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.
-
@om-surushe/efficient-searchgithub.com/om-surushe/efficient-searchupdated this year
MCP server for compact Google Programmable Search results
npm MIT -
@om-surushe/efficient-adogithub.com/om-surushe/efficient-adoupdated this year
Efficient Azure DevOps MCP - LLM-optimized ADO workflows for AI assistants
npm MIT -
Production-ready GitLab MCP Server with progressive disclosure pattern
npm MIT -
@om-surushe/efficient-ticktickgithub.com/om-surushe/efficient-ticktickupdated this year
Efficient TickTick MCP - LLM-optimized task management with intelligent time handling and 70% lower token costs
npm MIT -
Agent-Efficiency-MCPgithub.com/DillonRich/Agent-Efficiency-MCPupdated this year
Local BYOK MCP. Rewrite messy IDE prompts into Agent_Efficiency_MCP.md, freeze until GO. AGPL-3.0. Commercial licenses available.
AGPL-3.0 ★ 2 -
@efficy/tribecrm-mcp-servergithub.com/efficy-sa/tribecrm-mcp-serverupdated this year
Model Context Protocol server for TribeCRM API - enables AI assistants to interact with TribeCRM
npm MIT -
An MCP server that cuts AI agent token usage by 94% by rendering brand-compliant dashboards from JSON specs instead of raw code. Built by M4TIC.
npm MIT -
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 -
ObsidianPilot: Enhanced MCP server with token-efficient editing for Obsidian vaults
pypi MIT -
@skills-server/mcpgithub.com/ivanenev/skills-serverupdated this year
Enhanced Skills MCP Server with progressive disclosure and token efficiency
npm GPL-3.0 -
@fiialkod/toon-mcp-serverupdated this year
MCP server providing LEAN and TOON format encoding/decoding for token-efficient LLM data exchange
npm MIT -
cdt-smart-snapshotupdated this year
Token-efficient snapshot MCP server for Chrome DevTools protocol: smart_snapshot, snapshot_diff, screenshot_to_disk
npm Apache-2.0 -
zest-langgithub.com/r2jitu/zest-langupdated this year
Token-efficient programming language for LLM tool calls; transpiles to Python; ships with MCP server
★ 1 -
@scottlepper/ultra-bitbucket-mcpupdated this year
Token-efficient MCP server for Bitbucket Cloud. Handle-based diffs, consolidated tools, code-api mode.
npm MIT -
beaglelathegithub.com/beaglelathe/latheupdated this year
Token-efficient MCP server: fused search + batched fuzzy edit, structured test/git/lint/todos/commit tools.
pypi Apache-2.0 -
animamunchgithub.com/animaios/animamunchmcpupdated this year
Token-efficient MCP server for source code exploration via tree-sitter AST parsing
pypi Other/Proprietary License -
Deterministic, token-efficient AST call-graph slicing for AI coding agents, exposed as a local MCP server.
pypi MIT -
Token-efficient MCP server for Jira & Confluence Cloud: shaped, minimal responses that cut agent context use by up to ~98%.
MIT -
MCP server for token-efficient, bounded Docker and Docker Compose operations: logs, inspect, config, compose, run, exec, and startup verification.
BSD-3-Clause -
ado-code-mode-mcpgithub.com/thijs-hakkenberg/ado-code-mode-mcpupdated this year
Token-efficient Azure DevOps MCP server using Code Mode pattern — 2 tools instead of 99, 98% fewer bootstrap tokens
npm MIT -
Aether Pulse — Open-Source AI Token Efficiency Leaderboard, Cache Doctor MCP Server & Architect Loadout Platform by Eloquent (@mjeanhudson-dev)
npm -
excel-lsp-for-AI-agentsgithub.com/Brody900/excel-lsp-for-AI-agentsupdated this year
LSP-style semantic index for AI agents + MCP server for Excel workbooks. Improving token efficiency up to 60x and accuracy by 30%
MIT -
Dev tools, optimized for agents. Structured, token-efficient MCP servers for git, test runners, npm, Docker, and more.
npm MIT ★ 141 -
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 -
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 -
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
-
Aether Browser MCP: Ultra token-efficient Chrome extension and native bridge for AI agents (Claude, Cursor, Antigravity)
npm MIT -
Token-efficient MCP file, shell, SSH and ops tools for coding agents — bounded reads, dedup, spill recovery and span edits.
npm GPL-3.0 ★ 3 -
Codex plugin MCP server (codex-plugin-mcp) for token efficiency, token reduction, context compression: exact-recoverable terminal, file, project, web, memory.
MIT ★ 4 -
pi-tokensavergithub.com/xilnick/pi-tokensaverupdated this year
Give your Pi AI agent a semantic memory — bridges tokensave's Rust-powered local graph engine into your coding workflow for token-efficient codebase exploration
npm MIT -
Token-efficient browser MCP server: headless Chrome in Docker that captures everything (console / network / IndexedDB / snapshots) and lets the model query on read. 56 tools across full / slim / gateway mount modes.
MIT ★ 1 -
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 -
Zero-dependency agent-to-agent codebase wiki for LLMs and AI agents. Autonomously maintained via record-change and mark-green for token-efficient lookup of files, dependencies, health, and summaries — across tiny scripts to 50k+ monorepos. Optional MCP server with rich tools for agents.
pypi MIT -
Free, open-source menu bar app that keeps the app you're using fast: background apps go to efficiency cores, idle apps are frozen when memory runs low, plus per-app CPU and memory limits, a widget, and an MCP server for Claude. Apple Silicon. A rewrite of AppPolice.
mcpb GPL-2.0 ★ 1 -
mcpgithub.com/MARS-Engine/mcpupdated this year
MCP Tools for more efficient work
0BSD -
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 -
Token-efficient SQL execution MCP server.
MIT -
Efficient implementation of the Google Drive MCP server
MIT ★ 72 -
rssdeck-mcpgithub.com/mephistophelesbits/rssdeck-mcpupdated this year
MCP server for AI agents - token-efficient RSS data
MIT -
ezfhirgithub.com/mfaughn/ezfhirupdated this year
AI-first MCP server for token-efficient FHIR specification access
-
Custom MCP server for precise and efficient legal citations
★ 1 -
dauphin-notion-mcpgithub.com/treuille/dauphin-notion-mcpupdated this year
A token-efficient, parallel MCP server for Notion
Apache-2.0 ★ 1 -
another-planka-mcpgithub.com/roelven/another-planka-mcpupdated this year
A token-efficient MCP server to interact with Planka
★ 3 -
Easy efficient MCP server to access the web
MIT -
myelingithub.com/et-do/myelinupdated this year
brain-inspired MCP for persistent efficient context across AI agents
pypi MIT ★ 9 -
AI-powered economic forecasting with MCP - achieving 98% token efficiency
MIT ★ 1 -
mcp-smart-readergithub.com/prefrontal-systems/mcp-smart-readerupdated this year
MCP Smart Reader - Token-efficient document summarization with FastMCP server
-
pywrdrb-mcpgithub.com/Pywr-DRB/pywrdrb-mcpupdated this year
Implements a local MCP to efficiently retrieve Pywr-DRB model details.
-
@randiadiel/tracelensgithub.com/randiadiel/tracelensupdated this year
Context-efficient local log inspection over MCP
npm MIT -
Fast, token-efficient Paradox script explorer for AI assistants
★ 2 -
An MCP server providing an efficient and safe text editor for LLMs
MIT ★ 5 -
deepseek-ocr2-lazygithub.com/groxaxo/deepseek-ocr2-lazyupdated this year
Efficient Lazy-Loading Server for DeepSeek-OCR-2 with MCP Support & Docker
★ 2 -
desk-mcpgithub.com/imohanvadivel/desk-mcpupdated this year
MCP server for the Zoho Desk API — 706 endpoints, 3 context-efficient tools
★ 3 -
bybit-announcements-mcpgithub.com/kukapay/bybit-announcements-mcpupdated this year
Empowering AI agents to fetch, track, and act on Bybit announcements efficiently.
MIT ★ 1 -
Nudgeno update data
MCP server that nudges better AI session behavior through token usage and efficiency analysis
pypi -
A token efficient knowledge & memory solution for agentic workflows.
cargo Apache-2.0 -
Qdrant MCP server compatible with multiple embedding models for efficient vector search and retrieval
pypi Apache-2.0 ★ 3 -
AutoHotkey v2 + UI Automation as token-efficient computer use for AI agents, via MCP
MIT ★ 9