Repository navigation
Integrate MCP for OAuth2 and enhance client registration features - #161
Merged
Merged
Conversation
…ation - Updated server version to 4.11.35 in package.json and package-lock.json. - Added @modelcontextprotocol/node and @modelcontextprotocol/server dependencies. - Implemented MCP authorization flow with endpoints for authorization, token handling, and discovery. - Created new mcp module with handlers for authorization, token generation, and user context verification. - Registered MCP tools for managing load balancers and gateways. - Added HTML responses for authorization requests and error handling. - Implemented session management and token verification for secure access.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This pull request introduces a full-featured Model Context Protocol (MCP) server to the codebase, enabling EdgeBalancer to act as an MCP-compatible backend. It adds OAuth2-style authorization, token issuance, client registration, and a
/mcpendpoint that supports a variety of AI clients. The landing page is updated to document these capabilities and provide connection instructions for multiple clients.MCP Server Integration and OAuth2 Authorization:
Added a new MCP server implementation using the
@modelcontextprotocol/serverand@modelcontextprotocol/nodelibraries, exposing a/mcpendpoint for AI clients to manage load balancers and gateways. [1] [2] [3] [4] [5] [6] [7] [8] [9] [10]Implemented OAuth2-style authorization flows:
/.well-known/oauth-protected-resource,/.well-known/oauth-authorization-server) for client compatibility./authorizeGET/POST) with login, consent UI, and redirect logic./mcp/auth/token) for exchanging authorization codes for access tokens./register) for dynamic client onboarding.Landing Page Documentation:
client/src/app/page.tsx) that documents the MCP server, its endpoint, supported tools, and provides copy-paste configuration snippets for connecting from popular AI clients (Claude Code, Cursor, Codex, etc.).These changes make EdgeBalancer accessible from a wide range of AI and code tools via the standardized MCP protocol, with robust authentication and clear user-facing documentation.