Model Context Protocol (MCP)
Open JSON-RPC protocol that lets AI applications connect to external tools, data sources and prompts through MCP servers.
Reference by Created by Anthropic; stewarded by the MCP maintainers
Chalk Labs
Need help deploying Model Context Protocol (MCP)?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
About
Use cases: api-integration
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
About the protocol
- Specification
- modelcontextprotocol.io/specification/2026-07-28
- Current version
- 2026-07-28blog.modelcontextprotocol.io
- Maintainer
- Created by Anthropic; stewarded by the MCP maintainersblog.modelcontextprotocol.io
- Governance
- Agentic AI Foundation (AAIF), a directed fund under the Linux Foundation, since 2025-12-09blog.modelcontextprotocol.io
- Launched
- 2024-11-25anthropic.com
- Anthropic reports adoption by ChatGPT, Cursor, Gemini, Microsoft Copilot and Visual Studio Code. anthropic.com
- More than 10,000 active public MCP servers as of December 2025. anthropic.com
Listings that use it
45,426 visible listings declare Model Context Protocol (MCP): 44,833 connectors, 226 plugins, 131 agents, 96 agent infrastructure, 67 harnesses & sdks, 28 no-code builders, 23 observability & evals, 22 identity, auth & payments.
Connectors
- 0.875score
World Monitor
worldmonitor.appOfficial
Real-time global intelligence across conflict, markets, energy, trade, shipping and cyber.
ConnectorAFreshness: ARemote★ 89.4KClaude Code +3 - 0.874score
REA
morluto
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
ConnectorAFreshness: ALocal★ 377.4KClaude Code +5 - 0.874score
Front-End Checklist
thedaviddias
Review frontend code and live pages against 386 quality-gated web development rules.
ConnectorAFreshness: ARemoteRead-only★ 74.6KClaude Code +3 - 0.873score
Browser Use
browser-use.comOfficial
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
ConnectorAFreshness: ARemoteLocal★ 119K↓ 1.5M/wkClaude Code +5 - 0.869score
Netdata
netdata
Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
ConnectorAFreshness: ARemote★ 81.1KClaude Code +3 - 0.869score
Metabase
metabase
Lets AI clients search, explore, query, and visualize data in a Metabase instance.
ConnectorAFreshness: ARemote★ 49.8KClaude Code +3
Plugins
- 0.899score
Repowise
repowise-dev
Know what your change breaks before you push.
PluginAFreshness: A★ 7.9KVS Code +3 - 0.885score
Mistral Vibe VS Code
mistralai
Mistral Vibe is an AI coding agent for VS Code that works across your whole project.
PluginAFreshness: A★ 5.2KVS Code +3 - 0.868score
Scaler Companion
Ashutosh Shrimal
Autonomous coding agent right in your IDE, capable of creating/editing files, running commands, using the browser, and more with your permission every step of…
PluginAFreshness: A★ 70.8KVS Code +3 - 0.834score
DebugMCP — Agentic Debugging for VS Code, Cursor & More
ozzafar
Your AI agent debugs for you — right inside VS Code, Cursor & other VS Code-based editors.
PluginAFreshness: A★ 573VS Code +3 - 0.811score
1C: Platform Tools
yellow-hammer
Разработка на 1С:Предприятии в VS Code (Cursor, Windsurf, VSCodium): проекты конфигуратора, 1С:EDT и OneScript, метаданные, vanessa-runner, тесты, отладка и…
PluginAFreshness: A★ 233VS Code +3 - 0.797score
Jolli Memory
Jolli
VS Code sidebar for Jolli Memory — AI-powered commit summaries and smart git operations
PluginAFreshness: A★ 148VS Code +3
Agents
- 0.744score
Browser Use
Browser Use
Open-source browser agent in Python, plus a hosted cloud with stealth browsers and an agent API
AgentAFreshness: A★ 119K↓ 1.5M/wk - 0.736score
Zed Agent
Zed Industries
Agent built into the Zed code editor that edits files, navigates code and runs tools, with changes reviewed in a diff
AgentAFreshness: A★ 92.1K - 0.735score
DeerFlow
ByteDance
Open-source super agent harness that runs sub-agents, memory, sandboxes and skills for research, coding and content tasks lasting minutes to hours.
AgentAFreshness: A★ 84.4K - 0.732score
Cline
Cline Bot Inc.
Open-source coding agent for VS Code, JetBrains, the terminal and a desktop app that asks for approval before each action
AgentAFreshness: A★ 70.8K - 0.731score
Open Interpreter
Open Interpreter
Terminal coding agent, forked from OpenAI's Codex, tuned for low-cost open models and compatible with ACP editors
AgentAFreshness: A★ 68.7K - 0.729score
Gemini CLI
Google
Open-source terminal agent that queries and edits codebases and automates tasks with Gemini models
AgentAFreshness: A★ 107.7K↓ 231.3K/wk
Signals
- Stars
- 9,524
- Forks
- 1,881
- Open issues
- 62
- Last commit
- Oct 23, 2026 (7 days ago)
- Last release
- Jul 28, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 2026-07-28
- License
- License unknown
- Website
- modelcontextprotocol.io
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get Model Context Protocol (MCP) running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
Model Context Protocol (MCP). Agent Mart. https://agentmart.dev/reference/model-context-protocol (last updated 2026-10-24)