io.github.base76-research-lab/token-compressor
Compress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.
MCP server · by base76-research-lab
About
io.github.base76-research-lab/token-compressor is an MCP server published by base76-research-lab. Marketplaces we read that list it: 1 (Official MCP Registry). The last change we recorded was on 2026-10-24. As of our marketplace pass on 2026-10-24.
What it asks for
- Runs on your machine
None of the marketplaces we read publishes its tools or the settings it asks for.
What it declares, asks for and runs, in full
Only install plugins from developers you trust. We list what marketplaces publish and do not test plugins.
Package
PyPI token-compressor-mcp (token-compressor-mcp on PyPI)
- PyPI downloads/week: 34 (2026-10-24)
- PyPI downloads/month: 78 (2026-10-24)
- Latest version on PyPI: 0.1.1, published 2026-03-03
No known vulnerabilities in OSV for 0.1.1 (checked 2026-10-24)
PyPI facts come from pypi.org, PyPI downloads from pypistats.org. Each figure is the registry's own and is never added to another. A registry that publishes no figure shows none: no number is not zero. Vulnerability records come from OSV.dev (CC BY 4.0) and concern the declared version only; a listing that declares no version gets no answer. We do not scan code.
Works with
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
A one-click link opens the client, which asks you to confirm before it adds the server.
From the marketplaces that list it and the MCP transport it declares, as each client documents them. We do not test plugins.
Connect
Commands and configs built only from what its marketplaces declare. We do not run them for you and do not test plugins.
As a local MCP server: PyPI package
Built from what Official MCP Registry declares.
claude mcp add --transport stdio token-compressor -- uvx token-compressor-mcp[mcp_servers.token-compressor]
command = "uvx"
args = ["token-compressor-mcp"]{
"mcpServers": {
"token-compressor": {
"command": "uvx",
"args": [
"token-compressor-mcp"
]
}
}
}Where it is published
| Marketplace | Status | Version | Figures | Verified | First seen |
|---|---|---|---|---|---|
| Official MCP Registry (Open the registry record) | Listed | 0.1.1 | Downloads/month (PyPI): 78 Downloads/week (PyPI): 34 Forks (GitHub): 2 Stars (GitHub): 12 |
Not marked |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
What changed
Nothing has moved on this plugin since we started watching it.
Similar plugins
Products whose own names, descriptions, tools and skills are closest in meaning to this one, on every marketplace we read. Closeness is ranked within this list only.
-
token_optimizer io.github.omkar9854/token_optimizer
Reversible context compression for AI agents: cut token usage up to 94%, originals retrievable
-
Pre-injection context compression for coding agents. Zero LLM calls, zero telemetry, offline-safe.
-
MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.
-
TokenSqueezer LLM Token Compressor
x402-gated LLM token compressor: strip filler, collapse JSON, densify prose. Paid in USDC.
-
Compress coding-agent context ~64%. Hosted Neural Keep MCP for Cursor/Claude/Codex.
-
SuperCompress v2 — hosted ~400M Neural Keep. Compress tool dumps before they burn tokens. Hosted MCP supports OAuth 2.1 sign-in (PKCE). Plugin no-key setup is next. Free tier: 5M…
-
semantic-frame io.github.Anarkitty1/semantic-frame
Token-efficient semantic compression for numerical data. 95%+ token reduction.
-
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.
-
token-optimizer-mcp io.github.ooples/token-optimizer-mcp
Context-window optimization: caching, compression & smart file tools that cut tokens 60-90%.
Similar plugins by marketplace
The same question asked of one marketplace at a time: is there an analog of this plugin there?
Has a listing on Claude Code: claude-plugins-community (5)
-
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…
-
Token-optimized document reader — silently compresses .md, .html, and .txt files on every Read, cutting context usage by ~30% with zero workflow change. Adaptive 4-stage…
-
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.
-
Automatic token optimization for Claude Code. Compresses tool output 40–60%, shows a live token meter in the statusline, auto-compacts at 70% context, builds a self-updating…
-
Automatically compresses verbose CLI output (git, docker, npm, terraform, kubectl, etc.) to save tokens in Claude Code sessions. 21 specialized processors with content-aware…
Has a listing on Claude Code: claude-plugins-official (5)
-
Build, train, evaluate, and use open source AI models, datasets, and spaces.
-
Agent Skills for Together AI platform — inference, training, embeddings, audio, video, images, function calling, and infrastructure. Covers serverless chat completions…
-
Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered…
-
Write accurate Pydantic AI code from the start. Up-to-date patterns, decision trees, and common gotchas for agents, tools, structured output, streaming, and multi-agent apps.
-
Precise local semantic code search via MCP. Indexes your codebase with Go AST parsing, embeds with Ollama or LM Studio, and exposes vector search to Claude through an MCP server…
Has a listing on 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
-
MCP server for terminal commands, file operations, and process management
-
Build multimodal AI applications with Pixeltable -- tables, computed columns, embedding search, UDFs, tool-calling agents, and 25+ AI provider integrations.
Has a listing on Codex: openai-curated (openai/plugins) (5)
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Install, open, and connect the signed ChatCut Desktop app from Codex.
-
AI-powered code review in Codex, powered by CodeRabbit.
Has a listing on Community GitHub marketplaces (5)
-
SuperCompress v2 — hosted ~400M Neural Keep. Compress tool dumps before they burn tokens. Hosted MCP supports OAuth 2.1 sign-in (PKCE). Plugin no-key setup is next. Free tier: 5M…
-
Read large logs, JSON and docs in a fraction of the tokens. Offline, fact-preserving optimizer.
-
Optimisation tokens — routing Haiku/Sonnet/Opus, classification T1/T2/T3, compression caveman, budget tracking. Inclut 6 skills + 3 agents.
-
Token-efficient code generation pipeline - parallel implementation with hosted LLM (Cerebras) for ~60% token savings. Includes MCP server.
-
Context pruning for Claude Code through the better-compact daemon: keeps long sessions lean without losing recallable history.
Has a listing on 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.
-
Shows live prompt-cache reuse, expiry, token composition, and AI Credit cost for the current GitHub Copilot session without making model calls.
-
Plain-English translation layer for non-technical Copilot CLI users. Translates every approval prompt, error message, and technical output into clear, jargon-free English with…
-
Visualizes live session AI-credit usage as a Pac-Man board with pellets, ghosts, fruit milestones, and game-over limits.
-
Task Researcher and Task Planner for intermediate to expert users and large codebases - Brought to you by microsoft/edge-ai
Has a listing on Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
Advanced Security plugin for 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…
-
Navigate and interact with your C++ code using the Microsoft C++ Language Server.
Has a listing on Cursor: cursor/plugins (5)
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Build apps, scripts, and automations with the TypeScript SDK.
-
Consult a stronger model before major decisions, when stuck, and before declaring done.
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
Has a listing on 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.
-
Giving Claude ability to run code with E2B via MCP (Model Context Protocol).
-
Discovers and retrieves llms.txt from websites.
-
Production-ready RAG service to search and retrieve data from your documents.
Has a listing on Official MCP Registry (5)
-
token_optimizer io.github.omkar9854/token_optimizer
Reversible context compression for AI agents: cut token usage up to 94%, originals retrievable
-
Pre-injection context compression for coding agents. Zero LLM calls, zero telemetry, offline-safe.
-
MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.
-
TokenSqueezer LLM Token Compressor
x402-gated LLM token compressor: strip filler, collapse JSON, densify prose. Paid in USDC.
-
Compress coding-agent context ~64%. Hosted Neural Keep MCP for Cursor/Claude/Codex.
Has a listing on 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.
-
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.
-
perplexity com.mcparmory/perplexity
Search the web, generate AI responses, and create embeddings with real-time information
Has a listing on npm registry (MCP servers) (5)
-
rubber-duck io.github.nesquikm/rubber-duck
Bridge to multiple LLMs and CLI agents: councils, debates, voting, and more
-
deepseek io.github.arikusi/deepseek
MCP server for DeepSeek AI with chat, reasoning, sessions, function calling, and cost tracking
-
ask-gemini io.github.Lykhoyda/ask-gemini
Bridge Claude with Gemini CLI for AI-to-AI collaboration, code review, and second opinions
-
sub-agents-mcp io.github.shinpr/sub-agents-mcp
MCP server for delegating tasks to specialized AI sub-agents across coding tools
-
ask-claude io.github.Lykhoyda/ask-claude
Bridge Codex and other MCP clients with Anthropic Claude Code CLI for read-only second opinions
Found by meaning, not by shared code or a shared repository: similar plugins stay separate products, and this is not a review or a recommendation.
Want this mark on your plugin in our catalog?
Prove you maintain it with a file in its repository, a file on your domain or a DNS record, and you can show this mark on the card, with live banners for your site and README. How verification works
You also get alerts when a marketplace lists it, drops it, changes its verified mark or what it asks for, and its remote endpoint goes on monitoring as a web service.
Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.