Azure Model Context Protocol (MCP) Hub

Created By
Azure-Samplesa year ago
Links to samples, tools, and resources for building and integrating Model Context Protocol (MCP) servers on Azure using multiple languages
Overview

What is Azure Model Context Protocol (MCP) Hub?

The Azure Model Context Protocol (MCP) Hub is a resource for developers to build and integrate Model Context Protocol (MCP) servers on Azure using various programming languages. It provides tools, samples, and resources to facilitate the development of AI agents that can call real APIs quickly.

How to use Azure MCP?

To use Azure MCP, developers can host their own MCP server using Azure Functions in languages like C#, Python, or TypeScript. They can also utilize official SDKs to build agents that connect to any MCP server.

Key features of Azure MCP?

  • Host your own MCP server using Azure Functions in multiple languages.
  • Access official SDKs for building clients, servers, or tools in C#, Python, TypeScript, and Java.
  • Integrate with various AI frameworks and tools for enhanced functionality.
  • Use plug-and-play MCP servers that expose real APIs for easy integration.

Use cases of Azure MCP?

  1. Building AI agents that interact with Azure services.
  2. Creating custom tools that leverage real-time data from various APIs.
  3. Developing applications that require seamless integration with cloud services.

FAQ from Azure MCP?

  • What languages can I use to build MCP servers?

You can use C#, Python, TypeScript, and Java to build MCP servers.

  • Is there support for using existing APIs with MCP?

Yes, MCP allows you to connect to existing APIs and services easily.

  • Can I contribute to the MCP project?

Yes! You can contribute by creating new servers or tools and submitting a pull request.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
Azure-Samples
Star
2
Language
-
License
MIT 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)

11 hours ago