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.
-
token-optimizer-mcpgithub.com/tjpatel16/token-optimizer-mcpupdated this year
High-performance MCP server for minimizing LLM token usage and API costs via structural code analysis and precision chunking
pypi MIT -
io.github.rccola990-cloud/mcp-token-optimizergithub.com/rccola990-cloud/mcp-token-optimizerno update data
Cut LLM token costs: count tokens, estimate cost, slim prompts, and pick the cheapest capable model.
npm -
This is a token optimizer. It forwards commands with heavy token consumption to an openrouter model or a local llm.
npm Apache-2.0 ★ 1 -
@cocaxcode/token-optimizer-mcpgithub.com/cocaxcode/token-optimizer-mcpupdated this year
Orchestration + observability + coach layer for Claude Code token optimization. Measures tool usage, enforces budgets, advises on complementary tools (serena, RTK), and proactively surfaces savings tips.
npm MIT -
Cuts Claude Code and LLM token usage by 60-85% via AST navigation, deduplication, and context-budget optimization.
-
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 -
Local MCP server that indexes folders you choose and gives Claude the few sections that answer a question instead of whole files, so Claude reads less. Windows scripts for Claude Desktop. SQLite FTS5 keyword search; no network connections, no telemetry.
MIT ★ 1 -
91.5% fewer tokens on tool output on Headroom's own benchmark, where Headroom removes 61.4%. Separately, the same SWE-bench tasks resolved at 0.71x the cost of plain Claude Code. Plus memory across sessions and subscription quota pacing. Claude Code, Codex, Copilot, Gemini and 12 more. Local, MIT.
npm MIT ★ 585 -
Token-optimized Trello MCP Server with 97% response reduction
npm MIT -
browser-optimizer-mcpgithub.com/yourusername/browser-optimizer-mcpupdated this year
Browser Optimizer MCP — reduces LLM token usage by 80-98% for browser automation
pypi MIT -
tokenist-optimizerupdated this year
Tokenist: Open-Source Local Token Optimizer Layer for AI Agents
npm MIT -
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 -
skill-orchestratorgithub.com/amasun/skill-orchestratorupdated this year
Dynamic Project Skill Orchestrator for AI Agents - 0 Base Token Optimization (v3.8.0 Twin Registry & Domain Routing Edition)
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 -
⚡ Claude Adaptive Token Optimizer — Zero-dependency, cache-preserving token optimization toolkit for Claude Code CLI and Desktop
MIT ★ 2 -
@iflow-mcp/lunkibr-n8n-mcp-liteupdated this year
Token-optimized MCP Server for n8n workflows - 80%+ token reduction
npm MIT -
Janus - An intelligent OpenAPI MCP server for token-optimized API exploration
npm MIT -
context-skeletongithub.com/msgtorahul-art/context-skeletonupdated this year
Zero-dependency structural code folding CLI, MCP server & LLM token optimizer
-
codiff-mcpstale
A Model Context Protocol (MCP) server for code diffing with intelligent token optimization
npm MIT -
@alidhibi/cctogithub.com/alidhibi/cctoupdated this year
Claude Code Token Optimizer — reduce token usage by 60–80% with local semantic indexing and MCP tools
npm MIT -
Lightweight WordPress MCP server - 42 tools, token-optimized responses
npm MIT ★ 4 -
Token-Optimized Unified MCP Server for Gmail & Microsoft 365. 60% fewer tokens, 100% more power.
npm NOASSERTION ★ 5 -
Context optimization & token-saving MCP server for OpenCode CLI on free model tiers
MIT -
@enzyme-protocol/mcp-serverupdated this year
Enzyme MCP - Token-optimized content digestion via Chrome CDP
npm PolyForm-Noncommercial-1.0.0 -
A token-optimization and memory layer between agent and model: dedups tool output, distills old turns, prunes to a token budget. Proxy, MCP server, CLI, or library
Apache-2.0 ★ 1 -
io.github.shivam-app-developers/ai-optimizergithub.com/shivam-app-developers/ai-optimizerno update data
MCP server that cuts AI coding agent token usage via framework-aware context optimization
npm -
@fosterg4/mcpsaverstale
MCP server for optimizing code references and reducing token usage through smart caching and AST parsing
npm MIT -
tokenettegithub.com/itsmeadarsh2008/tokenetteupdated this year
The Ultimate All-in-One AI Coding Enhancement MCP - Zero-Loss Token Optimization · Intelligent Model Routing · Quality Amplification
pypi MIT -
neko-prompt-optimizer-mcpupdated this year
MCP server for self-optimizing master prompts - Track rule usage, compress tokens, analyze dependencies
npm MIT -
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 -
Token-optimized CLI & Model Context Protocol (MCP) server for Playwright suite execution, on-demand failure clustering, and live browser automation
npm MIT -
Zero-dependency context & token optimizer for Claude Code, Codex CLI, and Google Antigravity. Cuts terminal output by up to 96.4% to prevent context window exhaustion.
npm MIT -
promptdietupdated this year
Token-optimizing MCP server for Cursor. Give your AI IDE access to specialized code agents backed by AST skeletonization and Eco-Telemetry.
npm MIT -
Pure Python FastMCP Server & CLI paste wrapper for Token-Optimized Object Notation (TOON) JSON context compression
MIT -
mcp-ghost-optimizedgithub.com/mathunterix/mcp-ghost-persoupdated this year
MCP server for Ghost CMS with optimized field projection - reduces token usage by 90-98%
npm MIT -
AgentCost — AI Agent Spend Analysis. MCP server that analyzes Claude Code session logs to find token waste and optimization opportunities. Free preview tier available.
npm MIT -
Zero-cost token optimization engine for AI coding assistants (Claude Code, Cursor, Antigravity, Windsurf). Saves 70-95% tokens via AST skeletons, differential cache, and line slicing.
NOASSERTION ★ 6 -
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 -
mcp-checkupgithub.com/yifanyifan897645/mcp-checkupupdated this year
MCP server that analyzes your MCP setup: token costs per server/tool, grades, duplicate detection, optimization report
npm MIT ★ 1 -
Context-optimized MCP server for web scraping. Reduces LLM token usage by 70-90% through server-side CSS filtering and HTML-to-markdown conversion.
MIT ★ 8 -
Token optimizer for Claude Code Gemini CLI & Qwen Code — compresses shell outputs via PreToolUse hook, tracks USD savings in TUI dashboard
MIT ★ 21 -
Token and context optimization for AI coding agents with smart compression, retrieval, recovery, routing, and MCP integrations.
MIT ★ 1 -
RAGStackgithub.com/SonicStrain/RAGStackupdated this year
Token-optimized RAG pipeline for Claude Code — 6 swappable layers, free local LLM via Ollama, Graphify graph RAG, one-click presets with auto-install, MCP + GUI + CLI
MIT -
MCP server with code-intelligence tools and git-like version management that carries minimal cross-session context (file diffs, insight notes, task handovers). Optimized for token efficiency and human review.
LGPL-3.0 -
cortex-works-minimalgithub.com/cortex-works/cortex-works-minimalupdated this year
A hyper-optimized MCP server that supercharges AI coding agents. Outperforms built-in IDE tools with AST-based precision editing and native OS control, drastically reducing LLM token consumption.
MIT ★ 8 -
Cross-platform CLI toolkit and local MCP server for AI coding agents. Optimizes context windows and token consumption by turning raw outputs into compact, deterministic Markdown/JSON reports.
pypi MIT ★ 3 -
claude-conduitgithub.com/Labontese/claude-conduitupdated this year
Token and agent optimization MCP server for Claude: smaller inputs, higher cache hit rates, per-session cost reports.
MIT -
pidgey-mcpgithub.com/manthan-railkar/hackateersupdated this year
Token-Optimized Middleware Engine & DOM Checkpointing Framework for AI Browser Automation
pypi MIT -
skillfm-mcpgithub.com/ericm1018/skillfm-mcpupdated this year
SkillFM Beacon MCP: AI health, token usage, LLM cost optimization, BYOK vault, and cleanup audits.
npm MIT -
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 -
Rug check any token on Base, Ethereum, Arbitrum, Optimism, Polygon or Solana for AI agents: 0-100 risk score with reasons. MCP server + JS client, $0.01 per check via x402.
npm MIT -
tokcodecutgithub.com/Bazina/tokcodecutupdated this year
Token-optimized MCP server giving Claude surgical read access to source files — structure, skeletons, symbols, imports, cross-file refs. Cuts 70–95% tokens on code nav.
MIT ★ 2 -
LLM-optimized MCP server for Datadog APM, logs, and metrics. Delivers structured, token-efficient trace and log insights designed specifically for AI-driven debugging—not just raw Datadog data.
MIT ★ 1 -
Azure FinOps playbook as code: 10 cost optimization patterns, AI FinOps (token attribution, routing, caching, PTU, ROI, eval gate) and an approval-gated FinOps agent over MCP. Offline, synthetic data, list-price snapshot.
MIT -
Android MCP server - production-grade, token-optimized, accessibility-first
npm MIT ★ 20 -
An MCP server and CLI to track model prices, detect volatility, and optimize token costs on OpenRouter.io for AI Agents such as Hermes or OpenClaw.
MIT ★ 2 -
tokenpilotgithub.com/rish-e/tokenpilotupdated this year
Automatic token optimization for Claude Code — hooks + MCP server that reduces wasted tokens via task classification, file read dedup, and configurable aggressiveness (1-10)
★ 1 -
bre-context-enginegithub.com/PavanAkurathi/bre-context-engineupdated this year
An AI-native context-optimization engine and Model Context Protocol (MCP) server. BRE uses AST-based skeletonization and MMKP constraints to supply AI agents with high-fidelity, token-efficient context.
-
n8n-mcp-litegithub.com/LunkiBR/n8n-mcp-liteupdated this year
Token-optimized MCP Server for n8n workflows with Focus Mode
★ 28 -
Daimonosgithub.com/beardfaceguy/daimonosno update data
Agent-optimized MCP server with structured JSON tools. 20-45% token savings.
mcpb