilham um sinal com esta, mas não o bastante para tratá-las como o mesmo produto.
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.
-
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 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)
-
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
Listado em 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
Listado em 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…
Listado em 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.
Listado em Community GitHub marketplaces (4)
-
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.
-
Filter noisy command output before it reaches the model; raw output stays recoverable. Skill + MCP server.
Listado em 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.
Listado em 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…
Listado em 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.
Listado em 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.
Listado em 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
Listado em 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.
Listado em 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 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 npm registry (MCP servers). Os números vêm das nossas próprias passagens regulares pelos marketplaces, última leitura em . Não publicamos dados de contato dos editores de plugins.