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.

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.

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.

BugBounty MCP Server is a comprehensive security testing tool that interacts with LLM through natural language, providing over 92 penetration testing tools, covering functions such as reconnaissance, scanning, vulnerability assessment, web applications, network security, OSINT, vulnerability exploitation, and report generation.

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.

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 Eunomia MCP Server is an open - source data governance tool for data policy management in LLM applications, supporting integration with the MCP server.

The MySQL MCP Server is an MCP server implementation integrated with a MySQL database, providing secure database access capabilities for LLMs, supporting read and write operations, and security controls.

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.

SMCP Proxy is a reverse proxy designed for Model Context Protocol (MCP) services, providing a security layer with OIDC authentication, supporting enterprise - level authentication and authorization, and simplifying standardized interactions with large language models (LLMs).

A service toolset based on the Model Context Protocol, providing functions such as encoding conversion, network diagnosis, system monitoring, security encryption, and QR code generation, and supporting LLM agents to call system tools.

An MCP server that allows LLMs to query PostgreSQL, SQLite, and MySQL databases, supports multiple database connections, and ensures security with the default read-only mode.

GUARDRAIL is a security framework specifically designed for the large language model (LLM) application ecosystem, providing comprehensive protection especially for the Model Context Protocol (MCP). It uses a multi - layer architecture, including an information gateway layer, a context verification layer, a request control layer, an execution isolation layer, and an audit monitoring layer, aiming to prevent data leakage, unauthorized access, and resource abuse. This framework emphasizes progressive adoption, allowing developers to gradually enhance security while maintaining high performance and ease of use.

MCP Bridge is a lightweight, LLM-independent RESTful proxy for connecting to multiple Model Context Protocol (MCP) servers and exposing their functions through a unified REST API. It solves the problem that platforms such as edge devices, mobile devices, and web browsers cannot efficiently run MCP servers, and provides optional risk-based execution levels, including security controls such as standard execution, confirmation workflows, and Docker isolation.

EMBA-MCP is a server that exposes the results of the EMBA firmware security analysis tool to LLMs (such as Claude, ChatGPT) through the MCP protocol, supporting structured queries, association analysis, and attack path explanations.

MCP Guardian is a tool for managing LLM assistant access to MCP servers, providing real-time control, message logging, approval, and automated security check functions.

An open - source production - grade MCP server for integrating Wazuh security data with LLMs (such as Claude Desktop App).

A production - grade open - source MCP server for integrating Wazuh security data with LLMs (such as the Claude desktop application). This service authenticates through the Wazuh RESTful API, retrieves alerts from the Elasticsearch index, converts events into an MCP - compatible JSON format, and exposes an HTTP endpoint for the Claude desktop to obtain real - time security context.

An MCP server integrated with MongoDB, designed specifically for recording and analyzing LLM security challenges, supporting AI security testing in the Grey Swan Arena competition.

The urlDNA MCP Server is a service that provides native tool usage for security-oriented LLM agents (such as OpenAI GPT-4.1 and Claude 3 Desktop), interacting directly with the urlDNA threat intelligence platform through the API. It supports various tools, including URL scanning, searching, and quick checking, and can be accessed via the SSE protocol.

sec-mcp is a Python security detection toolkit that provides security check functions for domains, URLs, IPs, etc. It supports integration with Python applications, use in the terminal CLI, or running as an MCP server to provide real-time threat insights for LLMs.

A lightweight MCP server that supports the Garak LLM vulnerability scanning tool, providing functions such as listing model types, models, and attack probes, and can run attack tests to generate reports.

MySSL MCP Server is a website security detection tool developed by TrustAsia, which supports integration with LLM models for certificate security checking.

The MCP command server is a secure system command execution service that is invoked through LLM applications (such as Claude) and provides security features such as whitelist control, user confirmation, and audit logs.

MySSL MCP Server is a website security detection tool developed by TrustAsia, which supports integration with LLM models for certificate security analysis.

The XFetch MCP Server is an enhanced web content retrieval service designed for LLMs. It can bypass security protections such as Cloudflare, support JavaScript rendering and precise content extraction, and provide Markdown conversion functionality.

Contrast MCP Server is a bridge that connects Contrast security data with AI agents/LLMs, helping developers and security professionals quickly fix vulnerabilities. It supports multiple deployment methods, including local running and Docker containers, and can be integrated with tools such as VS Code and Copilot.

A GitHub Model Context Protocol (MCP) server implemented in Go, providing a standard interface for LLMs to interact with GitHub repositories, issues, pull requests, etc., supporting rich GitHub API access and security control.

A Cisco Intersight API integration server based on the MCP protocol, providing infrastructure management and monitoring tools for LLM applications, supporting two configuration methods: security mode and full toolset.