You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs/development/roadmap.mdx
+18-15Lines changed: 18 additions & 15 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -3,7 +3,7 @@ title: Roadmap
3
3
description: Our plans for evolving Model Context Protocol
4
4
---
5
5
6
-
<Info>Last updated: **2025-03-27**</Info>
6
+
<Info>Last updated: **2025-07-22**</Info>
7
7
8
8
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/)**.
9
9
@@ -17,11 +17,28 @@ We value community participation! Each section links to relevant discussions whe
17
17
18
18
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).
19
19
20
+
## Agents
21
+
22
+
As MCP increasingly becomes part of agentic workflows, we're focusing on key improvements:
23
+
24
+
-**Asynchronous Operations**: supporting long-running operations that may take extended periods, with resilient handling of disconnections and reconnections
25
+
26
+
## Authentication and Security
27
+
28
+
We're evolving our authorization and security resources to improve user safety and provide a better developer experience:
29
+
30
+
-**Guides and Best Practices**: documenting specifics about deploying MCP securely in the form of guides and best practices to help developers avoid common pitfalls.
31
+
-**Alternatives to Dynamic Client Registration (DCR)**: exploring alternatives to DCR, attempting to address operational challenges while preserving a smooth user experience.
32
+
-**Fine-grained Authorization**: developing mechanisms and guidelines for primitive authorization for sensitive actions
33
+
-**Enterprise Managed Authorization**: adding the capability for enterprises to simplify MCP server authorization with the help of Single Sign-On (SSO)
34
+
-**Secure Authorization Elicitation**: enable developers to integrate secure authorization flows for downstream APIs outside the main MCP server authorization
35
+
20
36
## Validation
21
37
22
38
To foster a robust developer ecosystem, we plan to invest in:
23
39
24
40
-**Reference Client Implementations**: demonstrating protocol features with high-quality AI applications
41
+
-**Reference Server Implementation**: showcasing authentication patterns and remote deployment best practices
25
42
-**Compliance Test Suites**: automated verification that clients, servers, and SDKs properly implement the specification
26
43
27
44
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
32
49
33
50
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.
34
51
35
-
## Agents
36
-
37
-
As MCP increasingly becomes part of agentic workflows, we're exploring [improvements](https://github.com/modelcontextprotocol/specification/discussions/111) such as:
38
-
39
-
-**[Agent Graphs](https://github.com/modelcontextprotocol/specification/discussions/94)**: enabling complex agent topologies through namespacing and graph-aware communication patterns
40
-
-**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
41
-
42
52
## Multimodality
43
53
44
54
Supporting the full spectrum of AI capabilities in MCP, including:
45
55
46
56
-**Additional Modalities**: video and other media types
47
57
-**[Streaming](https://github.com/modelcontextprotocol/specification/issues/117)**: multipart, chunked messages, and bidirectional communication for interactive experiences
48
58
49
-
## Governance
50
-
51
-
We're implementing governance structures that prioritize:
52
-
53
-
-**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
54
-
-**Transparent Standardization**: establishing clear processes for contributing to the specification, while exploring formal standardization via industry bodies
55
-
56
59
## Get Involved
57
60
58
61
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.
0 commit comments