Pamela Fox pamelafox

Agents using MCP servers

Framework	MCP integration	Tool filtering?	Example
Langchain	MultiServerMCPClient accepts a dictionary of MCP servers	Filter with get_tools() after connecting to servers	Example
Agent-framework	MCPStreamableHTTPTool for each MCP server	Filter with allowed_tools on that class, or tools on agent.run()	Example
Pydantic AI	MCPServerStreamableHTTP for each MCP server	Apply `.filtered()` method to the server and use result as a toolset for agent	Example

YouTube Talk to Article – Lean MVP Technical Spec

Derived from the original PRD but intentionally simplified for fastest viable implementation. Focus: “folder in, article out” with minimal config, vision-first extraction, and straightforward alignment (no embeddings initially).

1. MVP Goal & Non-Goals

Goal: Given a folder containing a deck.pptx (and optionally a transcript + config.yaml), produce article.md plus slide images using a simple CLI: talk2article <folder>.

Included in MVP:

description	Python coding conventions and guidelines
applyTo	*/.py

Python Coding Conventions

Python Instructions

Write clear and concise comments for each function.

	import os

	from anthropic import AnthropicFoundry
	from dotenv import load_dotenv

	load_dotenv()

	endpoint = "https://pf-claude-foundry-proje-resource.openai.azure.com/anthropic"
	deployment_name = "claude-sonnet-4-5"

	"""Compare documents across two Azure AI Search indexes"""

	import argparse
	import asyncio
	import logging
	import os
	from collections.abc import Iterable, Mapping
	from dataclasses import dataclass, field
	from typing import Any, cast

	from langchain.agents.middleware import AgentMiddleware, AgentState, ModelRequest

	class ToolCallLimitMiddleware(AgentMiddleware):
	def __init__(self, limit) -> None:
	super().__init__()
	self.limit = limit

	def modify_model_request(
	self, request: ModelRequest, state: AgentState
	) -> ModelRequest:

	import json
	import os

	import azure.identity
	import openai
	from dotenv import load_dotenv
	from rich import print

	# Setup the OpenAI client to use either Azure, OpenAI.com, or Ollama API
	load_dotenv(override=True)

	#!/usr/bin/env python3
	"""
	Find characters whose repetitions tokenize to one token per character with tiktoken.

	A character c is considered "stable single-token" if:
	len(encode(c)) == 1 AND for all k in [1, max_reps], len(encode(c * k)) == k.

	Usage (from repo root with virtual env active):
	python find_single_token_char.py
	python find_single_token_char.py --model text-embedding-3-large --max-reps 32

	import os

	import openai
	from azure.identity import DefaultAzureCredential, get_bearer_token_provider

	client = openai.AzureOpenAI(
	api_version=os.environ["AZURE_OPENAI_VERSION"],
	azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
	azure_ad_token_provider=get_bearer_token_provider(DefaultAzureCredential(),
	"https://cognitiveservices.azure.com/.default"),