Token compressor

Measure what Chinese/Cantonese actually costs in tokens - and why. MCP server: cross-script comparison, per-token attribution, reproducible benchmark.

MCP server, written in Java 21 and compiled to a GraalVM native image, that reduces LLM token consumption in agentic coding workflows.

MCP server para validar tokens Betha

Trade tokenized stocks and equities onchain via Robinhood Chain and the Orkid solver ne…

MCP server for analyzing and optimizing context window token usage — audit tool definitions, compress schemas, track usage, and reduce bloat

Token usage auditor for AI coding tools. Investigate context bloat across Claude Code, Codex CLI & Gemini CLI.

Request-path token proxy + analyzer for agent conversations. Live: cut 74% of input tokens on a real DeepSeek call (mcp-token-saver-proxy.fly.dev). MIT core, no-LLM, crypto-native Pro.

MCP server that compresses prompts 40-60% using local LLM + embedding validation

MCP 服务器 — 把 token-budget 核心能力暴露给所有支持 MCP 的客户端（Claude Desktop / Cursor / Trae / Cline / DSH 等）

Save up to 80% tokens when AI reads code — MCP server for token-efficient code navigation, AST-aware structural reading instead of dumping full files into context window

Pre-execution LLM cost estimation, model comparison, prompt compression, and budget checking for AI agents. Zero LLM costs.

MCP server for context window optimization — audit token budgets, compress schemas, optimize tool loading

Find where your design-token sources disagree. Point it at a Figma export and a live-site scan (any DTCG files) and it shows you exactly which tokens have drifted, how much it matters, and gives you a clean diff to act on.

Zero-dependency MCP server that stops AI coding agents from wasting tokens. Works with Claude Code, Claude Desktop, Cursor.

Zero-dependency context window compressor, code signature folder, JSON minifier & token estimator for AI coding agents and MCP.

One-command installer for the Token Optimizer MCP server, skills, plugins, gateway config, and default-on instructions.

Local-first MCP server that returns distilled, faithful code context to cut LLM token usage without degrading reasoning.

An MCP server providing tools for AI agents to mint ERC-20 tokens, supporting 21 blockchains.

Local-first token reduction engine and MCP server: gives AI coding agents dependency skeletons (types, signatures, exports) instead of full files, so they read far fewer tokens.

A local proxy that strips web pages down to clean text before they enter your AI agent's context window. 704K tokens → 2.6K tokens. No LLM required.

This is a token optimizer. It forwards commands with heavy token consumption to an openrouter model or a local llm.

Your design system says one thing, your product ships another. Compare tokens from any design tool (Figma, Sketch, Penpot), live sites & apps, or codebases — get conflicts, confidence scores, and WCAG drift checks. CLI + library + MCP server.

Count and cut the tokens your prompts, chats and agents use, adapted to the model and task. MCP server and self-hosted gateway. Collects no data.

Autonomous AI agent tool and MCP server for semantic token compression and L402 edge solvency clearance.

MCP server for Angular: compiler-backed template answers, component contracts and version-accurate facts that save AI agents tokens

MCP server that translates design tokens between platforms — Tailwind, Figma, CSS to Material 3, SwiftUI, and CSS Variables

Agent Token Budget MCP — per-session spend cap with signed budget-exhausted attestations. Twin of bft-progress-council-mcp (spend-axis vs stall-axis guardrail). By MEOK AI Labs.

MCP server to price, check holdings of and burn $THREE on Solana from an AI agent, with a USD cap and confirmation.

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.

Slim agent tool output before it enters context: strip ANSI, fold repeated lines, collapse blank runs. Zero dependencies, never throws.

MCP server: ERC-20 honeypot and rug-pull check on Base and Ethereum before your agent swaps or approves, plus swap route data.

Cuts AI agent web-fetching costs by up to 99.9% by stripping junk from web pages before they reach your LLM

MCP server that translates design tokens between platforms — Tailwind, Figma, CSS to Material 3, SwiftUI, and CSS Variables. Built for the v0 → Figma → Claude Code pipeline.

Save 60-80% tokens when AI reads code — MCP server for token-efficient code navigation with AST-aware structural reading

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.

MCP server for Angular: compiler-backed template answers, component contracts and version-accurate facts that save AI agents tokens

Cuts Claude Code and LLM token usage by 60-85% via AST navigation, deduplication, and context-budget optimization.

Rug check any token on Base, Ethereum, Arbitrum, Optimism, Polygon or Solana: a 0-100 risk score with plain reasons, a CLEAN/MID/SKETCHY/RUGGY verdict with a share card, and a watchlist that re-checks up to 5 tokens per call. Pays $0.01 per call in USDC o

MCP server that resolves Solana .sol names and checks whether a three.ws agent handle is free to claim. No key needed.

💎 Semantic Context Compressor, Live Token/USD Cost Calculator & Adaptive Model-Tier Router MCP Server — Cut LLM token bills by 85% across Claude Code, Cursor, VS Code, Codex & Antigravity.

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.

Real-time Claude.ai/Codex subscription awareness for AI coding assistants. Surfaces your live Session 5hr and Weekly 7day utilization, forecasts when you'll hit the limit, gates expensive operations before they run, and measures real per-task cost — all without leaving your machine.

Curated, measurement-driven collection of token-saving MCPs for Claude Code, Codex, Cursor & Windsurf. Each MCP shipped here has passed Humanswith.ai's deterministic-compressor benchmark with documented byte-saving + quality-preservation measurements.

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 in Claude Code; the MCP tools work in any client.

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.

For OpenClaw, Hermes and more. Find free and low-cost inference (LLM models). Use them directly. Provides both a CLI and MCP server that knows which free-tier LLM APIs exist, which ones you have keys for, and which one fits your task. Returns endpoints so can you call models directly. No proxy, no middleware, no latency tax.

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.

Solana token safety check for AI trading agents and MCP: SAFE / CAUTION / DANGER with reasons from mint and freeze authority, Token-2022 traps (permanent delegate, transfer hook, transfer fee, default-frozen, pausable), metadata authority, DEX liquidity a

MCP server for converting JSON to TOON (Token-Oriented Object Notation) format - saves 30-60% on AI tokens

MCP server that analyzes your MCP setup: token costs, bloated schemas, duplicate tools, and optimization tips

MCP server for Solana trading in Claude Desktop — check balances, swap tokens, send SOL, and get prices via natural language

MCP server for Atlassian Jira built on scoped API tokens — server-side scope enforcement, configurable toolsets, project allowlisting, and Markdown/ADF fidelity

An MCP server that exposes Quieto Tokens design token generation and analysis as tools for LLMs.

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.

CHROMA — Design Tokens Agent by VibeCodes. Paletas, tokens e contraste WCAG.

Token-budgeted, self-healing browser automation MCP server: returns only what changed, ~99% fewer tokens than full-tree servers.

Token-efficient Figma MCP server with image export, query DSL, and design token support

MCP server exposing ERC-7303 (Token-Controlled Token Circulation) on-chain roles to AI agents

Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Cursor, Codex, Copilot, Gemini CLI. Local MCP server, free, open source.