Merge pull request modelcontextprotocol#1013 from modelcontextprotocol/ihrpr/roadmap

Update roadmap

Author: ihrpr

docs/development/roadmap.mdx

@@ -3,7 +3,7 @@ title: Roadmap
 description: Our plans for evolving Model Context Protocol
 ---
 
-<Info>Last updated: **2025-03-27**</Info>
+<Info>Last updated: **2025-07-22**</Info>
 
 The Model Context Protocol is rapidly evolving. This page outlines our current thinking on key priorities and direction for approximately **the next six months**, though these may change significantly as the project develops. To see what's changed recently, check out the **[specification changelog](/specification/2025-06-18/changelog/)**.
 
@@ -17,11 +17,28 @@ We value community participation! Each section links to relevant discussions whe
 
 For a technical view of our standardization process, visit the [Standards Track](https://github.com/orgs/modelcontextprotocol/projects/2/views/2) on GitHub, which tracks how proposals progress toward inclusion in the official [MCP specification](https://spec.modelcontextprotocol.io).
 
+## Agents
+
+As MCP increasingly becomes part of agentic workflows, we're focusing on key improvements:
+
+- **Asynchronous Operations**: supporting long-running operations that may take extended periods, with resilient handling of disconnections and reconnections
+
+## Authentication and Security
+
+We're evolving our authorization and security resources to improve user safety and provide a better developer experience:
+
+- **Guides and Best Practices**: documenting specifics about deploying MCP securely in the form of guides and best practices to help developers avoid common pitfalls.
+- **Alternatives to Dynamic Client Registration (DCR)**: exploring alternatives to DCR, attempting to address operational challenges while preserving a smooth user experience.
+- **Fine-grained Authorization**: developing mechanisms and guidelines for primitive authorization for sensitive actions
+- **Enterprise Managed Authorization**: adding the capability for enterprises to simplify MCP server authorization with the help of Single Sign-On (SSO)
+- **Secure Authorization Elicitation**: enable developers to integrate secure authorization flows for downstream APIs outside the main MCP server authorization
+
 ## Validation
 
 To foster a robust developer ecosystem, we plan to invest in:
 
 - **Reference Client Implementations**: demonstrating protocol features with high-quality AI applications
+- **Reference Server Implementation**: showcasing authentication patterns and remote deployment best practices
 - **Compliance Test Suites**: automated verification that clients, servers, and SDKs properly implement the specification
 
 These tools will help developers confidently implement MCP while ensuring consistent behavior across the ecosystem.
@@ -32,27 +49,13 @@ For MCP to reach its full potential, we need streamlined ways to distribute and
 
 We plan to develop an [**MCP Registry**](https://github.com/orgs/modelcontextprotocol/discussions/159) that will enable centralized server discovery and metadata. This registry will primarily function as an API layer that third-party marketplaces and discovery services can build upon.
 
-## Agents
-
-As MCP increasingly becomes part of agentic workflows, we're exploring [improvements](https://github.com/modelcontextprotocol/specification/discussions/111) such as:
-
-- **[Agent Graphs](https://github.com/modelcontextprotocol/specification/discussions/94)**: enabling complex agent topologies through namespacing and graph-aware communication patterns
-- **Interactive Workflows**: improving human-in-the-loop experiences with granular permissioning, standardized interaction patterns, and [ways to directly communicate](https://github.com/modelcontextprotocol/specification/issues/97) with the end user
-
 ## Multimodality
 
 Supporting the full spectrum of AI capabilities in MCP, including:
 
 - **Additional Modalities**: video and other media types
 - **[Streaming](https://github.com/modelcontextprotocol/specification/issues/117)**: multipart, chunked messages, and bidirectional communication for interactive experiences
 
-## Governance
-
-We're implementing governance structures that prioritize:
-
-- **Community-Led Development**: fostering a collaborative ecosystem where community members and AI developers can all participate in MCP's evolution, ensuring it serves diverse applications and use cases
-- **Transparent Standardization**: establishing clear processes for contributing to the specification, while exploring formal standardization via industry bodies
-
 ## Get Involved
 
 We welcome your contributions to MCP's future! Join our [GitHub Discussions](https://github.com/orgs/modelcontextprotocol/discussions) to share ideas, provide feedback, or participate in the development process.