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.
-
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 -
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.
pypi MIT ★ 5 -
Aether Pulse — Open-Source AI Token Efficiency Leaderboard, Cache Doctor MCP Server & Architect Loadout Platform by Eloquent (@mjeanhudson-dev)
-
Dev tools, optimized for agents. Structured, token-efficient MCP servers for git, test runners, npm, Docker, and more.
npm MIT ★ 141 -
Codex plugin MCP server (codex-plugin-mcp) for token efficiency, token reduction, context compression: exact-recoverable terminal, file, project, web, memory.
MIT ★ 4 -
stumpgithub.com/hegner123/stumpupdated this year
Token-efficient directory tree visualization MCP server in Zig - optimized for LLM consumption with 50%+ reduction vs standard tree output
MIT -
Token-efficient local code retrieval MCP server — index a codebase once with tree-sitter, query exact symbols instead of re-reading files.
MIT -
MCP server for efficient context sharing between Claude Code sub-agents with 96% token reduction via action-based tools
npm MIT -
mcp-servergithub.com/minhtri22/mcp-serverupdated this year
A Token-Efficient Model Context Protocol (MCP) Server. Empowers AI Agents with Semantic Long-term Memory, Agile Dashboard, and a Dynamic Plugin Sandbox
-
Token-efficient MCP file, shell, SSH and ops tools for coding agents — bounded reads, dedup, spill recovery and span edits.
GPL-3.0 ★ 3 -
recursive-thinking-mcpgithub.com/parth3930/recursive-thinking-mcpupdated this year
Token-efficient recursive thinking MCP server for AI agents. Achieve production-ready solutions through iterative refinement with 70% token reduction. Perfect for Claude, AI problem-solving, and complex task automation.
npm MIT -
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 -
mcp-web-fetchgithub.com/pavex/mcp-web-fetchupdated this year
Token-efficient web reading and HTTP requests for MCP agents.
-
Save 60-80% tokens when AI reads code — MCP server for token-efficient code navigation with AST-aware structural reading
npm ★ 5 -
figma-querygithub.com/standardbeagle/figma-queryupdated this year
Token-efficient Figma MCP server with image export, query DSL, and design token support
-
code-nav-mcpgithub.com/Balki01/code-nav-mcpupdated this year
Efficient code navigation MCP server - reduce Claude Code token usage by 95%+
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 -
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 -
kinrggithub.com/hotienky/kinrgupdated this year
The Context Engine for AI Coding: Persistent incremental knowledge graph for token-efficient, context-aware reviews
pypi MIT -
sylvangithub.com/darki73/sylvanupdated this year
Code intelligence MCP server for token-efficient code retrieval, analysis, and refactoring
pypi Custom Non-Commercial -
Token-efficient MCP server for structured documentation retrieval via section-level indexing
pypi LicenseRef-jDocMunch-Dual-Use -
Token-efficient MCP server for tabular data retrieval via CSV/Excel/Parquet/JSONL indexing
pypi LicenseRef-jDataMunch-Dual-Use -
nooongithub.com/corrupt952/nooonupdated this year
Lightweight, read-only Notion MCP Server optimized for token efficiency
npm MIT -
memory-mcp-litegithub.com/thuupx/memory-mcp-liteupdated this year
A local-first, token-efficient MCP memory server for AI coding clients
★ 4 -
MCP plugin focused on boosting agent context efficiency and saving tokens
MIT ★ 1 -
octoboost-mcp-servergithub.com/eugenregehr/octoboost-mcp-serverupdated this year
OctoBoost MCP Server for token-efficient SEO / GEO analysis. Analyze multiple URLs with categorized checks and scored results.
npm -
SigRankno update data
SigRank — ranks AI coding operators by token cascade efficiency (Yield = Cache Reads × Output / Input²). Tools for yield calculation, leaderboard queries, operator lookups, local token usage pulls, and signed token-count submission to the public board. Privacy-first: runs locally, only four token counts leave the machine (ed25519-signed). Install: npx sigrank
smithery -
pawsift-mcpgithub.com/dolphprefect/pawsift-mcpupdated this year
PawSift 🐾 is a high-performance, token efficient mcp server that bridges Android Logcat to LLMs.
★ 3 -
Token-efficient multi-agent task dispatcher & self-scaling orchestrator for Antigravity (AGY)
MIT -
MCP server with code-intelligence tools and git-like version management that carries minimal cross-session context (file diffs, insight notes, task handovers). Optimized for token efficiency and human review.
LGPL-3.0 -
Free, open-source, token-efficient local alternative to Firecrawl with native MCP Server for LLMs (>73% token reduction).
MIT ★ 5 -
Universal & Token-Efficient Java Decompiler and MCP Server for AI & Developers
npm Apache-2.0 -
ohh-my-excelgithub.com/adityaidev/ohh-my-excelupdated this year
Persistent, incrementally-updated knowledge graph for Excel workbooks — safe, fast, token-efficient MCP server
pypi MIT -
Token-efficient MCP server for tabular data retrieval. Index CSV/Excel files, query rows, aggregate — 99%+ token savings vs raw file reads.
NOASSERTION ★ 83 -
Token-efficient MCP control for an AI agent's real Chrome session. Control your browser with AI without the token cost, but with all the functionality.
MIT -
qhgithub.com/anderson-0/qhactive
Token-efficient database MCP server for AI agents (Go)
MIT -
Token-efficient Outlook mail, calendar and Teams for AI agents: CLI + MCP server
MIT -
Quickly reads webpages and converts to markdown for fast, token efficient web scraping
npm MIT ★ 163 -
Matryoshkagithub.com/yogthos/Matryoshkaupdated this year
MCP server for token-efficient large document analysis via the use of REPL state
Apache-2.0 ★ 149 -
kuri-browser-agentgithub.com/theerud/kuri-browser-agentupdated this year
A lightweight, token-efficient browser automation extension for Gemini CLI, powered by Kuri.
MIT -
Read Microsoft Loop files and workspaces through Microsoft Graph with bounded, token-efficient MCP responses.
npm MIT -
docxenginegithub.com/ruwadgroup/docxengineupdated this year
AI-optimized DOCX manipulation engine: deterministic OOXML editing with tracked changes, hash-anchored addressing, and a token-efficient agent view.
pypi Apache-2.0 -
hartracegithub.com/rafsanbasunia/hartraceupdated this year
An MCP server for HTTP traffic analysis with value provenance tracing — token-efficient HAR inspection for AI agents.
pypi MIT -
Token-efficient browser MCP server — structured web pages for AI agents, not raw accessibility dumps
npm MIT ★ 184 -
Local, token-efficient MCP server for evidence-first reading of PDF, DOCX, PPT, and PPTX research documents.
★ 2 -
Token-efficient MCP server for codebase search, NuGet decompilation, and deep PDF reading.
MIT -
n24q02m-crgactive
Token-efficient code review knowledge graph: semantic search and call-graph resolution.
pypi Apache-2.0 -
High-performance, token-efficient Chromium browser automation for AI coding agents. Powered by a lightweight native Rust MCP Server and a Manifest V3 Google Chrome Extension.
Apache-2.0 ★ 1 -
astrovisor-mcpgithub.com/rokoss21/astrovisor-mcpupdated this year
AstroVisor MCP for Claude and AI clients — stdio + Streamable HTTP, live OpenAPI discovery, 456 operations and token-efficient results.
MIT ★ 5 -
checkforgithub.com/hegner123/checkforupdated this year
Token-efficient file search tool with JSON output and MCP server support
MIT -
The Compiler-Aware Operating System Kernel CodeGraph Engine for Token-Efficient Structural Codebase Retrieval
MIT ★ 4 -
aosp-mcpgithub.com/ItzNotABug/aosp-mcpupdated this year
Android source code search for AI agents: a fast, token-efficient MCP server for cs.android.com
Apache-2.0 ★ 4 -
Persistent, token-efficient repository memory for AI tools: symbols, import graph and LLM summaries per file — CLI, library and MCP server
npm MIT -
Token-efficient MCP server for DaVinci Resolve Studio — kernel + domain architecture keeps context cost proportional to the work.
GPL-3.0 ★ 26 -
Skims the web without making waves — a Japanese-web-native MCP server for low-impact, token-efficient web collection
MIT -
codemagic-mcpgithub.com/lexandro/codemagic-mcpupdated this year
MCP server for Codemagic CI/CD: start builds, poll status, diagnose failures. Token-efficient and secret-redacting by design.
MIT ★ 1 -
Token-efficient, markdown-first Notion MCP server — agents write markdown, never touch raw Notion JSON
npm MIT -
Token-efficient context engine for AI coding agents. v2.23.0: token-killer pack — deep-forget (unlearning propagation), dangling-reference guard, MCP schemas-on-demand. 2462 tests, 43 MCP tools, Elastic-2.0.
NOASSERTION ★ 3 -
toon-memorygithub.com/LuiggiVal08/toon-memoryupdated this year
MCP server giving AI coding agents offline, token-efficient persistent memory — recall decisions, patterns, and bugs across sessions with 68.5% fewer tokens than re-reading context. No LLM, no server; works with 15+ agents.
MIT ★ 12 -
Token-efficient browser automation MCP for AI agents, with semantic page snapshots and stable element IDs.
MIT ★ 19