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. 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.
-
Codex plugin MCP server (codex-plugin-mcp) for token efficiency, token reduction, context compression: exact-recoverable terminal, file, project, web, memory.
MIT ★ 4 -
Universal Plop-In AI Token Efficiency Leaderboard, Top 10 Harness Liquid-Physics HUD, Cache Doctor MCP Server, and Architect Loadout Platform for Claude Code, Google Antigravity, OpenAI Codex, Cursor, Aider, Windsurf, Continue, Copilot, OpenHands, and T3
npm MIT -
Token-efficiency plugin for Claude Code and Codex: MCP tools and hooks that replace high-volume Read/Grep/Edit/Bash calls with compact equivalents, powered by @ashlr/core-efficiency.
npm MIT ★ 3 -
Turn any folder or Git repo into safe, token-efficient context for LLMs, AI chats, and coding agents like Claude Code, Codex, and Cursor — local-first GUI, TUI, CLI, and a read-only MCP server with Live Context, agent journal, Smart Ignore, secret/PII redaction, Git scopes, and code compression. Windows, macOS, Linux.
Apache-2.0 ★ 41 -
efficient-tokengithub.com/fahomid/efficient-tokenupdated this year
Local-first MCP server that returns distilled, faithful code context to cut LLM token usage without degrading reasoning.
npm MIT -
Aether Pulse — Open-Source AI Token Efficiency Leaderboard, Cache Doctor MCP Server & Architect Loadout Platform by Eloquent (@mjeanhudson-dev)
-
Token-efficient MCP file, shell, SSH and ops tools for coding agents — bounded reads, dedup, spill recovery and span edits.
GPL-3.0 ★ 3 -
Token-lean, ref-stable, privacy-first browser protocol for AI agents (core + Playwright/CDP driver + MCP server).
npm MIT -
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
npm MIT -
Quickly reads webpages and converts to markdown for fast, token efficient web scraping
npm MIT ★ 163 -
Token-efficient MCP server for tabular data retrieval. Index CSV/Excel files, query rows, aggregate — 99%+ token savings vs raw file reads.
NOASSERTION ★ 83 -
n24q02m-crgactive
Token-efficient code review knowledge graph: semantic search and call-graph resolution.
pypi Apache-2.0 -
crggithub.com/n24q02m/crgactive
Knowledge graph for token-efficient code reviews -- semantic search and call-graph resolution across your codebase.
pypi Apache-2.0 ★ 76 -
Token-efficient code reading for AI coding agents: budgeted, symbol-aware, diff-aware reads over MCP.
MIT ★ 1 -
Token-efficient code intelligence for AI agents — 66 MCP tools via tree-sitter AST, BM25F search, semantic search, and LSP bridge
npm NOASSERTION ★ 4 -
Local-first long-term memory for AI agents - plain Markdown vault + thin MCP server. CJK-aware BM25, token-efficient by design.
NOASSERTION ★ 6 -
toon-memorygithub.com/luiggival08/toon-memoryupdated this year
The Continuity Layer for AI Agents — an MCP memory server that preserves project knowledge, decisions, and conventions across sessions so every session starts where the last one ended. Offline, token-efficient, no LLM, no server; works with 20+ agents.
npm MIT -
knotgithub.com/raultov/knotactive
High-performance Rust MCP server & CLI codebase indexer for AI agents. Unlocks deep codebase understanding through semantic vector search, structural graph traversal, and cross-repo dependency resolution. Empowers AI coding agents with semantic and structural search for maximum token efficiency.
MIT ★ 11