This is a curated list of Web3 Model Context Protocol (MCP) servers, covering multiple categories such as chain interaction, trading, DeFi, market data, tools, and social. MCP is an open protocol that standardizes how applications provide context to LLMs, similar to the USB - C port for AI applications. DeMCP is the first decentralized MCP network, focusing on providing self - developed and open - source MCP services for agents, supporting cryptocurrency payments, and redefining the security and reliability of MCP by combining TEE and blockchain registries.

The MCP MongoDB Server is a model context protocol service that allows LLMs to interact with MongoDB databases, providing functions such as collection schema checking, query execution, and intelligent ID handling, and supporting read - only mode and security configuration.

Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.

Nexus is an AI tool aggregation gateway that supports connecting multiple MCP servers and LLM providers, providing tool search, execution, and model routing functions through a unified endpoint, and supporting security authentication and rate limiting.

The AI Infrastructure Agent is an intelligent system that allows users to manage AWS cloud resources through natural language commands. It uses AI models to convert user requirements into executable AWS operations and provides web dashboards, state management, and security protection functions.

BloodHound - MCP is a project that integrates the Model Context Protocol (MCP) server with BloodHound, analyzing Active Directory security data through natural language.

BloodHound - MCP is a tool that integrates the Model Context Protocol (MCP) server with BloodHound. It analyzes Active Directory attack paths through natural language and provides more than 75 dedicated tools for AD security assessment.

Awesome MCP Servers is a comprehensive collection of Model Context Protocol (MCP) servers, covering 7,158 MCP servers divided into 33 categories, including AI integration, art and media, browser automation, cloud services, databases, developer tools, file systems, finance, gaming, hardware, healthcare, infrastructure, knowledge management, location maps, marketing, monitoring, multimedia processing, operating systems, project management, scientific research, security, social media, travel and transportation, utilities, and version control, etc.

The Semgrep MCP Server is a server based on the Model Context Protocol (MCP) for scanning code for security vulnerabilities through Semgrep, supporting multiple integration methods and tools.

Awesome MCP Security is a collection of resources related to the security of the Model Context Protocol (MCP), including security considerations, papers, videos, articles, tools, and servers, aiming to help users understand and address MCP - related security challenges.

This project implements functions similar to Claude Code through the MCP protocol, providing tools for code understanding, modification, and command execution. It supports multiple models and Jupyter notebook operations, and has security control and development expansion capabilities.

MobSF MCP is a Node.js-based implementation of the Model Context Protocol that provides a standardized interface for the Mobile Security Framework (MobSF) and supports integration with automated workflows and third-party tools.

The MCP Terminal Server is a secure command-line interface service that provides terminal interaction capabilities for AI models while ensuring system security.

An Ubuntu MCP server based on a security - first model, providing controlled system operation access for AI assistants, including multi - layer security protection, audit logs, and resource limits.

This project is a toolset for managing and configuring multiple Model Context Protocol (MCP) servers, mainly serving AI assistants such as Claude Desktop. It provides functions such as file system access, SQLite database queries, web automation, and GitHub integration, and includes installation scripts, configuration templates, and security practice guides.

The Kafka MCP Server is an Apache Kafka Model Context Protocol (MCP) server implemented in Go. Through a standardized interface, it enables LLM models to perform Kafka operations. It provides functions such as producing/consuming messages, managing topics and consumer groups, and monitoring cluster health. It supports multiple security authentication methods and can be integrated with AI applications such as Cursor and Claude.

The Zebbern Kali MCP server is a comprehensive penetration testing platform based on the Model Context Protocol (MCP), providing 139 functions for AI assistants (such as GitHub Copilot) to directly execute security tools on the Kali Linux system through a standardized API, covering network reconnaissance, web application testing, password cracking, vulnerability exploitation, and Active Directory attacks.

The Vulners MCP Server is a tool that provides access to the Vulners vulnerability database through the Model Context Protocol (MCP), supporting direct query of vulnerability information, CVE search, security bulletin analysis, and software package audit in AI assistants such as Claude Desktop.

Sandbox MCP is a model context protocol server that allows LLMs to run code in secure Docker containers, solving the security problem of the inability to test code generated by AI.

GhidraMCP is a Ghidra plugin that enables AI - assisted binary analysis through the Model Context Protocol (MCP), connecting reverse engineering with AI assistants and providing functions such as natural language interaction, in - depth code analysis, and security vulnerability detection.

The Windows Command Line MCP Server is a secure intermediary service that allows AI models to interact with the Windows system under strict security control, including functions such as executing commands, creating projects, and obtaining system information.

This project is an MCP server for the Metasploit framework, providing a bridge between large - language models (such as Claude) and the Metasploit penetration testing platform, and supporting the control of complex security testing workflows through a natural language interface.

MCP Fortress is a comprehensive security tool designed for Model Context Protocol (MCP) servers, offering automated vulnerability scanning, runtime protection, risk scoring, and threat detection functions, and supporting integration with AI assistants such as Claude Code through the MCP server mode for security analysis.

The ChuckNorris MCP Server is an enhanced prompt tool designed for large language models. It uses dynamic mode adaptation technology to bypass security restrictions and is mainly used for security research and evaluation purposes.

The GoHighLevel MCP server is a fundamental project aiming to connect the GoHighLevel community with AI automation through the Model Context Protocol (MCP). It provides access to all sub - account level GoHighLevel API endpoints, supports 269 tools, covering multiple functional categories such as contact management, messaging, sales pipelines, and calendar appointments. The project emphasizes community collaboration, an open architecture, and educational resources, while also reminding users to pay attention to key issues such as AI security, rate limits, and data security.

The Socket MCP server is a Model Context Protocol service for dependency security scanning, providing security scores and vulnerability detection functions for software package ecosystems such as npm and PyPI, supporting AI assistant integration and multiple deployment methods.

falcon-mcp is a Model Context Protocol server that connects AI agents to the CrowdStrike Falcon platform, providing programmatic access to core security capabilities such as security detections, events, and behaviors, and supporting intelligent security analysis and automated workflows.

PhonePi MCP is an open - source project that can transform your phone into a toolbox for AI assistants. It enables remote control of phone functions through the Model Context Protocol, including managing contacts, messages, settings, etc. It emphasizes local deployment and network security.

The Tenzir MCP Server is a service based on the Model Context Protocol, used to connect AI assistants with security data pipelines and map data to the Open Cybersecurity Schema Framework (OCSF).

The Kernel MCP Server is an open - source server based on the Model Context Protocol (MCP), providing AI assistants with secure access to Kernel platform tools and browser automation capabilities. It supports cloud application deployment, headless browser control, document search, etc., and uses OAuth 2.0 authentication to ensure security.

HydraMCP is a lightweight and scalable network security toolkit that connects AI assistants with security tools through the Model Context Protocol (MCP), supporting AI - assisted security research, scanning, and analysis.

Shield MCP is a security middleware designed for Model Context Protocol (MCP) servers, providing functions such as tool access control, result sanitization, structured logging, and rate limiting. It can enhance security and monitoring capabilities without modifying the official SDK.

The IR Toolshed MCP Server is a comprehensive model context protocol server that provides incident response and network analysis tools for security professionals, supporting various network analysis functions such as ASN query, DNS query, WHOIS record retrieval, and IP geolocation.

MCPwner is a security research automation server based on the Model Context Protocol, integrating multiple security testing tools (SAST, SCA, secret scanning, etc.) to provide a unified interface for LLM - driven security analysis workflows.

The Dynatrace Managed MCP server is an open-source project that allows AI assistants to interact with self-hosted Dynatrace Managed deployments through the Model Context Protocol (MCP), directly integrating observability data into AI-assisted workflows. It supports local and remote modes, can be configured for multiple environments, and provides the ability to query data such as problems, security, entities, SLOs, events, logs, and metrics.

The Recall MCP server is a service that implements the Model Context Protocol and is used to interact with the Recall blockchain storage service. It provides functions such as account management, bucket operations, and object storage, and pays special attention to the security protection of private keys.

Fastly MCP is a tool that integrates Fastly API features into an AI assistant through the Model Context Protocol (MCP), allowing users to manage CDN services, caching, security configurations, etc. via AI while protecting the security of API keys.

ZAP-MCP is a bridging protocol between OWASP ZAP and AI models, which realizes AI-driven automated security testing and analysis functions through a standardized interface.

The Zabbix MCP Server is a Python - based Model Context Protocol server that provides programmable access and management capabilities for Zabbix monitoring data. It supports querying resources such as hosts, templates, triggers, and problems, and has read - write operations, security features, and multiple transmission methods.

The Filesystem MCP Server is a Node.js-based filesystem tool server that follows the Model Context Protocol (MCP), providing AI agents with secure and efficient file access capabilities. It ensures operation security by limiting the project root directory, supports batch operations to reduce communication overhead, and offers rich file management functions such as reading, writing, editing, searching, and permission management.