Get Started

Technology · Protocol

Model Context Protocol

Protocol · Anthropic · Catalog tech@1

Open protocol connecting AI applications to tools and data.

Categories
Matched as
  • mcp
  • model context protocol

Momentum

Each signal is ranked as a percentile among the technologies that have it. A signal without enough history is not counted, and never shown as zero. How momentum works

Momentum

90/ 100

2 of 5 signals

The mean of Model Context Protocol’s 2 signals, each ranked as a percentile among the technologies that have it, on a scale of 0 to 100. Signals without history are left out, never counted as zero.

Snapshot OCT 24, 2026 · Scoring tech@1

Official repository stars
Collecting
Star growth needs repository snapshots 30 days apart.47,315 stars now
Member repository stars
Collecting
Star growth needs repository snapshots 30 days apart.3 new members in 30 days
Package adoption
+31.0% · 30d
96th percentile among technologies with this signalnpm, in its own unit
Open models
No official models
No official model on Hugging Face, so this signal does not apply.
News
7 vs 1
84th percentile among technologies with this signal7 in the last 30 days · 1 in the 30 before

Adoption by registry

The growth of Model Context Protocol’s own packages, one row per registry in that registry’s own unit. Registries count different things over different windows, so they are never added together.

RegistryFigureAbout 30 days ago → latestGrowthPackages
npmDownloads (30 days)260.4M → 341.2Mdownloads / 30 days+31.0% · 30d9

News activity

Events · 7 days
2published events that mention it
Events · 30 days
7published events that mention it
Previous 30 days
1events in the 30 days before

Momentum history

Momentum history 2 daily scores · 0 to 100
OCT 8: momentum 91.05OCT 24: momentum 90.24
Table of snapshots (2)
DayMomentumMembersOfficial starsNews · 30d
OCT 24, 20269066147,3157
OCT 8, 20269166147,3156

Repositories

Official 3

Members 661repositories tagged with one of its aliases, most-starred first

  • adtexterry-lgtm/unigit-ecosystem

    UNIGIT public brand and ecosystem hub — AI should work for everyone.

    Tagged mcpJavaScript

    1.3K

  • apecloud/ApeRAG

    ApeRAG: Production-ready GraphRAG with multi-modal indexing, AI agents, MCP support, and scalable K8s deployment

    Tagged mcpPython

    1.3K

  • Ataraxy-Labs/weave

    Entity-level git merge driver. Resolves false conflicts git invents when independent agents edit the same file. ~95% reduction vs. line-based merge.

    Tagged mcpRust

    1.3K

  • strands-agents/tools

    A set of tools that gives agents powerful capabilities.

    Tagged mcpPython

    1.3K

  • BetterDB-inc/monitor

    Real-time monitoring, slowlog analysis, and audit trails for Valkey and Redis

    Tagged mcpTypeScript

    1.3K

  • SmythOS/sre

    The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular, and production-ready, it lets developers build, run, and manage intelligent agents across local, cloud, and edge environments.

    Tagged mcpTypeScript

    1.3K

  • caliber-ai-org/ai-setup

    Continuously sync your AI setups with one command. Codebase tailor suited agent skills, MCPs and config files for Claude Code, Cursor, and Codex.

    Tagged mcpTypeScript

    1.3K

  • datalayer/jupyter-mcp-server

    🪐 🔧 Model Context Protocol (MCP) Server for Jupyter.

    Tagged mcpPython

    1.3K

  • LangChat/langchat

    LangChat 是由 LangChat Team 开发的开源 AI Agent 应用平台，支持多模型、Agent、知识库 RAG、Skills、MCP 与智能问数。

    Tagged mcpVue

    1.3K

  • K-Dense-AI/k-dense-byok

    An AI co-scientist running on your desktop. Claude Science but better.

    Tagged mcpTypeScript

    1.3K

  • mcpjungle/MCPJungle

    One place to manage & connect to all your MCP servers

    Tagged mcpGo

    1.3K

  • pnoker/iot-dc3

    IoT DC3 — Connect the Physical World to AI. An open-source Industrial IoT Runtime for Physical AI: 36 protocol drivers, edge-to-cloud data delivery, and an MCP tool gateway so AI agents act on devices in a safe, controllable, traceable loop.

    Tagged mcpJava

    1.3K

Packages

“Is” packages are Model Context Protocol itself; ecosystem packages depend on them. The two are counted separately and never added together. Adoption is each registry’s own figure, with its percentile within that registry.

Is 15the technology itself, most-adopted first

  • @modelcontextprotocol/sdk

    Model Context Protocol implementation for TypeScript

    Listed in the catalognpm

    242.4Mdownloads / 30 daysTop 10% on npm
  • @modelcontextprotocol/core

    Model Context Protocol for TypeScript — public Zod schemas (spec + OAuth/OpenID)

    Published from modelcontextprotocol/typescript-sdknpm

    36.1Mdownloads / 30 daysTop 25% on npm
  • @modelcontextprotocol/server

    Model Context Protocol implementation for TypeScript - Server package

    Published from modelcontextprotocol/typescript-sdknpm

    29.6Mdownloads / 30 daysTop 25% on npm
  • @modelcontextprotocol/client

    Model Context Protocol implementation for TypeScript - Client package

    Published from modelcontextprotocol/typescript-sdknpm

    22.1Mdownloads / 30 daysTop 25% on npm
  • @modelcontextprotocol/node

    Model Context Protocol implementation for TypeScript - Node.js middleware

    Published from modelcontextprotocol/typescript-sdknpm

    8.8Mdownloads / 30 daysTop 50% on npm
  • @modelcontextprotocol/express

    Express adapters for the Model Context Protocol TypeScript server SDK - Express middleware

    Published from modelcontextprotocol/typescript-sdknpm

    1.8Mdownloads / 30 daysLower half on npm
  • @modelcontextprotocol/hono

    Hono adapters for the Model Context Protocol TypeScript server SDK - Hono middleware

    Published from modelcontextprotocol/typescript-sdknpm

    368.7Kdownloads / 30 daysLower half on npm
  • @modelcontextprotocol/fastify

    Fastify adapters for the Model Context Protocol TypeScript server SDK - Fastify middleware

    Published from modelcontextprotocol/typescript-sdknpm

    90.1Kdownloads / 30 daysLower half on npm
  • @modelcontextprotocol/codemod

    Codemod to migrate MCP TypeScript SDK code from v1 to v2

    Published from modelcontextprotocol/typescript-sdknpm

    4.8Kdownloads / 30 daysLower half on npm
  • dive-mcp-sdk

    Model Context Protocol SDK

    Published from modelcontextprotocol/python-sdkPyPI

    Not published by PyPI
  • hud-mcp-python-sdk

    Model Context Protocol SDK

    Published from modelcontextprotocol/python-sdkPyPI

    Not published by PyPI
  • mcp

    Model Context Protocol SDK

    Listed in the catalogPyPI

    Not published by PyPI

Ecosystem 541packages that depend on it, most-adopted first

  • lumibot

    Python framework for algorithmic trading: backtesting and live deployment for stocks, options, crypto, futures, and forex. Same code for backtest and live trading.

    Depends on mcpPyPI

    Not published by PyPI
  • markitdown-mcp

    An MCP server for the "markitdown" library.

    Depends on mcpPyPI

    Not published by PyPI
  • mcp-ai-forever

    Enhanced MCP server for interactive user feedback and command execution in AI-assisted development, featuring dual interface support (Web UI and Desktop Application) with intelligent environment detection and cross-platform compatibility.

    Depends on mcpPyPI

    Not published by PyPI
  • mcp-antlogs

    A MCP server which proxies requests to a remote MCP server over streamable HTTP or SSE.

    Depends on mcpPyPI

    Not published by PyPI
  • mcp-atlassian

    The Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification. This project enables secure, contextual AI interactions with Atlassian tools while maintaining data privacy and security. Key features include:

    Depends on mcpPyPI

    Not published by PyPI
  • mcp-cmd-execution

    A MCP server which proxies requests to a remote MCP server over streamable HTTP or SSE.

    Depends on mcpPyPI

    Not published by PyPI
  • mcp-contextforge-gateway

    ContextForge AI Gateway — an AI gateway, registry, and proxy for MCP, A2A, and REST/gRPC APIs. Exposes a unified control plane with centralized governance, discovery, and observability. Optimizes agent and tool calling, and supports plugins.

    Depends on mcpPyPI

    Not published by PyPI
  • mcp-feedback

    Enhanced MCP server for interactive user feedback and command execution in AI-assisted development, featuring dual interface support (Web UI and Desktop Application) with intelligent environment detection and cross-platform compatibility.

    Depends on mcpPyPI

    Not published by PyPI
  • mcp-feedback-enhanced

    MCP server for interactive user feedback in AI-assisted development, featuring dual interface support (Web UI and Desktop Application) with intelligent environment detection and cross-platform compatibility.

    Depends on mcpPyPI

    Not published by PyPI
  • mcp-feedback-enhanced-fixed

    Enhanced MCP server for interactive user feedback and command execution in AI-assisted development, featuring dual interface support (Web UI and Desktop Application) with intelligent environment detection and cross-platform compatibility.

    Depends on mcpPyPI

    Not published by PyPI
  • mcp-for-blender

    Open source Blender integration through the Model Context Protocol (not affiliated with Blender Foundation)

    Depends on mcpPyPI

    Not published by PyPI
  • mcp-google-sheets

    This MCP server integrates with your Google Drive and Google Sheets, to enable creating and modifying spreadsheets.

    Depends on mcpPyPI

    Not published by PyPI

Latest news the 10 latest events that mention it