docs: address CodeRabbit feedback for Phase 12 PR

- Add `text` fence language to architecture diagrams (MD040)
- Update roadmap directory structure (remove websearch, add clinicaltrials/biorxiv)
- Mark Phase 12 as COMPLETE in roadmap
- Rename test_mcp_server.py to test_mcp_tools_live.py for clarity
- Update hackathon requirements with MCP implementation status
- Fix async pattern in Modal integration doc

docs/implementation/12_phase_mcp_server.md

@@ -23,7 +23,7 @@
 
 ### What MCP Enables
 
-```
+```text
 Current State:
   Our Tools → Called directly by Python code → Only our app can use them
 
@@ -105,12 +105,12 @@ async def search_pubmed(query: str, max_results: int = 10) -> str:
 ### 3.3 MCP Server URL
 
 Once launched:
-```
+```text
 http://localhost:7860/gradio_api/mcp/
 ```
 
 Or on HuggingFace Spaces:
-```
+```text
 https://[space-id].hf.space/gradio_api/mcp/
 ```
 
@@ -806,7 +806,7 @@ Phase 12 is **COMPLETE** when:
 
 ## 12. Architecture After Phase 12
 
-```
+```text
 ┌────────────────────────────────────────────────────────────────┐
 │                      Claude Desktop / Cursor                   │
 │                           (MCP Client)                         │

docs/implementation/roadmap.md

@@ -41,7 +41,9 @@ src/
 ├── tools/                      # Search tools
 │   ├── __init__.py
 │   ├── pubmed.py               # PubMed E-utilities tool
-│   ├── websearch.py            # DuckDuckGo search tool
+│   ├── clinicaltrials.py       # ClinicalTrials.gov API
+│   ├── biorxiv.py              # bioRxiv/medRxiv preprints
+│   ├── code_execution.py       # Modal sandbox execution
 │   └── search_handler.py       # Orchestrates multiple tools
 ├── prompts/                    # Prompt templates
 │   ├── __init__.py
@@ -61,7 +63,8 @@ tests/
 ├── unit/
 │   ├── tools/
 │   │   ├── test_pubmed.py
-│   │   ├── test_websearch.py
+│   │   ├── test_clinicaltrials.py
+│   │   ├── test_biorxiv.py
 │   │   └── test_search_handler.py
 │   ├── agent_factory/
 │   │   └── test_judges.py
@@ -202,7 +205,7 @@ Structured Research Report
 
 ### Hackathon Integration (Phases 12-14)
 
-12. **[Phase 12 Spec: MCP Server](12_phase_mcp_server.md)** 📝 P0 - REQUIRED
+12. **[Phase 12 Spec: MCP Server](12_phase_mcp_server.md)** ✅ COMPLETE
 13. **[Phase 13 Spec: Modal Pipeline](13_phase_modal_integration.md)** 📝 P1 - $2,500
 14. **[Phase 14 Spec: Demo & Submission](14_phase_demo_submission.md)** 📝 P0 - REQUIRED
 
@@ -223,11 +226,11 @@ Structured Research Report
 | Phase 9: Source Cleanup | ✅ COMPLETE | Remove DuckDuckGo |
 | Phase 10: ClinicalTrials | ✅ COMPLETE | ClinicalTrials.gov API |
 | Phase 11: bioRxiv | ✅ COMPLETE | Preprint search |
-| Phase 12: MCP Server | 📝 SPEC READY | MCP protocol integration |
+| Phase 12: MCP Server | ✅ COMPLETE | MCP protocol integration |
 | Phase 13: Modal Pipeline | 📝 SPEC READY | Sandboxed code execution |
 | Phase 14: Demo & Submit | 📝 SPEC READY | Hackathon submission |
 
-*Phases 1-11 COMPLETE. Phases 12-14 for hackathon compliance.*
+*Phases 1-12 COMPLETE. Phases 13-14 for hackathon prizes.*
 
 ---
 

docs/pending/01_hackathon_requirements.md

@@ -1,5 +1,7 @@
 # MCP's 1st Birthday Hackathon - Requirements Analysis
 
+> **✅ MCP Server implemented in Phase 12** - Track 2 compliant
+
 ## Deadline: November 30, 2025 11:59 PM UTC
 
 ---
@@ -21,7 +23,7 @@ tags:
 | Requirement | DeepCritical Status | Action Needed |
 |-------------|---------------------|---------------|
 | Autonomous Agent behavior | ✅ Have it | Search-Judge-Synthesize loop |
-| Must use MCP servers as tools | ❌ **MISSING** | Add MCP server wrapper |
+| Must use MCP servers as tools | ✅ **DONE** | `src/mcp_tools.py` |
 | Must be a Gradio app | ✅ Have it | `src/app.py` |
 | Planning, reasoning, execution | ✅ Have it | Orchestrator + Judge |
 | Context Engineering / RAG | ✅ Have it | LlamaIndex + ChromaDB |

docs/pending/03_modal_integration.md

@@ -49,22 +49,24 @@ import numpy as np
 
 ### Step 1: Wire Into Agent Pipeline
 
-Add a `StatisticalAnalysisAgent` that uses Modal:
+Add a `StatisticalAnalyzer` service that uses Modal:
 
 ```python
-# src/agents/analysis_agent.py
+# src/services/statistical_analyzer.py
+import asyncio
 from src.tools.code_execution import get_code_executor
 
-class AnalysisAgent:
+class StatisticalAnalyzer:
     """Run statistical analysis on evidence using Modal sandbox."""
 
     async def analyze(self, evidence: list[Evidence], query: str) -> str:
         # 1. LLM generates analysis code
         code = await self._generate_analysis_code(evidence, query)
 
-        # 2. Execute in Modal sandbox
+        # 2. Execute in Modal sandbox (run sync executor in thread pool)
         executor = get_code_executor()
-        result = executor.execute(code)
+        loop = asyncio.get_event_loop()
+        result = await loop.run_in_executor(None, executor.execute, code)
 
         # 3. Return results
         return result["stdout"]

tests/integration/{test_mcp_server.py → test_mcp_tools_live.py}

@@ -1,10 +1,10 @@
-"""Integration tests for MCP server functionality."""
+"""Integration tests for MCP tool wrappers with live API calls."""
 
 import pytest
 
 
-class TestMCPServerIntegration:
-    """Integration tests for MCP server (requires running app)."""
+class TestMCPToolsLive:
+    """Integration tests for MCP tools against live APIs (PubMed, etc.)."""
 
     @pytest.mark.integration
     @pytest.mark.asyncio