MCP Plexus
M

MCP Plexus

MCP Plexus is a Python framework based on FastMCP 2.7 for building secure and scalable multi-tenant MCP servers. It supports OAuth 2.1 integration and API key management, providing an isolated environment and tool access control for modern AI applications.
2.5 points
4.4K

What is MCP Plexus?

MCP Plexus is a Python framework based on FastMCP 2.7 for building secure and scalable Model Context Protocol (MCP) applications. It allows developers to deploy multi-tenant MCP servers and seamlessly integrate AI models with external services.

How to use MCP Plexus?

By defining tenants, registering users, creating tools, and resources, MCP Plexus can provide isolated AI backend systems for different customers or organizations. Users can access external services through OAuth 2.1 or API keys.

Use Cases

Suitable for scenarios that require customized AI backends for different customers, such as enterprise-level AI assistants and multi-tenant SaaS platforms.

Main Features

Multi-tenant Support
Supports multiple independent tenants, each with its own data and tool access permissions.
External Service Integration
Securely connects to external services such as GitHub and Google through OAuth 2.1.
API Key Management
Securely stores and injects API keys without hard - coding sensitive information in the code.
Standardized MCP Server
Uses FastMCP's decorators to define tools, resources, and prompts, simplifying the development process.
Persistent Storage
By default, uses SQLite to store user authentication tokens, OAuth tokens, and API keys.
Advantages
Supports a multi-tenant architecture, enabling data isolation and independent configuration.
Simplifies external service integration, providing OAuth 2.1 and API key management.
Improves security, protecting sensitive credentials (such as OAuth tokens and API keys).
Is easy to expand, supporting custom authentication providers and services.
Uses the FastMCP library, ensuring high performance and a good developer experience.
Limitations
Currently relies on Redis for session management, which may increase deployment complexity.
Some features (such as the internal OAuth provider) are still under development.
For non-technical users, some configuration steps may be complex.
Requires some Python development experience to fully utilize its features.

How to Use

Install Dependencies
Clone the project and install the dependencies, including the Python environment and Redis.
Configure Environment Variables
Create a `.env` file and set the necessary environment variables, such as `HOST_APP_REGISTRATION_SECRET` and `PLEXUS_ENCRYPTION_KEY`.
Start the Server
Run the development server to start providing MCP services.
Register a User
Register a user through the `/{entity_id}/plexus-auth/register-user` interface to obtain the `plexus_user_auth_token`.
Call Tools
Use the `GET /{entity_id}/mcp/` endpoint to initialize an MCP session and call registered tools.

Usage Examples

Enterprise-level AI Assistant
Provide customized AI assistants for different enterprises, each with an independent toolset and data.
Weather Query Tool
Provide weather forecast services using the OpenWeatherMap API.
Multi-tenant SaaS Platform
Provide a unified AI backend for different customers, with each customer's data and tools completely isolated.

Frequently Asked Questions

How to securely store API keys?
How to handle expired OAuth tokens?
Does it support multiple languages?
How to expand the functionality of MCP Plexus?

Related Resources

Official Documentation
Complete documentation and source code for MCP Plexus.
Quick Start Guide
A guide to help you quickly get started with MCP Plexus.
Video Tutorial
Demonstrate how to use MCP Plexus to create a multi-tenant MCP server.

Installation

Copy the following command to your Client for configuration
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

A
Acemcp
Acemcp is an MCP server for codebase indexing and semantic search, supporting automatic incremental indexing, multi-encoding file processing, .gitignore integration, and a Web management interface, helping developers quickly search for and understand code context.
Python
8.5K
5 points
B
Blueprint MCP
Blueprint MCP is a chart generation tool based on the Arcade ecosystem. It uses technologies such as Nano Banana Pro to automatically generate visual charts such as architecture diagrams and flowcharts by analyzing codebases and system architectures, helping developers understand complex systems.
Python
8.1K
4 points
M
MCP Agent Mail
MCP Agent Mail is a mail - based coordination layer designed for AI programming agents, providing identity management, message sending and receiving, file reservation, and search functions, supporting asynchronous collaboration and conflict avoidance among multiple agents.
Python
8.4K
5 points
K
Klavis
Klavis AI is an open-source project that provides a simple and easy-to-use MCP (Model Context Protocol) service on Slack, Discord, and Web platforms. It includes various functions such as report generation, YouTube tools, and document conversion, supporting non-technical users and developers to use AI workflows.
TypeScript
12.9K
5 points
M
MCP
The Microsoft official MCP server provides search and access functions for the latest Microsoft technical documentation for AI assistants
11.9K
5 points
A
Aderyn
Aderyn is an open - source Solidity smart contract static analysis tool written in Rust, which helps developers and security researchers discover vulnerabilities in Solidity code. It supports Foundry and Hardhat projects, can generate reports in multiple formats, and provides a VSCode extension.
Rust
10.6K
5 points
D
Devtools Debugger MCP
The Node.js Debugger MCP server provides complete debugging capabilities based on the Chrome DevTools protocol, including breakpoint setting, stepping execution, variable inspection, and expression evaluation.
TypeScript
10.0K
4 points
S
Scrapling
Scrapling is an adaptive web scraping library that can automatically learn website changes and re - locate elements. It supports multiple scraping methods and AI integration, providing high - performance parsing and a developer - friendly experience.
Python
11.8K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
17.5K
4.5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
18.4K
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
27.4K
5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
54.5K
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
23.0K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
51.0K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
17.1K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
36.5K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2025AIBase