Model Context Protocol (MCP) Agent Frameworks Demo

Created By
andrewginnsa year ago
Repo for demonstrating simple Model Context Protocol (MCP) server with several Agent Frameworks
Overview

What is the Model Context Protocol (MCP) Agent Frameworks Demo?

The Model Context Protocol (MCP) Agent Frameworks Demo is a repository that showcases the usage of a simple MCP server integrated with various agent frameworks, including Google ADK, LangGraph, OpenAI Agents, and Pydantic-AI Agents.

How to use the MCP Agent Frameworks?

To use the MCP Agent Frameworks, clone the repository, set up your environment variables in a .env file, and run any of the sample scripts provided in the basic_mcp_use directory. For example, you can run uv run basic_mcp_use/pydantic_mcp.py which requires a GEMINI_API_KEY.

Key features of the MCP Agent Frameworks?

  • Demonstrates integration with multiple LLM agent frameworks.
  • Provides a simple MCP server for context management.
  • Includes tracing capabilities through Logfire for observability.

Use cases of the MCP Agent Frameworks?

  1. Building AI applications that require context management for LLMs.
  2. Monitoring and tracing LLM agent interactions using Logfire.
  3. Facilitating the development of interoperable AI solutions across different LLM providers.

FAQ from the MCP Agent Frameworks?

  • What is the Model Context Protocol (MCP)?

MCP is a standardized interface that allows applications to provide context for LLMs, simplifying the development process and enhancing interoperability.

  • How do I set up the environment for MCP?

Clone the repository, install required packages, and set up your environment variables in a .env file.

  • Can I use different LLM providers with MCP?

Yes! MCP allows you to switch between different LLM providers without overhauling your tool and data integrations.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
andrewginns
Star
1
Language
Python
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