Awesome MCP - Model Context Protocol

A carefully curated collection of high-quality tools, libraries, research papers, projects, and tutorials centered around Model Context Protocol (MCP) — a novel paradigm designed to enable modular, adaptive coordination between large language models (LLMs) and external tools or data contexts. This repository serves as a comprehensive, well-organized knowledge hub for researchers and developers exploring the next frontier of interactive, context-aware AI systems.

The MCP framework facilitates fine-grained orchestration of model behavior through structured, tool-integrated communication protocols. It supports advanced workflows like adaptive reasoning, multi-tool routing, contextual memory access, and iterative refinement. By treating models not as static endpoints but as participants in a dynamic co-mining or co-creation loop, MCP pushes the boundaries of what intelligent systems can achieve.

To keep the community up-to-date with the latest developments, this repository is continuously enriched with newly published MCP-related papers, real-world use cases, and open-source implementations. From LangGraph-based architectures to custom tool routers and model-control interfaces, the collection aims to highlight both foundational ideas and emerging best practices.

[!NOTE] 📢 Announcement: Our paper is now available on arXiv!
Title: Model Context Protocols in Adaptive Transport Systems: A Survey
If you find this paper interesting, please consider citing our work. Thank you for your support!

@article{chhetri2025model,
  title={Model Context Protocols in Adaptive Transport Systems: A Survey},
  author={Chhetri, Gaurab and Somvanshi, Shriyank and Islam, Md Monzurul and Brotee, Shamyo and Mimi, Mahmuda Sultana and Koirala, Dipti and Pandey, Biplov and Das, Subasish},
  journal={arXiv preprint arXiv:2508.19239},
  year={2025}
}

Whether you are building AI agents, researching model-tool alignment, or experimenting with novel retrieval-augmented generation pipelines, this resource offers a centralized, evolving platform to explore the powerful and expanding universe of MCP-enabled systems.

Last Updated

October 17, 2026 at 03:55:30 AM UTC

Theorem

Papers (169)

• Agentic Semantic Control for Autonomous Wireless Space Networks: Extending Space-O-RAN with MCP-Driven Distributed Intelligence
• Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol Ecosystem
• ETDI: Mitigating Tool Squatting and Rug Pull Attacks in Model Context Protocol (MCP) by using OAuth-Enhanced Tool Definitions and Policy-Based Access Control
• Gaming Tool Preferences in Agentic LLMs
• Enterprise-Grade Security for the Model Context Protocol (MCP): Frameworks and Mitigation Strategies
• Securing GenAI Multi-Agent Systems Against Tool Squatting: A Zero Trust Registry-Based Approach
• MCP Bridge: A Lightweight, LLM-Agnostic RESTful Proxy for Model Context Protocol Servers
• MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits
• Beyond Formal Semantics for Capabilities and Skills: Model Context Protocol in Manufacturing
• Mind the Metrics: Patterns for Telemetry-Aware In-IDE AI Application Development using the Model Context Protocol (MCP)
• We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems
• Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Servers
• Gradientsys: A Multi-Agent LLM Scheduler with ReAct Orchestration
• MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in LLM Agent Multi-Turn Conversations
• Magentic-UI: Towards Human-in-the-loop Agentic Systems
• MCP2OSC: Parametric Control by Natural Language
• Help or Hurdle? Rethinking Model Context Protocol-Augmented Large Language Models
• Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol (MCP) Ecosystem
• AniME: Adaptive Multi-Agent Planning for Long Animation Generation
• MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers
• Towards Agentic OS: An LLM Agent Framework for Linux Schedulers
• EHR-MCP: Real-world Evaluation of Clinical Information Retrieval by Large Language Models via Model Context Protocol
• XARP Tools: An Extended Reality Platform for Humans and AI Agents
• Tool Preferences in Agentic LLMs are Unreliable
• Dynamic ReAct: Scalable Tool Selection for Large-Scale MCP Environments
• Model Context Protocol for Vision Systems: Audit, Security, and Protocol Extensions
• IoT-MCP: Bridging LLMs and IoT Systems Through Model Context Protocol
• Agentic-AI Healthcare: Multilingual, Privacy-First Framework with MCP Agents
• LLM\times\timesMapReduce-V3: Enabling Interactive In-Depth Survey Generation through a MCP-Driven Hierarchically Modular Agent System
• NetMCP: Network-Aware Model Context Protocol Platform for LLM Capability Extension
• Securing AI Agent Execution
• ORCHID: Orchestrated Retrieval-Augmented Classification with Human-in-the-Loop Intelligent Decision-Making for High-Risk Property
• TEM Agent: enhancing transmission electron microscopy (TEM) with modern AI tools
• Hiding in the AI Traffic: Abusing MCP for LLM-Powered Agentic Red Teaming
• Securing the Model Context Protocol (MCP): Risks, Controls, and Governance
• MCP vs RAG vs NLWeb vs HTML: A Comparison of the Effectiveness and Efficiency of Different Agent Interfaces to the Web (Technical Report)
• PaperDebugger: A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing
• Leveraging Large Language Models to Bridge On-chain and Off-chain Transparency in Stablecoins
• LeechHijack: Covert Computational Resource Exploitation in Intelligent Agent Systems
• Benchmark for Planning and Control with Large Language Model Agents: Blocksworld with Model Context Protocol
• AgentBay: A Hybrid Interaction Sandbox for Seamless Human-AI Intervention in Agentic Systems
• RoboNeuron: A Modular Framework Linking Foundation Models and ROS for Embodied AI
• MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments
• Agentic AI for Autonomous Defense in Software Supply Chain Security: Beyond Provenance to Vulnerability Mitigation
• Enterprise Identity Integration for AI-Assisted Developer Services: Architecture, Implementation, and Case Study
• Data Product MCP: Chat with your Enterprise Data
• Towards Verifiably Safe Tool Use for LLM Agents
• AJAR: Adaptive Jailbreak Architecture for Red-teaming
• Agentic Artificial Intelligence (AI): Architectures, Taxonomies, and Evaluation of Large Language Model Agents
• A Universal Large Language Model -- Drone Command and Control Interface
• Faramesh: A Protocol-Agnostic Execution Control Plane for Autonomous Agent Systems
• Breaking the Protocol: Security Analysis of the Model Context Protocol Specification and Prompt Injection Vulnerabilities in Tool-Integrated LLM Agents
• OptAgent: an Agentic AI framework for Intelligent Building Operations
• Secure Tool Manifest and Digital Signing Solution for Verifiable MCP and LLM Pipelines
• SoK: Trust-Authorization Mismatch in LLM Agent Interactions
• Human Tool: An MCP-Style Framework for Human-Agent Collaboration
• AgentRob: From Virtual Forum Agents to Hijacked Physical Robots
• Information Fidelity in Tool-Using LLM Agents: A Martingale Analysis of the Model Context Protocol
• An Agentic AI Control Plane for 6G Network Slice Orchestration, Monitoring, and Trading
• EAA: Automating materials characterization with vision language model agents
• MCPShield: A Security Cognition Layer for Adaptive Trust Calibration in Model Context Protocol Agents
• From Docs to Descriptions: Smell-Aware Evaluation of MCP Server Descriptions
• AutoEDA: Enabling EDA Flow Automation through Microservice-Based LLM Agents
• AWCP: A Workspace Delegation Protocol for Deep-Engagement Collaboration across Remote Agents
• Agentic AI for Scalable and Robust Optical Systems Control
• The Auton Agentic AI Framework
• REGAL: A Registry-Driven Architecture for Deterministic Grounding of Agentic AI in Enterprise Telemetry
• VDCook:DIY video data cook your MLLMs
• AgenticCyOps: Securing Multi-Agentic AI Integration in Enterprise Cyber Operations
• Turn: A Language for Agentic Computation
• ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMs
• Invisible Threats from Model Context Protocol: Generating Stealthy Injection Payload via Tree-based Adaptive Search
• SOMA: Strategic Orchestration and Memory-Augmented System for Vision-Language-Action Model Robustness via In-Context Adaptation
• IndustriConnect: MCP Adapters and Mock-First Evaluation for AI-Assisted Industrial Operations
• RoboNeuron: A Middle-Layer Infrastructure for Agent-Driven Orchestration in Embodied AI
• Leveraging Large Language Models to Bridge Cross-Domain Transparency in Stablecoins
• Flowr -- Scaling Up Retail Supply Chain Operations Through Agentic AI in Large Scale Supermarket Chains
• A Formal Security Framework for MCP-Based AI Agents: Threat Taxonomy, Verification Models, and Defense Mechanisms
• Agent-Driven Corpus Linguistics: A Framework for Autonomous Linguistic Discovery
• Trust-as-a-Service: Task-Specific Orchestration for Effective Task Completion via Model Context Protocol-Aided Agentic AI
• MCP-DPT: A Defense-Placement Taxonomy and Coverage Analysis for Model Context Protocol Security
• MPAC: A Multi-Principal Agent Coordination Protocol for Interoperable Multi-Agent Collaboration
• Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
• enclawed: A Configurable, Sector-Neutral Hardening Framework for Single-User AI Assistant Gateways
• YAIFS: Yet (not) Another Intelligent Fog Simulator: A Framework for Agent-Driven Computing Continuum Modeling & Simulation
• AgentBound: Securing Execution Boundaries of AI Agents
• An Agentic Framework for Intent Co-Creation in 6G NaaS: Architecture and Open-Source Model Evaluation
• From CRUD to Autonomous Agents: Formal Validation and Zero-Trust Security for Semantic Gateways in AI-Native Enterprise Systems
• A First Look at the Security Issues in the Model Context Protocol Ecosystem
• Autonomous Traffic Signal Optimization Using Digital Twin and Agentic AI for Real-Time Decision-Making
• Tool Use as Action: Towards Agentic Control in Mobile Core Networks
• Feedback-Normalized Developer Memory for Reinforcement-Learning Coding Agents: A Safety-Gated MCP Architecture
• Say the Mission, Execute the Swarm: Agent-Enhanced LLM Reasoning in the Web-of-Drones
• When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI
• SecureMCP: A Policy-Enforced LLM Data Access Framework for AIoT Systems via Model Context Protocol
• Unsafe by Flow: Uncovering Bidirectional Data-Flow Risks in MCP Ecosystem
• Octopus Protocol: One-Shot Hardware Discovery and Control for AI Agents via Infrastructure-as-Prompts
• LychSim: A Controllable and Interactive Simulation Framework for Vision Research
• NIMO Controller: a self-driving laboratory orchestrator based on the Model Context Protocol
• VectraYX-Nano: A 42M-Parameter Spanish Cybersecurity Language Model with Curriculum Learning and Native Tool Use
• Formal Skill: Programmable Runtime Skills for Efficient and Accurate LLM Agents
• Semantic Attacks on Tool-Augmented LLMs: Securing the Model Context Protocol Against Descriptor-Level Manipulation
• Device Context Protocol: A Compact, Safety-First Architecture for LLM-Driven Control of Constrained Devices
• Queen-Bee Agents: A BeeSpec-Centered Architecture for Governed Enterprise MCP Orchestration
• VATS: Exploiting Implicit Authority in Error-Path Injection via Systematic Mutation
• Game-Theoretic Multi-Agent Control for Robust Contextual Reasoning in LLMs
• Pepti-Agent: An AI Agent for Peptide Design and Optimization
• ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM Agents
• From Privacy to Workflow Integrity: Communication-Graph Metadata in Autonomous Agent Interoperability
• From Specification to Execution: AI Assisted Scientific Workflow Management
• Trust-as-a-Service: Intelligent Collaboration Orchestration via Model Context Protocol-Aided Agentic AI
• MCP-SandboxScan: WASM-based Secure Execution and Runtime Analysis for MCP Tools
• Verifiable Manifest Signing and Transparency Enforcement for Secure MCP-Based LLM Pipelines
• A hardware-safety-gated system for LLM-written native ARTIQ control code on a trapped-ion platform
• From Tool Connection to Execution Control: Benchmarking Security Invariants in MCP-Style Agent Runtimes
• ContextNest: Verifiable Context Governance for Autonomous AI Agent
• Unicode TAG-Block Concealment of Tool-Metadata Payloads in the Model Context Protocol: An Approval-View Fidelity Gap Across Three Independent Server Implementations
• The Balkanization of Execution-Security Research for AI Coding Agents: Isolation, Access Control, and Time-of-Check-to-Time-of-Use Vulnerabilities
• MCP Pitfall Lab: Exposing Developer Pitfalls in MCP Tool Server Security under Multi-Vector Attacks
• Contract-Grounded Behavior Tree Synthesis via Coding Agents
• JW-ASTClaw: A Generalizable Multi-Agent Framework for Autonomous Solar Telescope and Its Implementation within Chinese Meridian Project
• RegNetAgents: A Multi-Agent Framework for Cross-Network Regulatory Driver Identification in Cancer Genomics
• Scalable LLM Agent Tool Access in the Cloud
• Trustworthy AI LLM Scalability Risk Index (LSRI): A Cybersecurity Framework Assessing Agentic-AI Security & Software Model Supply Chain Safety Boosting AI-Generated Malware Defense & Explainability Mitigating Emerging Risks of Generative AI
• A corrective agentic hybrid RAG and an operations-grounded evaluation for a scientific facility
• The Hitchhiker's Guide to Agentic AI: From Foundations to Systems
• A Comparative Study of MCP and A2A for Inter-Agent Coordination in LLM-Based Systems
• An Empirical Study of Model Context Protocol Applications
• Registry Descriptions Go Stale Unevenly: An 89-Day Measurement of Model Context Protocol Drift, and Why Drift-Ranked Re-Auditing Under-Covers It
• Safety Invariants for Agents Orchestrating Irreversible State Transitions: A Four-Dimensional Formalism Evaluated on Public Ledgers
• Exposed by Design: A Dynamic Security Assessment of Internet-Facing MCP Servers at Scale
• Spectroscopic Binary Detection as Agent-Callable Tools: Detecting 40,000+ Main-Sequence Binary Candidates from SDSS DR19 APOGEE Spectra
• RoboHarness: A Memory-Augmented Policy Harness for Vision-Language-Action Model Robustness via In-Context Adaptation
• Task-Conditioned Least-Privilege Learning for Executable Terminal and MCP Agents
• TrustShiftProbe: Characterizing, Benchmarking, and Defending Staged Trust Attacks on MCP Servers
• APPA: Recoverable Information-Flow Control for Real-World LLM Agents
• ToolMinimize: Auditing and Rewriting LLM Agent Tool Calls to Minimize Privacy Exposure
• Claude Code Complete User Handbook
• Agentic AI for operating scientific instruments for nanoscale characterization
• CP^2^2N^2^2: A Control Plane for Heterogeneous Physical Neural Networks
• ACLE-MCP: Attested Capability Leases for Execution-Time Trust in Remote LLM Tool Use
• Public-Sharing Labels and Verbatim Field Egress in an MCP-to-A2A Agent Configuration: A Controlled Multi-Model Study
• Skill-as-API: Confidential Multi-Agent Coordination for Agentic Software Engineering
• Orchestra: Corroboration-Based Regulatory Candidate Discovery via Composed Bioinformatics MCP Agents
• AnchorVLN: Geometry-Anchored Vision-Language Grounding Reasoning for Open-Vocabulary Navigation
• An Open-Source Hardware and Software Toolkit to Enable Agentic RHEED-Guided Thin-Film Synthesis
• Authorization Architectures for Tool-Using AI Agents
• The Stochastic Deputy: Structural Tenant Isolation for Tool-Using LLM Agents
• An LLM-Agnostic, MAVLink-Based Drone Command and Control Interface and Agentic Harness Using the Model Context Protocol
• DriveMCP: An Agentic AI framework for Advanced Driver Assistance System
• EchoPath: Execution-Level Replayable Memory for GUI Agents
• When Agents Look Like Beacons: NIDS Evasion by Model Context Protocol Traffic
• Measuring and Exploiting Implicit Trust in LLM Tool-Calling Pipelines
• MCP-GRANITE Benchmark: GRANularity Interface TEsting for MCP-Based LLM Agents
• Zero-Trust Authorization and Discovery for Enterprise MCP
• A2M: Trace-Optimized Agent Hijacking in the MCP Ecosystem
• Multi-Agent AI Architecture for Regulated Insurers: A generic AI framework under Solvency II and the AI Act in Austria and Germany
• Progressive Skill Discovery as Access Control for Tool-Using LLM Agents: Structural Governance through Role-Scoped Capability Delivery
• Bridging LLM Agents and Data Spaces: An Architectural Mediation Approach using the Model Context Protocol
• Cartograph: Federated Tool Discovery with Operator-Attested Retrieval for AI Agents
• HTN Planning as a Coordination Layer for Multi-Server MCP Tool Orchestration
• Skill-Based AI Agents for Power-System Studies
• PROJECTMEM: A Local-First, Event-Sourced Memory and Judgment Layer for AI Coding Agents
• Localizing Post-Wire Semantic Changes in MCP Agent Frameworks
• COPEX: Benchmarking LLM Robustness to Adversarial Context Across Model Context Protocol Layers
• CyTReX: Explainable AI-Based Cybersecurity Threat Reasoning Framework for DER Networks
• The Cost of a Hop: Benchmarking NLIP and A2A
• KedgeFlow: A Programmable Control Plane for Enterprise AI Agents
• Which Metadata Matters for LLM Tool Selection in MCP? Evidence from Controlled Factor-Level Interventions

Library

• WritBase - MCP-native task management for AI agent fleets. Multi-agent permissions, full provenance, inter-agent task delegation, and A2A protocol alignment.
• Roundtable - Multi-model AI brainstorming MCP server — consult a council of AI models that debate your question, then a moderator synthesizes the best answer. 13 tools including consult_council, review_code, debug_issue, design_architecture, plan_implementation, and assess_tradeoffs. Remote endpoint: https://mcp.roundtable.now/mcp.
• operant-mcp - Security testing MCP server with 51 tools for penetration testing, network forensics, memory analysis, and vulnerability assessment.

Tutorial

Written Tutorials

• Architecture of MCP - Anthropic
• MCP Specification - Anthropic

Video Tutorials

Contributing

We welcome contributions to this repository! If you have a resource that you believe should be included, please submit a pull request or open an issue. Contributions can include:

• New libraries or tools related to MCP.
• Tutorials or guides that help users understand and implement MCP.
• Research papers that advance the field of MCP.
• Any other resources that you find valuable for the community

How to Contribute

1. Fork the repository.
2. Create a new branch for your changes.
3. Make your changes and commit them with a clear message.
4. Push your changes to your forked repository.
5. Submit a pull request to the main repository.

Before contributing, take a look at the existing resources to avoid duplicates.

License

This repository is licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). You are free to share and adapt the material, provided you give appropriate credit, link to the license, and indicate if changes were made.

Star History