- Conduid
- Marketplace
- #tokens
MCP servers tagged tokens
83 live MCP servers tagged "tokens", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with tokens.
Caveman Shrink
MCP proxy that compresses prose fields (tool descriptions, etc.) using caveman rules. Same accuracy, fewer context tokens.
Goldrush MCP Server
This project provides a MCP (Model Context Protocol) server that exposes Covalent's GoldRush APIs as MCP resources and tools. It is implemented in TypeScript using @modelcontextpr…
Lean Ctx
Hybrid Context Optimizer — Shell Hook + MCP Server. Reduces LLM token consumption by 89-99%. Single Rust binary, zero dependencies.
Tokenfold
Local, provider-neutral compression for LLM prompts, tool schemas, JSON, logs, and diffs. Lossless, receipt-audited, no ML tax.
Slack Tools
Tools for interacting with Slack's local data with Model Context Protocol support
Ctxray
X-ray your AI coding agent's context window — see what CLAUDE.md, rules, skills and MCP tool schemas cost you in tokens, across Claude Code / Cursor / Codex / Copilot / Gemini / W…
Indxr
A fast codebase indexer and MCP server for AI coding agents.
Ide Relay MCP
The missing human checkpoint for AI coding agents. Give your AI agent a "pause & ask" button — review, correct, or enrich every step before it runs.
Gortex
High-performance code intelligence engine that indexes repositories into an in-memory knowledge graph and exposes it via CLI, MCP Server, and web UI. Built for AI coding agents -…
Tokenuse
A Rust TUI and Desktop app for exploring AI coding tool token and cost usage
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…
Scopeon
AI context observability & optimization for Claude Code, Copilot CLI, Codex, Gemini — TUI dashboard, preset optimization, cost tracking, CI gates
Token Reducer
High-performance token and context compressor for coding agents, AGY, and developer CLI tools
Dsh MCP Lazy
Lazy MCP gateway for DeepSeek Harness: one stable proxy tool instead of N tool schemas, servers connect on first use and idle out, metadata cached to disk.
Dsh MCP Lazy
Lazy MCP gateway for DeepSeek Harness: one stable proxy tool instead of N tool schemas, servers connect on first use and idle out, metadata cached to disk.
Context Cost
Measure what your MCP servers cost in context tokens — audit your own config, or badge the server you publish
Tokensfun
tokensfun mcp for Claude Code existing-app token deployment.
Brevix Shrink
MCP middleware proxy that compresses tools/list, prompts/list, and resources/list responses to save tokens. Sister project to Brevix.
Tokens For Good
Donate your spare AI tokens to research nonprofits for Fierce Philanthropy
Agentctx
Agent Context Manager — manage context windows, memory, roles, token budgets, and multi-agent chains for Claude Code, Codex, Cursor, and any LLM-based agentic tool.
Tooltax
Token-budget linter and public leaderboard for MCP tool schemas.
Xchain
Model Context Protocol (MCP) stdio server for the XChain Platform: read chain/token/balance data on BTC, LTC and DOGE (mainnet/testnet/regtest), and optionally submit policy-gated…
Agent Context Cost
Claude Code context window and token usage audit: see what your skills, subagents, plugins, CLAUDE.md and MCP servers cost before you type, ranked, with duplicates flagged and rem…
Ctxslim
Put your MCP servers on a diet. A 100% local proxy that cuts MCP context bloat by up to 72%. Zero config, zero API keys.
Haircut
The barber for your coding agents' config. Weighs everything Claude Code, Codex and eight other agents load, in tokens from your own transcripts, and parks the dead weight with a…
Siftr
Fast, cheap judgment for AI coding agents: semantic search, focused reads and list picking in ~2s. CLI + MCP server on TypeSafe Jev. Benchmarked on SWE-bench.
Clifast
Turn any file into a CLI from TypeScript/JavaScript exports
Context Cost
Measure what your MCP servers cost you in context tokens — audit your own config, diff a change, gate it in CI
Context Tax
What Claude Code sends on every turn before you type a word: what it costs, which of it you never used, and which of your skills never reached the agent.
Claude Diet
See which skills, plugins, memory, and MCP configs are eating your Claude Code context — before your bill does. Local CLI, zero network calls, terminal + HTML + JSON output.
Token Diet
Local token-saving, intelligence-preserving context layer for Claude Code, Cowork, Codex and any MCP host. Press / and save tokens.
Pastoon
Auto-convert clipboard JSON to TOON format - 40% fewer LLM tokens. macOS tray + MCP server.
Context Tax
What your coding agent's context costs you every turn, and which of it you never used.
Mrcp Engine
Deterministic AST code-intelligence engine for AI agents — MCP server + REST API for architecture analysis, security audits, and doc generation.
Jettison
Token optimizer for AI coding agents. Repo map, read pruning, prose compression — client-side, no proxy. 20-25% fewer turns, measured by live A/B. Verify it on your own repo.
Context Budget
Audit how many context tokens each MCP server's tools cost before they fill your agent's window.
Flattype
Flatten JSON into compact key: value text for APIs and LLMs: typed models, HTTP, React, Vue, Angular, Svelte, Solid, Python (PyPI) and Claude/MCP helpers
Ctxray
X-ray your AI coding agent's context window — see what CLAUDE.md, rules, skills and MCP tool schemas cost you in tokens, across Claude Code / Cursor / Codex / Copilot / Gemini / W…
inth3shadows/terse
<server>`
Macu Minimize AI Credit Usage
Minimize AI credit usage. Analyze tool call patterns across Claude Code, OpenCode & Codex to find unused tools and cut token waste
Deus In Machina
Design System Runtime (DSR) — enforcement + structure + runtime for design systems
ContextTax
Measure the context-window tax an MCP server charges your AI agent — the real token cost of its tool schemas + responses. Ground truth (Anthropic count_tokens) or keyless estimate…
Warden AI
The structurally-verified context layer for AI coding agents. Cut 50-90% of your agent's token spend.
Compendium
MCP server that compresses, summarizes, and filters context to minimize LLM token usage
Designsystemet Flutter
Flutter-implementasjon av Designsystemet (designsystemet.no).
Developer Ctx
MCP Server that Exposes Project Context, Codebase Search, Safe Commands & API Spec Summary for Any Model Or MCP Client
Context Usage MCP
MCP server exposing a get_context_usage tool that reports the current session's raw token usage from its on-disk transcript/rollout. Works under Claude Code and Codex CLI.
Turnstile
Scan any MCP server: a token-cost + metadata-safety report card at the tools/list boundary. Deterministic, i18n-honest concealment detection. Python + TypeScript.
Winnow
Local-first context compression for AI agents — content-aware, reversible, zero runtime deps. Cuts agent token usage 40-95% while keeping the signal.
Token Lint
Token budget linter for MCP tool schemas — see what your connected servers cost before you burn the context window