NerdCabalMCP

🤖 Agentic Protocols & MCP Servers 2026

The Comprehensive Awesome List

 █████╗  ██████╗ ███████╗███╗   ██╗████████╗██╗ ██████╗
██╔══██╗██╔════╝ ██╔════╝████╗  ██║╚══██╔══╝██║██╔════╝
███████║██║  ███╗█████╗  ██╔██╗ ██║   ██║   ██║██║
██╔══██║██║   ██║██╔══╝  ██║╚██╗██║   ██║   ██║██║
██║  ██║╚██████╔╝███████╗██║ ╚████║   ██║   ██║╚██████╗
╚═╝  ╚═╝ ╚═════╝ ╚══════╝╚═╝  ╚═══╝   ╚═╝   ╚═╝ ╚═════╝

A curated collection of agentic protocols, MCP servers, agent frameworks, and integration platforms as of January 2026.

📚 Table of Contents

🔌 Agentic Protocols

Core Protocols

1. Model Context Protocol (MCP)

By: Anthropic Status: Production (v1.0+) Purpose: Standard protocol for connecting AI models to external tools and data sources

Links:

Key Features:

Language Support: TypeScript, Python, Rust, Go

2. Agent-to-Agent (A2A) Protocol

By: Anthropic Status: Production Purpose: Structured communication between AI agents

Specification:

interface AgentCard {
  name: string;
  version: string;
  description: string;
  capabilities: string[];
  input_schema: JSONSchema;
  output_schema: JSONSchema;
  dependencies: string[];
}

Key Features:

Reference Implementation: NerdCabalMCP (this repo!)

3. Anthropic Design Kit (ADK)

By: Anthropic Status: Recommended patterns Purpose: Design patterns for multi-agent workflows

Patterns:

Resources:

4. OpenAI Assistants API

By: OpenAI Status: Production Purpose: Stateful agent execution with built-in tools

Key Features:

Links:

5. LangGraph Protocol

By: LangChain AI Status: Production (v0.2+) Purpose: Graph-based agent orchestration

Key Features:

Links:

6. AutoGen Protocol

By: Microsoft Research Status: Production (v0.4+) Purpose: Multi-agent conversation framework

Key Features:

Links:

7. CrewAI Protocol

By: CrewAI Status: Production Purpose: Role-based agent collaboration

Key Features:

Links:

8. Semantic Kernel Agents

By: Microsoft Status: Production Purpose: Enterprise agent orchestration

Key Features:

Links:

🖥️ MCP Servers

Official Anthropic Servers

Server Purpose Language Status
mcp-server-filesystem File system operations TypeScript ✅ Production
mcp-server-git Git repository management TypeScript ✅ Production
mcp-server-github GitHub API integration TypeScript ✅ Production
mcp-server-postgres PostgreSQL database access TypeScript ✅ Production
mcp-server-sqlite SQLite database operations TypeScript ✅ Production
mcp-server-brave-search Web search via Brave TypeScript ✅ Production
mcp-server-google-maps Google Maps integration TypeScript ✅ Production
mcp-server-slack Slack workspace access TypeScript ✅ Production
mcp-server-puppeteer Browser automation TypeScript ✅ Production

Community MCP Servers

Research & ML

Server Purpose Author Links
NerdCabalMCP 14 specialized research agents @Tuesdaythe13th GitHub
mcp-arxiv ArXiv paper search and retrieval Community GitHub
mcp-mlflow MLflow experiment tracking Community Custom
mcp-wandb Weights & Biases integration Community Custom
mcp-huggingface HuggingFace model hub access Community Custom

Development Tools

Server Purpose Author Links
mcp-docker Docker container management Community GitHub
mcp-kubernetes Kubernetes cluster operations Community Custom
mcp-vercel Vercel deployment Community Custom
mcp-railway Railway.app integration Community Custom

Data & Analytics

Server Purpose Author Links
mcp-bigquery Google BigQuery access Community Custom
mcp-snowflake Snowflake data warehouse Community Custom
mcp-elasticsearch Elasticsearch queries Community Custom
mcp-redis Redis cache operations Community Custom

Communication

Server Purpose Author Links
mcp-discord Discord bot integration Community Custom
mcp-telegram Telegram bot API Community Custom
mcp-twilio SMS/voice via Twilio Community Custom

Creative & Design

Server Purpose Author Links
mcp-figma Figma design access Community Custom
mcp-canva Canva template generation Community Custom
mcp-dall-e DALL-E image generation Community Custom
mcp-stable-diffusion Stable Diffusion integration Community Custom

Building Your Own MCP Server

Quick Start Template:

import { Server } from '@modelcontextprotocol/sdk/server/index.js';
import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
import {
  CallToolRequestSchema,
  ListToolsRequestSchema,
} from '@modelcontextprotocol/sdk/types.js';

const server = new Server(
  {
    name: 'my-mcp-server',
    version: '1.0.0',
  },
  {
    capabilities: {
      tools: {},
    },
  }
);

// List available tools
server.setRequestHandler(ListToolsRequestSchema, async () => ({
  tools: [
    {
      name: 'my-tool',
      description: 'Does something useful',
      inputSchema: {
        type: 'object',
        properties: {
          input: { type: 'string' }
        },
        required: ['input']
      },
    },
  ],
}));

// Handle tool calls
server.setRequestHandler(CallToolRequestSchema, async (request) => {
  if (request.params.name === 'my-tool') {
    const result = doSomething(request.params.arguments.input);
    return {
      content: [{ type: 'text', text: JSON.stringify(result) }]
    };
  }
  throw new Error(`Unknown tool: ${request.params.name}`);
});

// Start server
const transport = new StdioServerTransport();
await server.connect(transport);

Resources:

🏗️ Agent Frameworks

1. LangChain

Focus: Full-stack LLM application framework Status: Production (v0.3+)

Key Components:

Links:

Popular Use Cases:

2. Haystack

Focus: NLP and LLM pipelines Status: Production (v2.0+)

Key Features:

Links:

3. LlamaIndex

Focus: Data framework for LLM applications Status: Production

Key Features:

Links:

4. Flowise

Focus: Visual agent builder (drag-and-drop) Status: Production

Key Features:

Links:

5. Langflow

Focus: Visual LangChain builder Status: Production

Key Features:

Links:

6. AgentGPT

Focus: Autonomous web-based agents Status: Production

Key Features:

Links:

7. SuperAGI

Focus: Developer-first agent framework Status: Active Development

Key Features:

Links:

8. Agent Protocol

Focus: Standardized agent API Status: Specification (v1.0)

Purpose: Common interface for agent communication across frameworks

Specification:

POST /agent/tasks          # Create task
GET  /agent/tasks/{id}     # Get task status
POST /agent/tasks/{id}/steps # Execute step

Links:

Supported By: AutoGPT, SuperAGI, AIOS, BabyAGI

🎭 Multi-Agent Orchestration

1. Swarm (by OpenAI)

Status: Experimental Focus: Lightweight multi-agent coordination

Key Concepts:

Example:

from swarm import Swarm, Agent

client = Swarm()

agent_a = Agent(
    name="Agent A",
    instructions="You are a helpful agent.",
    functions=[transfer_to_agent_b],
)

agent_b = Agent(
    name="Agent B",
    instructions="Only speak in haikus.",
)

response = client.run(
    agent=agent_a,
    messages=[{"role": "user", "content": "Hello!"}],
)

Links:

2. MetaGPT

Status: Production Focus: Software development team simulation

Roles:

Links:

3. CAMEL

Status: Research Focus: Communicative agents for “mind” exploration

Key Features:

Links:

4. ChatDev

Status: Active Development Focus: Waterfall software development simulation

Phases:

Links:

🔗 Integration Platforms

Design & Creative

Figma

Integration Type: REST API, Webhooks, Plugins

Capabilities:

Links:

MCP Server: mcp-figma (community)

Canva

Integration Type: REST API, Webhooks

Capabilities:

Links:

MCP Server: mcp-canva (community)

Lovable (formerly GPT Engineer)

Integration Type: API, SDK

Capabilities:

Links:

Development Platforms

Replit

Integration Type: REST API, Nix packages

Capabilities:

Links:

GitHub

Integration Type: REST API, GraphQL, Apps, Actions

Capabilities:

Links:

MCP Server: mcp-server-github (official)

Cursor

Integration Type: IDE, Extensions

Capabilities:

Links:

Windsurf (by Codeium)

Integration Type: IDE, Extensions

Capabilities:

Links:

ML & Data Platforms

HuggingFace

Integration Type: Python SDK, REST API

Capabilities:

Links:

MCP Integration: Via dataset-builder agent in NerdCabal

Kaggle

Integration Type: Python API

Capabilities:

Links:

Streamlit

Integration Type: Python framework

Capabilities:

Links:

Use Case: UI for NerdCabalMCP (see STREAMLIT_UI_DESIGN.md)

Cloud & Infrastructure

Antigravity (by Railway)

Integration Type: API, CLI

Capabilities:

Links:

Vercel

Integration Type: REST API, CLI

Capabilities:

Links:

Cloudflare Workers

Integration Type: REST API, Wrangler CLI

Capabilities:

Links:

LLM Providers

Anthropic (Claude)

Models: Claude 3.5 Sonnet, Claude 3 Opus, Claude 3.5 Haiku API: REST, Python SDK, TypeScript SDK

Key Features:

Links:

OpenAI

Models: GPT-4o, GPT-4 Turbo, GPT-3.5 Turbo, o1-preview, o1-mini API: REST, Python SDK, Node SDK

Key Features:

Links:

Google (Gemini)

Models: Gemini 1.5 Pro, Gemini 1.5 Flash, Gemini 2.0 Flash API: REST, Python SDK

Key Features:

Links:

Cohere

Models: Command R+, Command R, Embed API: REST, Python SDK

Key Features:

Links:

Mistral AI

Models: Mistral Large, Mistral Medium, Mixtral API: REST, Python SDK

Key Features:

Links:

Together AI

Focus: Open-source model hosting Models: 100+ including Llama, Mistral, Qwen

Links:

Replicate

Focus: Model hosting and inference Models: Open-source models, Stable Diffusion, Whisper

Links:

🛠️ Development Tools

Agent Development

Tool Purpose Links
Claude Code Anthropic’s official CLI for Claude with agent support GitHub
Codex (GitHub Copilot) AI pair programmer Official Site
Aider AI pair programming in terminal GitHub
Continue Open-source Copilot alternative GitHub

Observability & Debugging

Tool Purpose Links
LangSmith LangChain debugging and monitoring Official Site
Weights & Biases ML experiment tracking Official Site
MLflow ML lifecycle management Official Site
Arize ML observability Official Site
Phoenix (by Arize) LLM observability (open-source) GitHub

Vector Databases

Database Purpose Links
Pinecone Managed vector DB Official Site
Weaviate Open-source vector DB Official Site
Qdrant Vector similarity search Official Site
Chroma Embeddings database GitHub
Milvus Distributed vector DB Official Site

Evaluation Frameworks

Framework Purpose Links
HELM Holistic evaluation (Stanford) Official Site
LM Eval Harness Standardized evaluation (EleutherAI) GitHub
MMLU Multitask accuracy benchmark Paper
BIG-bench Diverse task evaluation GitHub
AgentBench Agent task evaluation Official Site

📄 Research Papers

Foundational Papers

  1. “Communicative Agents for Software Development” (2023) Introduces role-playing framework for multi-agent collaboration arXiv:2307.07924

  2. “Reflexion: Language Agents with Verbal Reinforcement Learning” (2023) Self-reflection for improving agent decision-making arXiv:2303.11366

  3. “ReAct: Synergizing Reasoning and Acting in Language Models” (2023) Reasoning + Acting paradigm for agents arXiv:2210.03629

  4. “Toolformer: Language Models Can Teach Themselves to Use Tools” (2023) Self-supervised tool learning arXiv:2302.04761

  5. “AutoGPT: An Experimental Open-Source Attempt to Make GPT-4 Fully Autonomous” (2023) Autonomous goal-oriented agents GitHub

  6. “Generative Agents: Interactive Simulacra of Human Behavior” (2023) Stanford/Google research on believable agent behavior arXiv:2304.03442

  7. “MetaGPT: Meta Programming for Multi-Agent Collaborative Framework” (2023) Software development team simulation arXiv:2308.00352

  8. “AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation” (2023) Microsoft’s multi-agent framework arXiv:2308.08155

  9. “Chain-of-Thought Prompting Elicits Reasoning in Large Language Models” (2022) Foundational work on reasoning chains arXiv:2201.11903

  10. “Large Language Models are Zero-Shot Reasoners” (2022) Let’s think step by step paradigm arXiv:2205.11916

2024-2026 Recent Papers

  1. “The Co-Scientist: A Research Platform for Human-AI Collaboration” (2024) Google DeepMind’s approach to AI-assisted research Google DeepMind Blog

  2. “Agent-as-a-Judge: Evaluating Multi-Agent Systems with LLM Judges” (2024) Evaluation methodologies for agent systems

  3. “Mixture of Agents: Collaborative LLM Ensembles” (2024) Together AI’s approach to agent collaboration

  4. “Constitutional AI for Agent Alignment” (2024) Anthropic’s approach to aligned agents

  5. “Swarm Intelligence in LLM Agents” (2024) Decentralized coordination patterns

👥 Community Resources

Forums & Communities

Newsletters

YouTube Channels

Podcasts

🔮 Emerging Trends (2026)

1. Agent Operating Systems (AOS)

Platforms that provide infrastructure for running multi-agent systems:

Examples: AIOS, AgentOS, Kernel (by SkyDeck)

2. Agentic RAG

Combining retrieval-augmented generation with autonomous agents:

3. Human-Agent Collaboration Interfaces

UIs designed specifically for working alongside agents:

4. Agent Marketplaces

Platforms for discovering, sharing, and monetizing agents:

5. Specialized Agent Hardware

Hardware optimized for running agent workloads:

6. Agent Security & Safety

Emerging standards for safe agent deployment:

7. Cross-Platform Agent Portability

Standards for moving agents between platforms:

Reference: Agent Protocol (see above)

🎓 Learning Resources

Courses

  1. “LangChain for LLM Application Development” (DeepLearning.AI) Hands-on course on building with LangChain

  2. “Building Systems with the ChatGPT API” (DeepLearning.AI) Multi-agent system development

  3. “AI Agents in LangGraph” (LangChain) Building stateful agents

  4. “Multi-Agent Systems with AutoGen” (Microsoft) Microsoft’s agent framework

  5. “Prompt Engineering for Developers” (DeepLearning.AI) Foundational prompting techniques

Books

  1. “Generative AI with LangChain” by Ben Auffarth Comprehensive guide to building with LangChain

  2. “Building LLM Powered Applications” by Valentina Alto Production patterns for LLM apps

  3. “Prompt Engineering Guide” (DAIR.AI) Free online book on prompting

Documentation & Guides

📊 Comparison Matrix

When to Use Each Protocol

Use Case Recommended Protocol Why
Tool calling from Claude MCP Native integration, official support
Multi-agent workflows LangGraph or AutoGen Mature orchestration patterns
Role-based collaboration CrewAI Built-in role management
Research simulation ChatDev or MetaGPT Specialized for software development
Simple agent handoffs Swarm Lightweight, minimal setup
Enterprise integration Semantic Kernel Microsoft ecosystem
Visual agent building Flowise or Langflow No-code approach

Protocol Feature Comparison

Feature MCP A2A LangGraph AutoGen CrewAI
Stateful ❌ ❌ ✅ ✅ ✅
Multi-agent ❌ ✅ ✅ ✅ ✅
Tool calling ✅ ✅ ✅ ✅ ✅
Loops/cycles ❌ ❌ ✅ ✅ ❌
Human-in-loop ❌ ❌ ✅ ✅ ✅
Visual editor ❌ ❌ ❌ ❌ ❌
Production-ready ✅ ✅ ✅ ✅ ✅

🚀 Getting Started Recommendations

For Beginners

  1. Start with MCP to understand tool calling
  2. Build a simple agent with CrewAI
  3. Learn LangChain basics
  4. Experiment with Flowise for visual understanding

For Intermediate Developers

  1. Master LangGraph for complex workflows
  2. Explore AutoGen for multi-agent systems
  3. Build custom MCP servers
  4. Integrate with LangSmith for observability

For Advanced Users

  1. Implement A2A protocol for custom agents
  2. Design ADK patterns for your use case
  3. Contribute to open-source frameworks
  4. Build production systems with monitoring

🤝 Contributing to This List

This awesome list is maintained by the NerdCabal community. To contribute:

  1. Fork the repository
  2. Add your resource with description and links
  3. Ensure it’s categorized correctly
  4. Submit a pull request

Criteria for inclusion:

📜 License

This awesome list is released under CC0 1.0 Universal (public domain).

🙏 Acknowledgments

Thanks to all the researchers, engineers, and communities building the agentic future:

Last Updated: January 2026 Version: 1.0.0 Maintained by: @Tuesdaythe13th

Built with ❤️ by the NerdCabal community
This site is open source. Improve this page.