Simple MCP Server with upstream auth via local rest endpoint

Created By
BarDwellera year ago
A sandbox for MCP server prototyping
Overview

what is Ozzynet MCP Server?

Ozzynet MCP Server is a prototype server that provides tools with access control based on user authentication via an external URL, specifically using GitHub OAuth.

how to use Ozzynet MCP Server?

To use the Ozzynet MCP Server, you need to set up a GitHub OAuth application, configure the application.properties file with your client ID and secret, and run the server using JBang. You can then interact with the server through a compatible MCP client like Claude.

key features of Ozzynet MCP Server?

  • Upstream authentication via GitHub OAuth
  • Session-based access control
  • Prototype environment for MCP server development

use cases of Ozzynet MCP Server?

  1. Prototyping and testing MCP server functionalities.
  2. Integrating with GitHub for issue tracking and management.
  3. Developing applications that require user authentication and access control.

FAQ from Ozzynet MCP Server?

  • How do I set up the OAuth2 app with GitHub?

You can create an OAuth2 app by navigating to GitHub settings, selecting 'OAuth Apps', and following the prompts to create a new app.

  • What are the requirements to run the Ozzynet MCP Server?

You need JBang, an OAuth2 app with GitHub, and a compatible MCP client like Claude.

  • Can I use this server for production?

This server is intended for prototyping and development purposes, not for production use.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
BarDweller
Star
0
Language
Java
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago