Model Context Protocol (sse) servers
LocalAbout Model Context Protocol (sse) servers
This repository collects reference implementations and community server listings for MCP, with an emphasis on SSE. It is for developers and organizations exploring MCP servers and remote connections, and also documents differences between protocol specifications.
Key features
- 01Collects MCP reference implementations
- 02Lists community-built servers
- 03Describes MCP specification differences
- 04Includes TypeScript and Python SDK implementations
Use cases
- 01Find MCP server examples
- 02Compare MCP specification versions
- 03Explore community MCP servers
MCP support
The repository gathers MCP server implementations and community server references, with a focus on remote SSE connections. The listed servers illustrate controlled access to tools and data for LLMs.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project README
Model Context Protocol (sse) servers
This repository is a collection of reference implementations for the Model Context Protocol (MCP) with SSE, as well as references to community built servers and additional resources.
For many enterpises, it's no way to have each employees to connect to AI Tools without control and governance, it's critical to have these MCP tools with remote connect capabilities (sse) and allow enterprise to create a reliable and responsible environemnt to run AI realted usecases.
All the MCP servers listed in this repository showcase the versatility and extensibility of MCP, demonstrating how it can be used to give Large Language Models (LLMs) secure, controlled access to tools and data sources.
Each MCP server is implemented with either the Typescript MCP SDK or Python MCP SDK.
Note: Lists in this README are maintained in alphabetical order to minimize merge conflicts when adding new items.
MCP Spec
There are two mcp spec released at 2025 Mar/30, let's quick compare the differnece of these two specs:
To organize the differences clearly, the following table encapsulates the comparison:
| Feature/Aspect | Description | 2024-11-05 (Final) | 2025-03-26 (Latest) |
|---|---|---|---|
| Authorization Framework | A system to manage and control access to MCP servers, ensuring that only authorized users or applications can interact with them. | No specific framework mentioned; general guidelines for user consent. | Added a comprehensive framework based on Oatuh 2.1 for standardized authorization processes. |
| Transport Layer | The method used for data transmission between clients and servers. | HTTP with Server-Sent Events (HTTP+SSE) | Replaced with Streamable HTTP, which likely offers more flexibility or improved performance. |
| JSON-RPC Batching | The ability to send multiple JSON-RPC requests in a single message, which can improve efficiency by reducing network overhead. | Not supported | Supported, allowing for batch processing of requests. |
| Tool Annotations | Descriptive labels or metadata for tools that indicate their behavior, such as whether they are read-only or can perform destructive operations. | Not mentioned | Added to provide better understanding and control over tool usage. |
| ProgressNotification | Notifications that inform about the progress of ongoing operations. | Did not have a message field | Added a message field to provide descriptive status updates, enhancing user experience and debugging. |
| Data Support | The types of data that the protocol can handle and transmit. | Text and Image | Added support for Audio data, expanding the range of content types that can be managed. |
| Completions Capability | A feature that allows for providing suggestions or completions for arguments in requests, which can be useful for user interfaces or to assist in constructing requests. | Not explicitly mentioned | Added to support argument autocompletion, likely improving usability and efficiency. |
Implications and Observations
The updates from 2024-11-05 to 2025-03-26 indicate a focus on enhancing security, flexibility, and usability.
The addition of an OAuth 2.1-based authorization framework and Streamable HTTP transport suggests a move toward more robust and scalable implementations.
The inclusion of audio data support and tool annotations could significantly expand MCP’s applicability, particularly in multimedia and complex AI workflows.
The unexpected detail of audio support, not previously highlighted, may indicate a shift toward more versatile AI interactions, potentially impacting industries like voice assistants or multimedia content analysis.
🌟 Reference Servers
These servers aim to demonstrate MCP features and the TypeScript and Python SDKs.
- Weather - Provides weather forecasts and alert for U.S states
🤝 Third-Party Servers
🌎 Community Servers
A growing set of community-developed and maintained servers demonstrates various applications of MCP across different domains.
Note: Community servers are untested and should be used at your own risk. They are not affiliated with or endorsed by Anthropic.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.