github/servers
1
1
Fork 0
mirror of https://github.com/modelcontextprotocol/servers.git synced 2026-02-19 11:54:58 -05:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #3256 from modelcontextprotocol/localden/security-note

Browse Source 
Update security requirements for servers
This commit is contained in:
Den Delimarsky
2026-01-27 15:03:04 -08:00
committed by GitHub
parent b68d67d155 80397a9d3b
commit e6b0b0f5d3
2 changed files with 10 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@@ -5,6 +5,9 @@ This repository is a collection of *reference implementations* for the [Model Co
> [!IMPORTANT]
> If you are looking for a list of MCP servers, you can browse published servers on [the MCP Registry](https://registry.modelcontextprotocol.io/). The repository served by this README is dedicated to housing just the small number of reference servers maintained by the MCP steering group.
> [!WARNING]
> The servers in this repository are intended as **reference implementations** to demonstrate MCP features and SDK usage. They are meant to serve as educational examples for developers building their own MCP servers, not as production-ready solutions. Developers should evaluate their own security requirements and implement appropriate safeguards based on their specific threat model and use case.
The servers 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.
Typically, each MCP server is implemented with an MCP SDK:

8
SECURITY.md
View File

@@ -3,7 +3,13 @@ Thank you for helping us keep our MCP servers secure.
The **reference servers** in this repo are maintained by [Anthropic](https://www.anthropic.com/) as part of the Model Context Protocol project.
The security of our systems and user data is Anthropic’s top priority. We appreciate the work of security researchers acting in good faith in identifying and reporting potential vulnerabilities.
The security of our systems and user data is Anthropic's top priority. We appreciate the work of security researchers acting in good faith in identifying and reporting potential vulnerabilities.
## Important Notice
The servers in this repository are **reference implementations** intended to demonstrate MCP features and SDK usage. They serve as educational examples for developers building their own MCP servers, not as production-ready solutions.
**Bug bounties are not awarded for security vulnerabilities found in these reference servers.** Our bug bounty program applies exclusively to the [MCP SDKs](https://github.com/modelcontextprotocol) maintained by Anthropic. If you discover a vulnerability in an MCP SDK that is maintained by Anthropic, please report it through our vulnerability disclosure program below.
## Vulnerability Disclosure Program