MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
compress-tokensgithub.com/Amir-Zecharia/compress-tokensupdated this year
MCP server that compresses text by removing unnecessary tokens using local LLM surprisal scoring
MIT ★ 1 -
glyph-compressgithub.com/Neolambo/glyph-compressupdated this year
Cut the tokens your IDE-to-LLM coding session is billed for. Stops re-sending files the model already has, places provider cache breakpoints where they cover the request, and compresses what needs sending — measured against real tokenizers, not character counts. CLI, VS Code, MCP server, proxy.
npm AGPL-3.0 ★ 4 -
MCP server and hook toolkit that compresses tool output to save context window tokens.
npm MIT ★ 14 -
Agentic_context_compression_frameworkgithub.com/saitarrun/Agentic_context_compression_frameworkupdated this year
Rust MCP server for lossless agent-context compression, reducing token usage while preserving retrieval accuracy.
-
Self-documenting Model Context Protocol server for code context compression with real-time token savings statistics. Reduces LLM context by 70-98% while preserving semantic meaning. No system prompt configuration needed.
npm MIT -
tokencompressgithub.com/jiawei686/tokencompressupdated this year
🔐 Local, zero-cloud token & text compression for LLM prompts and logs. Offline rules + optional local Ollama semantic + lossless gzip. MCP / HTTP / CLI / library. 中文友好。
MIT ★ 1 -
ak-primusgithub.com/ak-primus/ak-primusupdated this year
Intelligent token compression + routing MCP server
pypi MIT -
Model Context Protocol (MCP) server for compressing AI context to reduce token usage. Provides tools to shrink text, summarize files, and cache repository content.
npm MIT -
ai-token-killer-mcpgithub.com/pzcuong/ai-token-killerupdated this year
AI Token Killer - Advanced LLM token optimization with JSON-first compression, auto-rewrite hooks, and workflow automation. Installs a pre-built binary, no Rust required.
npm MIT -
@csc-protocol/token-saveractive
Autonomous AI agent tool and MCP server for semantic token compression and L402 edge solvency clearance.
npm UNLICENSED -
rust-cave-001github.com/ether-btc/rust-cave-001updated this year
High-performance text compression — Rust-backed Python bindings for sentence-aware NLP compression and token optimization. Now with MCP server.
pypi MIT -
@groobybugs/cave-toolsgithub.com/groobybugs/cave-toolsupdated this year
A caveman needs their tools. Token-compression MCP server for any agent.
npm MIT -
Thai-first context compression MCP server for Claude Code — 50-88% token savings, 100% recoverable
pypi MIT -
token_optimizergithub.com/omkar9854/token_optimizerupdated this year
Zero-dependency, fully-reversible context compression for AI agents — cut LLM token usage up to 94% (JSON tabularization, log template mining, query-aware code skeletons). Stdlib-only, air-gap ready, built-in MCP server.
pypi Apache-2.0 ★ 1 -
promptthrift-mcpgithub.com/woling-dev/promptthrift-mcpupdated this year
Smart token compression MCP server for LLM apps. Gemma 4 local compression, multi-model cost tracking, intelligent model routing. Save 70-90% on API costs.
MIT ★ 1 -
Model Context Protocol (MCP) server for ASON compression/decompression. Enables Claude Desktop and other MCP clients to compress JSON data using the token-optimized ASON format.
npm MIT -
MCP server that compresses, summarizes, and filters context to minimize LLM token usage
npm MIT -
sym-protocolgithub.com/sym-protocol/sym-protocolupdated this year
SYM Protocol v1.0.1 — Symbolic prompt compression for LLMs. Reduce input tokens 40-65% without losing meaning. MCP server + CLI + Agent. Dynamic domain detection + history compression + stopwords.
npm MIT -
tokensavergithub.com/pozii/tokensaverupdated this year
MCP server that cuts AI agent token costs by up to 97% — compression, caching, pruning, web extraction
Apache-2.0 ★ 1 -
Pure Python FastMCP Server & CLI paste wrapper for Token-Optimized Object Notation (TOON) JSON context compression
MIT -
claude-context-savergithub.com/dongnh311/claude-context-saverupdated this year
MCP server that cuts Claude Code token usage: log compression (builds/tests/installs) + smart file reading (symbol-level source access via tree-sitter).
npm MIT ★ 2 -
Unified token compression engine combining Headroom, FastMCP, mcp-agent, MetaGPT, Claw Compactor, SuperCompress, and Netflix OCI Agent into one platform with MCP server, agent orchestration, and Streamlit dashboard
MIT ★ 1 -
Codex plugin MCP server (codex-plugin-mcp) for token efficiency, token reduction, context compression: exact-recoverable terminal, file, project, web, memory.
MIT ★ 4 -
Agent Intermediate Language (AILv1): Zero-loss AI context compression protocol, AST signature extractor, and MCP server that cuts LLM handoff tokens by 85–95%.
MIT ★ 1 -
agentready-cloud-mcpactive
MCP server for AgentReady: compress prompts with TokenCut and turn any URL into clean, token-light Markdown, inside Claude, Cursor, Windsurf and any MCP client.
npm MIT -
context-squeezegithub.com/yousudip/context-squeezeupdated this year
Deterministic context-compression MCP server for Claude: squeeze codebases, files, and logs to fit token budgets using tree-sitter and tree-walking — no LLM in the loop. (Rust)
MIT ★ 1 -
better-ctxgithub.com/jadzeino/betterctx-clientupdated this year
Context Intelligence Engine with CCP. 34 MCP tools, 8 read modes, 90+ compression patterns, cross-session memory (CCP), persistent AI knowledge with temporal facts + contradiction detection, multi-agent context sharing + diaries, LITM-aware positioning, AAAK compact format, adaptive compression with Thompson Sampling bandits. Supports 24 AI tools. Reduces LLM token consumption by up to 99%.
cargo MIT -
SuperBased plugin for Claude Code — screenshot capture, AI vision, OCR, screen recording, visual regression testing, token compression, voice dictation, and proactive monitoring via 28 MCP tools
★ 1 -
denselygithub.com/alibaizhanov/denselyupdated this year
Lossless context compression for LLMs: 2x-8x fewer tokens, byte-exact reconstruction (sha256-verified). MCP server for Claude Code & Cursor.
pypi MIT ★ 8 -
logzipgithub.com/NailShakurov/logzipupdated this year
Compress logs for LLM analysis — Rust-powered, Python API. 40-60% token savings.
MIT ★ 12 -
@iflow-mcp/tidesurf-coregithub.com/tidesurf/coreupdated this year
Connect Chromium to LLM agents via token-efficient DOM compression
npm Apache-2.0 -
Context compression for AI agents — cut token usage costs with retrievable CCR compression. Rust core + Python API, Claude Code & Codex plugin, MCP server. PyPI: furl-ctx
Apache-2.0 ★ 5 -
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
pypi Apache-2.0 ★ 79,833 -
Reversible, structure-aware context compression engine for LLM agents (Rust) — cuts token cost of tool outputs, JSON and logs. Deterministic, sans-io, zero network.
npm Apache-2.0 -
meshmindgithub.com/AntoniovanDijck/meshmindupdated this year
A single MCP server merging local codebase mapping, recency research, and token compression for AI agents.
MIT ★ 1 -
localmind-mcpgithub.com/kemerdev/localmind-mcp-serverupdated this year
LocalMind MCP server: token-frugal code context compression with local Ollama
npm ISC -
Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, Cursor, Codex, Kiro, Zed, any MCP client. Rust, zero LLM calls.
cargo Apache-2.0 ★ 677 -
Token-efficient semantic compression for numerical data. 95%+ token reduction.
pypi -
token-lens-mcpgithub.com/mdfifty50-boop/token-lens-mcpupdated this year
MCP server for context window optimization — audit token budgets, compress schemas, optimize tool loading
npm -
⚡ Fast, local, provenance-aware Code-Context MCP Server & DeepSeek Cordis Harness. Compresses 500k+ tokens by 99.9% via AST elision, PageRank & Progressive Zoom-in for Claude Code, Cursor, Antigravity.
pypi MIT -
Rust-native context compression for Claude Code, Codex & MCP agents: filters & compresses noisy tool output (tests, diffs, logs, JSON, provider traffic) before it reaches the LLM — fewer wasted tokens, full evidence recoverable. Local-first, Apache-2.0. Pairs with Code Explorer.
npm Apache-2.0 ★ 4 -
cctxgithub.com/anil7948/cctxupdated this year
Reduce Claude Code token usage by 70-90% using a free local LLM (Ollama). MCP server + Stop hook with codebase indexing, tool output compression, and turn summarization.
npm MIT ★ 3 -
codebase-pilotgithub.com/kalpeshgamit/codebase-pilotupdated this year
AI context engine for Claude Code, Cursor, Windsurf — pack, compress, and optimize any codebase. Save 60-90% tokens. Web dashboard on port 7456.
npm MIT ★ 6 -
Measure what context compression actually costs an LLM agent: where a session's tokens go, and whether a rewrite pays for the prompt cache it invalidates. Rust crate, MCP server and benchmark harness.
npm MIT ★ 1 -
rtk-mcp-servergithub.com/alexiyous/rtk-mcp-serverupdated this year
Token-optimized MCP server that compresses shell tool output by 60–90%, with RTK-style prompt injection prevention for Claude Desktop
★ 1 -
MCP server that intercepts and compresses tool outputs before they reach the LLM context. Reduces 60-90% token consumption without losing actionable information.
npm MIT -
Cut token usage in Claude Code, Cursor, Codex & Gemini: deterministic in-process context compression for AI coding agents. Lossless and retrievable (#ref), AST code skeletons, TOON JSON tables, stdio MCP. No LLM, no network, MIT.
pypi MIT ★ 3 -
Token-first headless browser MCP server. Compresses any webpage into a tiny semantic graph — cutting 90%+ of token waste.
npm MIT -
Self-hosted AI workspace that compresses prompts before they leave your machine — 79% fewer tokens, measured. Drop-in gateway for Claude Code, Cursor, Aider and any OpenAI/Anthropic client, plus an MCP server. Free, MIT, zero telemetry.
MIT ★ 3 -
matlab-mcp-proxygithub.com/nightfury1802/matlab-mcp-proxyupdated this year
MATLAB/Simulink/Simscape MCP compression proxy — 14 domain-specific rules, 48-85% token reduction on simulation output
MIT ★ 4 -
tokenwise-mcpupdated this year
Library + MCP server for reducing LLM token costs via compression, summarization, chunking, and Anthropic prompt-cache breakpoint planning
npm SEE LICENSE IN LICENSE -
Universal token saver for AI coding agents: compresses every tool output (shell, MCP, Roblox Studio, grep, big files) before the model reads it. One Rust binary.
MIT -
Turn any folder or Git repo into safe, token-efficient context for LLMs, AI chats, and coding agents like Claude Code, Codex, and Cursor — local-first GUI, TUI, CLI, and a read-only MCP server with Live Context, agent journal, Smart Ignore, secret/PII redaction, Git scopes, and code compression. Windows, macOS, Linux.
nuget Apache-2.0 ★ 41 -
Turn anything into token-optimized, layout-aware Markdown - and know exactly what it saved you. Lossless compression, honest token reports, CLI + MCP server + agent skill.
npm Apache-2.0 ★ 1 -
The Autonomous Context Firewall & MCP Server for AI Coding Agents. Compress noisy test logs by 90%+ and extract Python AST skeletons at 0 LLM tokens.
pypi MIT ★ 1 -
Token optimizer for Claude Code Gemini CLI & Qwen Code — compresses shell outputs via PreToolUse hook, tracks USD savings in TUI dashboard
MIT ★ 21 -
thinchaingithub.com/SnipMCP/thinchainupdated this year
MCP server that cuts options chain tokens 95% for AI trading agents. Sanitize, compress, circuit-break.
pypi MIT -
neko-prompt-optimizer-mcpupdated this year
MCP server for self-optimizing master prompts - Track rule usage, compress tokens, analyze dependencies
npm MIT -
Token-economy stack for AI coding agents — input/output compression + MCP tools to cut agent session cost.
NOASSERTION -
Calendar MCP server with atomic booking, conflict prevention, deterministic RRULE expansion, and TOON token compression for AI agents
npm MIT ★ 13