- Conduid
- Marketplace
- #token-optimization
MCP servers tagged token-optimization
299 live MCP servers tagged "token-optimization", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with token-optimization.
Gcf
The AI-native wire format for structured data. 100% comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ lossless round-trips across 17 formats. Spec v3.5.1…
Ecotokens
Token optimizer for Claude Code Gemini CLI & Qwen Code — compresses shell outputs via PreToolUse hook, tracks USD savings in TUI dashboard
Agy Headless Bridge
Call the Google Antigravity CLI (agy) headlessly from any non-TTY context — Windows ConPTY + POSIX pty + MCP server. Fixes the empty-output bug (#76).
Unity MCP Efficient
Token-efficient facade and Codex skill for MCP for Unity: 96% smaller measured tool-schema surface, compact results, batching, and recovery.
Fak
Agentic Runtime
Markdown For Agents
HTML to Markdown converter for AI agents. 90+% fewer tokens, one dependency, works everywhere.
8v
8v is one binary that reads, writes, searches, checks, builds, tests, and formats code, using fewer input and output tokens than the agent's native tools.
Paper7
arXiv papers as clean Markdown for LLMs. 97% smaller than PDF. Zero dependencies. Bash-only.
Opencode Lazy Loading
Opencode lazy load plugin Saves 85%+ on tools and MCP servers tokens per request. The LLM loads tool instructions on-demand instead of receiving thousands of tokens of schemas it…
Multiplexer
One MCP server fronting many: list_servers, list_tools, search_tools, describe_tool, call_tool, refresh_tools, authorize_server. Lazy schema discovery slashes context-token costs.…
Polyglot
Write in your native language, Claude Code responds in English. Local-GPU translation + multi-layer anti-bypass enforcement. ~18% tokens saved on Polish, ~43% on CJK.
Contextwise
Dynamic Model Context Protocol (MCP) Tool Routing, Schema Compression & Execution Gateway
Dsh Tool Guardian
Tool Guardian as a native DeepSeek Harness (DSH) bundle: keeps tool definitions out of the context window by fronting your MCP servers behind a small native router. A bridge to th…
Everything Slim
everything MCP (58% less tokens). Quick setup: npx everything-slim --setup
Context Control
🔥 Context Control MCP v5.0 PORTABLE EDITION - Análisis universal de proyectos que funciona en CUALQUIER entorno. Contexto completo automático para IA.
Slim
MCP Slim - Lightweight CLI proxy for AI agents that reduces token usage vs full MCP
Larkx
AI codebase indexer and MCP server for Claude Code, Cursor, and Copilot. Pre-index your project into a compact graph and measure real token savings with `larkx bench`.
Gamedev Log Analyzer
Token-efficient game-engine & build log analysis (Unreal/Unity/Godot/MSVC-UBT-MSBuild) for the CLI and MCP — parse, dedup, classify by severity/category, diff runs, locate file:li…
Claude Code Deepseek Delegator
MCP server that lets Claude Code delegate heavy-token tasks to DeepSeek. Claude orchestrates; DeepSeek does the heavy lifting. Zero dependencies.
Distill Shrink
MCP middleware that compresses tool/resource descriptions before they hit context, with net-savings telemetry shared with the Distill skill.
Yats Toolkit
YATS — Yet Another Token Saver. One-command MCP server that indexes your codebase into a knowledge graph so AI agents (Claude, Cursor, Copilot) can search and navigate it without…
Playwright Lean
Token-optimized CLI & Model Context Protocol (MCP) server for Playwright suite execution, on-demand failure clustering, and live browser automation
Openvisio Oss
No description published.
Repocode
AI codebase context tool that analyzes, ranks, and compresses repositories into optimized context files for LLMs, AI coding assistants, and MCP workflows.
Rote
Compile AI agent skills into cheap, fast, deterministic pipelines that run without an LLM in the loop
Skim
Runtime token proxy + intelligence dashboard for LLM tools. Intercepts API calls, strips waste, tracks costs — for individual developers and Fortune 500 teams.
Codex Context Reader
A read-only MCP plugin for ChatGPT Chat that retrieves local project context on demand to reduce unnecessary token use.
TokenJar
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 slic…
BurnRate
⚡ Terminal HUD, hard budget breakers & prompt-cache leak alerts for AI coding agents (Claude Code, Cursor, Codex)
CodePrism
Standalone Python package + MCP server that builds and maintains a persistent knowledge graph of any codebase, exposing precise, token-efficient context to AI coding agents.
Code Context Engine
MCP context engine for AI coding agents: a local code graph answers "which files does this task need?" — folded evidence packets instead of whole files. Recall 1.000 on repos it w…
Ziplex
A tool that converts local projects into structured contexts that AI can understand instantly
Community
reShapr Community repo
.github
Central repository for the reShapr project community health assets.
Brain
Local-first MCP server that tells coding agents which files to read, and how sure it is. 97% Hit@10 on Java (SWE-bench Multilingual), 89% on Python (SWE-bench Lite), zero LLM cost…
Matlab MCP Proxy
MATLAB/Simulink/Simscape MCP compression proxy — 14 domain-specific rules, 48-85% token reduction on simulation output
Agent Friend
Find the MCP schema issues eating your context window. 156 checks. Grade A+ through F. ESLint for MCP.
Crux
Compression Runtime for Universal eXecution — a 60–95% token reducer for AI coding agents (Claude Code, Cursor, Cline, …). Single Rust binary, SQLite, 11 layers, local-first.
Callsieve
Local code retrieval for AI coding agents. Rust CLI and MCP server with indexing, compact context, and reproducible evaluation tools.
Allan MCP Memory Code
Store persistent knowledge graphs for AI coding assistants using a local Docker setup with hybrid search and entity extraction.
Fable
One repo, one skill: a self-improving experience layer for AI agents - multi-dataset session retrieval, on-device triage, token compression, smart-mode routing for hard tasks, vid…
Surfboard
The Web Browser for LLMs
Botte Secrete
Token Efficiency Toolkit — codex, claude code, antigravity, hermes, openclaw, acceleration, and smart workflows
Osiris Producers
Discover infrastructure resources across hyperscalers, cloud, hosting providers, and on-premises IT/OT environments. Generate private, vendor-neutral OSIRIS JSON snapshots for doc…
Fmm
fmm turns a repo into queryable structure: file topology, exports, imports, dependencies, LOC, and file outlines with line ranges
Emu
Stop burning API tokens. 9 algorithmic engines for real-time context optimization, infinite-loop detection, and smart prompt compression.
Wuji Legion Codex
无极军团 3.0：面向 Codex 的智能工作中枢。以自然语言组织 Skill、插件与 MCP，保留白帽判断、有界执行与证据驱动进化。公开开发中。
Bundlebox
The zero-token software factory for AI coding agents: scan, pack, route and run work across Claude Code, Codex, Gemini CLI, Cursor, Aider, OpenCode and any agent, and measure ever…
Master Of
Universal AI skill & context gateway: keeps rarely-used skills dormant behind domain gates across Claude Code, Antigravity (AGY), Cursor, and any MCP-compatible agent
Rlcd Gateway
Self-hosted gateway for LLMs and decision models. Claude Code, Codex, OpenCode and any OpenAI/Anthropic SDK app reach any provider (OpenRouter, Groq, Ollama…) with context pruning…