fix: Critical fixes for MCP server functionality

- Fix async context manager in graph_data_operations.py clear_data function
- Correct import paths for Gemini and Voyage embedders in factories.py
- Move LLM provider dependencies to optional-dependencies section
- Add sentence-transformers as optional dependency for local embeddings
- Update README with optional dependency installation instructions

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

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

mcp_server/README.md

@@ -78,6 +78,9 @@ curl -LsSf https://astral.sh/uv/install.sh | sh
 
 # Create a virtual environment and install dependencies in one step
 uv sync
+
+# Optional: Install additional LLM providers (anthropic, gemini, groq, voyage, sentence-transformers)
+uv sync --extra providers
 ```
 
 ## Configuration

mcp_server/factories.py

@@ -25,14 +25,14 @@ except ImportError:
     HAS_AZURE_EMBEDDER = False
 
 try:
-    from graphiti_core.embedder.gemini_embedder import GeminiEmbedder
+    from graphiti_core.embedder.gemini import GeminiEmbedder
 
     HAS_GEMINI_EMBEDDER = True
 except ImportError:
     HAS_GEMINI_EMBEDDER = False
 
 try:
-    from graphiti_core.embedder.voyage_embedder import VoyageEmbedder
+    from graphiti_core.embedder.voyage import VoyageEmbedder
 
     HAS_VOYAGE_EMBEDDER = True
 except ImportError:

mcp_server/pyproject.toml

@@ -11,10 +11,15 @@ dependencies = [
     "azure-identity>=1.21.0",
     "pydantic-settings>=2.0.0",
     "pyyaml>=6.0",
+]
+
+[project.optional-dependencies]
+providers = [
     "google-genai>=1.8.0",
     "anthropic>=0.49.0",
     "groq>=0.2.0",
     "voyageai>=0.2.3",
+    "sentence-transformers>=2.0.0",
 ]
 
 [dependency-groups]