Neva
Neva is an easily configurable MCP server and client SDK in Rust, supporting tool invocation and resource management. It is currently in the preview stage.
rating : 2.5 points
downloads : 23
What is Neva MCP Server?
Neva is an implementation of the MCP protocol developed in Rust, providing server and client SDKs. It allows developers to easily build and connect to MCP services, enabling functions such as tool invocation, resource access, and prompt analysis.How to use Neva MCP Server?
You can start an MCP server or connect to an existing service with simple Rust code. The server side can register tools, resources, and prompt handlers, while the client side can invoke these functions.Applicable Scenarios
Suitable for scenarios that require building model services, tool integration, or AI application backends, especially projects that need flexible protocol support.Main Features
Client SDKProvides a complete MCP client implementation, supporting functions such as tool invocation and resource access.
Server FrameworkAn easily extensible server framework that supports registering tools, resources, and prompt handlers.
Standard Input/Output SupportSupports communication with child processes through standard input and output.
Asynchronous SupportAsynchronous implementation based on Tokio, capable of handling concurrent requests with high performance.
Advantages and Limitations
Advantages
Simple and easy-to-use API design
High-performance Rust implementation
Flexible configuration options
Complete error handling mechanism
Limitations
Currently in preview stage, the API may be unstable
Requires a Rust development environment
Documentation and examples are still being improved
How to Use
Add Dependencies
Add the neva dependency to Cargo.toml and choose the client-full or server-full feature as needed.
Initialize the Client/Server
Create a Client or App instance and configure the required options.
Connect/Start the Service
The client calls the connect method to connect, and the server calls the run method to start.
Invoke Functions
The client can invoke tools and access resources, while the server needs to register handlers first.
Usage Examples
Create an Echo ServiceImplement a simple echo tool to return the input message.
Resource AccessImplement a resource handler to return resource details by name.
Frequently Asked Questions
Is Neva currently stable?
What Rust version is required?
How to contribute code?
Related Resources
API Documentation
Complete API reference documentation
Example Code
Example code for various usage scenarios
GitHub Repository
Project source code and issue tracking
Featured MCP Services

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
1.7K
5 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
823
4.3 points

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
79
4.3 points

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
130
4.5 points

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#
554
5 points

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
6.6K
4.5 points

Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
5.2K
4.7 points

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
745
4.8 points