- 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.
Notion Slim
notion MCP (52% less tokens). Quick setup: npx notion-slim --setup
Lithium Kb
🧠 Fast, zero-dependency structured knowledge base (.agent-kb/) with 2D neural graph visualizer │ & MCP server for Claude, Codex, PI, Cursor, Windsurf, Zed & Other AI coding agent…
Tileward Claude Marketplace
Claude Code plugin marketplace for Tileward: a hook that refuses off-policy prompts before the model sees them, and a hosted MCP server that recalls only the relevant slice of a l…
AI Agent Orchestrator
Production multi-agent orchestration framework - Claude Code, CLAUDE.md governance, multi-tier model routing, token economics
Context Skeleton
Zero-dependency structural code folding CLI, MCP server & LLM token optimizer
Codeaware MCP
MCP server for Claude Code, powered by the v4 semantic runtime: builds persistent, budget-aware repository intelligence from AST/graphs, serves bounded context packages, preserv…
LRO
Large Result Offloading (LRO) -- a token-aware strategy for managing large tool outputs in LLM context windows. Includes empirical evaluation and formal specification.
Save The Token
Reduce Codex and Claude context waste by measuring MCP tools, repo instructions, and safe token-budget cuts.
Betterthantoon
GCF vs TOON benchmark data
Modelbound Claude Code Plugin
Official ModelBound plugin for Claude Code — sync skills and rules, run the Skill Development Pipeline, optimize tokens, and guard MCP/bash tool use.
Frontload
Local-first context gateway that helps AI coding agents read less, spend less, and stay grounded in your repo.
Graph X
Local knowledge graph for any project: zero-dependency indexer + 7-tool MCP server for Claude Code + live neumorphic graph UI. Cuts Claude token usage 8-10x.
2papi
Self-hosted AI gateway in Go: pool Claude/ChatGPT/Gemini subscription accounts behind one OpenAI-compatible endpoint, with virtual keys, budgets, built-in token savers and an MCP…
Ctxweight
Static, pre-flight audit of your AI agent's context cost — know what CLAUDE.md, AGENTS.md, skills and MCP schemas cost per turn, before you run the agent.
Leptin
Personal, local-first memory infrastructure for your coding agent. No account, no subscription; the agent can install it itself. Keeps long-term memory correct when decisions chan…
Lucider
Comment directives in, compact AI context out — a drift-aware code graph for JS/TS that gives Claude, Codex & other assistants a small query pack instead of the whole tree. CLI +…
Modelbound Cursor Extension
Cursor & VS Code extension — sync rules, skills, and system prompts with ModelBound. MCP bridge, version control, and Skill Development Pipeline.
Ctxdiet
Detect, fix, and measure AI coding-agent context-token waste across Claude Code, Codex, Cursor, Gemini & Copilot.
Token Save MCP
Stop your coding agent burning context on file reads. Delegates big reads to a cheap worker model and returns only the answer — 87-99% saved, measured per call. A hook enforces it…
Specter Tree
Reduce Claude Code token usage 54–67%. MCP server for web engineers — AI agents find symbols, trace callers, and map hierarchies by name instead of reading files. Built for TypeSc…
Cost Analyzer
Analyze MCP tool schema overhead, token usage, and per-turn cost for AI agents. Estimate context bloat, tool-calling overhead, and routing savings for OpenAI-compatible backends.
Chroman
Drop-in Chrome MCP supplement. Playwright + stealth. ~700x token reduction vs browser MCP on admin dashboards.
Agentic Context Compression Framework
Rust MCP server for lossless agent-context compression, reducing token usage while preserving retrieval accuracy.
Cc Lean
Static, offline audit + setup for a lean Claude Code — flags never-used MCP connectors, oversized CLAUDE.md, and missing guardrails.
DeltaLens
Semantic-diff-aware code intelligence for AI coding assistants
Sherpa MCP
A Claude Code plugin that offloads the heavy lifting — reading, searching, and batch-editing code — to your local LLM. Claude does the thinking; your local model does the grunt wo…
Autonomous Shell Eaze Editor Plugin
🐚 An unofficial shell plugin for Eaze Editor that gives AI agents secure, autonomous access to your system's shell — with persistent sessions, async execution, interactive input,…
Pypkg Audit Ptc Agent
MCP-based context engineering patterns (PTC + PTD) achieving 51% token reduction vs ReAct for LLM agent systems
Ctxpress
Agent 上下文压缩引擎（Java）—— 在工具输出/日志/RAG 片段进入 LLM 前做确定性、可审计、关键信息零丢失的压缩
Context Loss Audit
Audit what your output compressor silently deleted: how much of the reduction was real noise, how much was signal. Turns a compressor's 'cuts 90%' claim into two honest numbers.
Shuttle Stack
Local-inference layer for coding agents: your files are read by llama.cpp on your machine, not by your agent's context. MCP, rootless Podman, no egress, cited answers, measured.
Alphaforensics MCP
AgentCost — AI Agent Spend Analysis. MCP server that analyzes Claude Code session logs to find token waste and optimization opportunities. Free preview tier available.
Token Guard
MCP server, written in Java 21 and compiled to a GraalVM native image, that reduces LLM token consumption in agentic coding workflows.
Sqlite Slim
sqlite MCP (33% less tokens). Quick setup: npx sqlite-slim --setup
Weline Codex MCP
将 Codex 的逐文件搜索与逐次修改升级为任务级批量读取和多文件批量提交，片段响应节省 Token，通过持久索引加速编码，通过文件锁、Hash、原子提交与回滚保护多会话修改，通过零配置项目隔离避免知识串扰，并将经过验证的开发经验持续产出为可复用 Skill。 一次安装，自动分项目；一次取全，一次批量提交；多会话有锁，不覆盖、不丢代码；少花 Token，更…
Tracefrugal
Measure Claude Code and Codex usage. Try reversible local Claude optimizations with version checks, hourly comparisons and quality history. Go, EN/KO.
PyStreamMCP
Intelligence layer for AI agents. Query planning, context discovery, cost optimization. 60-75% token reduction while maintaining quality.
Foveal
Multimodal working memory for agents: perceive each image once, reference it cheaply, zoom in only when needed and share what was learned across sub-agents.
Programmatic Tool Calling AI SDK
🤖 Optimize LLM usage by streamlining tool calls with code generation and sandbox execution for reduced costs and latency in any model.
Slim
Self-learning MCP proxy. Watches your Claude Code usage, generates optimized proxies, cuts token costs by 99%.
Tokenstunt
An agentic plugin to optimize token consumption and accelerate software development x5
Adaptive Prompt Compressor
Adaptive Prompt Compression system powered by Contextual Bandit (LinUCB) to optimize LLM API costs and response quality. 🧠🤖
Engram
The context spine that 10x's every AI coding session. Live in 8 IDEs (Claude Code, Cursor, Cline, Continue, Aider, Codex, Windsurf, Zed) via npm + OpenVSX + Anthropic plugin direc…
Token Saver
Content-aware output compression for AI coding assistants. 36 specialized processors cut CLI output tokens by 60-99% (git, pytest, npm, terraform, kubectl, docker, and more) witho…
Lens
Semantic MCP router/proxy: front a fleet of MCP servers, cut tool-definition context ~98%. Lazy tool discovery for Claude, Cursor & AI agents.
Slim
MCP Slim - Lightweight CLI proxy for AI agents that reduces token usage vs full MCP
Consult
No description published.
Thelyceum 22
No description published.
Betterthanjson
No description published.