Question 1

What is MCP?

Accepted Answer

The Model Context Protocol allows applications to provide context for LLMs in a standardised way, separating the concerns of providing context from the actual LLM interaction.

Question 2

Which agent frameworks are demonstrated?

Accepted Answer

Google Agent Development Kit (ADK), LangGraph Agents, OpenAI Agents, and Pydantic‑AI Agents are demonstrated.

Question 3

What MCP servers are included in the repository?

Accepted Answer

Two Python MCP servers: `example_server.py` (provides an `add(a,b)` tool, `get_current_time()` tool, and a dynamic greeting resource) and `mermaid_validator.py` (Mermaid diagram validation using mermaid‑cli).

Question 4

What credentials does it need?

Accepted Answer

It reads `GEMINI_API_KEY`, `OPENAI_API_KEY`, `LOGFIRE_TOKEN` from the environment. Store these in your client's env block or a secrets manager — never commit them to a repository — and grant the narrowest scope that still covers your use case.

Variable	Description	Required
GEMINI_API_KEY	Credential the server authenticates with.	Yes
OPENAI_API_KEY	Credential the server authenticates with.	Yes
LOGFIRE_TOKEN	Credential the server authenticates with.	Yes

Model Context Protocol (MCP) Agent Frameworks Demo MCP Server

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

What you get

More MCP options

Configuration

Frequently asked questions

Alternatives to the Model Context Protocol (MCP) Agent Frameworks Demo MCP Server

Filesystem

Context7

Explainability

Cloudquery

Vivac

Git Mcp