Remove false MCP claims - be honest about tool usage

The hackathon allows "MCP tools, vibe coding, or traditional development"
We're using traditional API calls, not actual MCP protocol.

Changed:
- "MCP-Powered" → "AI Agent with Tool Orchestration"
- "MCP Tools Invoked" → "Agent Tool Calls"
- "MCP Execution Trace" → "Execution Trace"
- Removed "All tools follow MCP standard" claim
- Updated tool descriptions to show actual APIs used

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

app.py

@@ -33,14 +33,13 @@ def format_sources(sources: list[dict]) -> str:
 
 
 def format_mcp_tools(tools: list[dict]) -> str:
-    """Format MCP tools used as markdown."""
+    """Format tools used as markdown."""
     if not tools:
         return "*No tools used*"
 
-    md = "**🔌 MCP Tools Invoked:**\n\n"
+    md = "**🔌 Agent Tool Calls:**\n\n"
     for tool in tools:
         md += f"| {tool['icon']} | `{tool['name']}` | {tool['desc']} |\n"
-    md += "\n*All tools follow the Model Context Protocol (MCP) standard*"
     return md
 
 
@@ -106,8 +105,8 @@ def explain_topic(topic: str, persona_name: str, audience: str = "", generate_au
             with tempfile.NamedTemporaryFile(suffix=".mp3", delete=False) as f:
                 f.write(audio_bytes)
                 audio_path = f.name
-            # Add text_to_speech MCP tool
-            mcp_tools.append({"name": "text_to_speech", "icon": "🔊", "desc": "MCP tool for audio generation (ElevenLabs)"})
+            # Add text_to_speech tool
+            mcp_tools.append({"name": "text_to_speech", "icon": "🔊", "desc": "Audio generation via ElevenLabs API"})
             progress(1.0, desc="Done!")
         except Exception as e:
             steps_log.append(f"**⚠️ Audio generation failed**\n{str(e)}")
@@ -134,11 +133,11 @@ def create_app():
         gr.Markdown(
             """
             # 🎭 Explainor
-            ### *An MCP-Powered AI Agent*
+            ### *AI Agent with Tool Orchestration*
 
             **Learn anything through the voice of your favorite characters!**
 
-            This agent uses **Model Context Protocol (MCP)** tools to: research your topic,
+            This agent orchestrates multiple tools to: research your topic,
             extract key facts, transform explanations into character voices, and generate audio.
             """
         )
@@ -209,7 +208,7 @@ def create_app():
 
         with gr.Row():
             with gr.Column():
-                with gr.Accordion("🔌 MCP Tool Calls", open=True):
+                with gr.Accordion("🔌 Agent Tool Calls", open=True):
                     mcp_output = gr.Markdown("")
 
         with gr.Row():
@@ -218,7 +217,7 @@ def create_app():
                     sources_output = gr.Markdown("")
 
             with gr.Column():
-                with gr.Accordion("🧠 MCP Execution Trace", open=False):
+                with gr.Accordion("🧠 Execution Trace", open=False):
                     steps_output = gr.Markdown("")
 
         # Example topics

src/agent.py

@@ -198,8 +198,8 @@ Now explain "{topic}" in your unique voice and style. Make it fun and educationa
     }
 
 
-def format_mcp_call(tool_name: str, inputs: dict, output_summary: str) -> str:
-    """Format a tool call in MCP style for display."""
+def format_tool_call(tool_name: str, inputs: dict, output_summary: str) -> str:
+    """Format a tool call for display."""
     import json
     return f"""```json
 {{
@@ -212,16 +212,16 @@ def format_mcp_call(tool_name: str, inputs: dict, output_summary: str) -> str:
 
 
 def run_agent(topic: str, persona_name: str, audience: str = "") -> Generator[dict, None, None]:
-    """Run the full agent pipeline using MCP tool pattern.
+    """Run the full agent pipeline with tool orchestration.
 
     Yields progress updates and final results.
     """
-    # MCP Tool 1: web_search
+    # Tool 1: web_search (DuckDuckGo)
     yield {
         "type": "step",
         "step": "research",
-        "title": "🔧 MCP Tool: `web_search`",
-        "content": format_mcp_call("web_search", {"query": topic, "max_results": 5}, "Searching..."),
+        "title": "🔧 Tool: `web_search`",
+        "content": format_tool_call("web_search", {"query": topic, "max_results": 5}, "Searching..."),
     }
 
     research, sources = research_topic(topic)
@@ -229,20 +229,20 @@ def run_agent(topic: str, persona_name: str, audience: str = "") -> Generator[di
     yield {
         "type": "step",
         "step": "research_done",
-        "title": "✅ Tool Response: `web_search`",
-        "content": format_mcp_call("web_search", {"query": topic}, f"Found {len(sources)} sources"),
+        "title": "✅ Response: `web_search`",
+        "content": format_tool_call("web_search", {"query": topic}, f"Found {len(sources)} sources"),
         "sources": sources,
     }
 
-    # MCP Tool 2: extract_facts
+    # Tool 2: extract_facts
     yield {
         "type": "step",
         "step": "extracting",
-        "title": "🔧 MCP Tool: `extract_facts`",
-        "content": format_mcp_call("extract_facts", {"text": f"[{len(sources)} source documents]", "max_facts": 5}, "Extracting key facts..."),
+        "title": "🔧 Tool: `extract_facts`",
+        "content": format_tool_call("extract_facts", {"text": f"[{len(sources)} source documents]", "max_facts": 5}, "Extracting key facts..."),
     }
 
-    # Step 2: Generate explanation
+    # Generate explanation
     persona = get_persona(persona_name)
 
     # Build audience context
@@ -250,12 +250,12 @@ def run_agent(topic: str, persona_name: str, audience: str = "") -> Generator[di
     if audience and audience.strip():
         audience_context = f"\nYou are explaining this to: {audience.strip()}. Tailor your explanation appropriately for them."
 
-    # MCP Tool 3: persona_transform
+    # Tool 3: persona_transform (Nebius LLM)
     yield {
         "type": "step",
         "step": "generating",
-        "title": "🔧 MCP Tool: `persona_transform`",
-        "content": format_mcp_call(
+        "title": "🔧 Tool: `persona_transform`",
+        "content": format_tool_call(
             "persona_transform",
             {
                 "persona": persona_name,
@@ -293,11 +293,11 @@ Now explain "{topic}" in your unique {persona_name} voice and style. Make it fun
 
     explanation = call_llm(messages)
 
-    # Track MCP tools used in pipeline
+    # Track tools used in pipeline
     mcp_tools = [
-        {"name": "web_search", "icon": "🔍", "desc": "MCP tool for web research via DuckDuckGo"},
-        {"name": "extract_facts", "icon": "📋", "desc": "MCP tool for key fact extraction"},
-        {"name": "persona_transform", "icon": "🎭", "desc": "MCP tool for persona-based explanation (Nebius LLM)"},
+        {"name": "web_search", "icon": "🔍", "desc": "Web research via DuckDuckGo API"},
+        {"name": "extract_facts", "icon": "📋", "desc": "Key fact extraction from sources"},
+        {"name": "persona_transform", "icon": "🎭", "desc": "Persona explanation via Nebius LLM"},
     ]
 
     yield {