feat: add Model Context Protocol (MCP) support and update documentation

YassinNouh21 · YassinNouh21 · commit 6c6f6eeafaee · 2025-05-31T18:25:53.000+03:00
Signed-off-by: yassinnouh21 &lt;yassinnouh21@gmail.com&gt;
diff --git a/docs/SUMMARY.md b/docs/SUMMARY.md
@@ -53,6 +53,7 @@
 * [Validating historical features with Great Expectations](tutorials/validating-historical-features.md)
 * [Building streaming features](tutorials/building-streaming-features.md)
 * [Retrieval Augmented Generation (RAG) with Feast](tutorials/rag-with-docling.md)
+* [MCP Feature Store Example - AI Agent Integration](../examples/mcp_feature_store/README.md)
 
 ## How-to Guides
 
@@ -146,6 +147,7 @@
 * [Feature servers](reference/feature-servers/README.md)
   * [Python feature server](reference/feature-servers/python-feature-server.md)
   * [\[Alpha\] Go feature server](reference/feature-servers/go-feature-server.md)
+  * [MCP Feature Server](reference/feature-servers/mcp-feature-server.md)
   * [Offline Feature Server](reference/feature-servers/offline-feature-server.md)
   * [Registry server](reference/feature-servers/registry-server.md)
 * [\[Beta\] Web UI](reference/alpha-web-ui.md)
diff --git a/docs/getting-started/genai.md b/docs/getting-started/genai.md
@@ -105,13 +105,61 @@ This integration enables:
 - Efficiently materializing features to vector databases
 - Scaling RAG applications to enterprise-level document repositories
 
+## Model Context Protocol (MCP) Support
+
+Feast supports the Model Context Protocol (MCP), which enables AI agents and applications to interact with your feature store through standardized MCP interfaces. This allows seamless integration with LLMs and AI agents for GenAI applications.
+
+### Key Benefits of MCP Support
+
+* **Standardized AI Integration**: Enable AI agents to discover and use features dynamically without hardcoded definitions
+* **Easy Setup**: Add MCP support with a simple configuration change and `pip install feast[mcp]`
+* **Agent-Friendly APIs**: Expose feature store capabilities through MCP tools that AI agents can understand and use
+* **Production Ready**: Built on top of Feast's proven feature serving infrastructure
+
+### Getting Started with MCP
+
+1. **Install MCP support**:
+   ```bash
+   pip install feast[mcp]
+   ```
+
+2. **Configure your feature store** to use MCP:
+   ```yaml
+   feature_server:
+     type: mcp
+     enabled: true
+     mcp_enabled: true
+     mcp_server_name: "feast-feature-store"
+     mcp_server_version: "1.0.0"
+   ```
+
+### How It Works
+
+The MCP integration uses the `fastapi_mcp` library to automatically transform your Feast feature server's FastAPI endpoints into MCP-compatible tools. When you enable MCP support:
+
+1. **Automatic Discovery**: The integration scans your FastAPI application and discovers all available endpoints
+2. **Tool Generation**: Each endpoint becomes an MCP tool with auto-generated schemas and descriptions
+3. **Dynamic Access**: AI agents can discover and call these tools dynamically without hardcoded definitions
+4. **Standard Protocol**: Uses the Model Context Protocol for standardized AI-to-API communication
+
+### Available MCP Tools
+
+The fastapi_mcp integration automatically exposes your Feast feature server's FastAPI endpoints as MCP tools. This means AI assistants can:
+
+* **Call `/get-online-features`** to retrieve features from the feature store
+* **Use `/health`** to check server status  
+
+For a complete example, see the [MCP Feature Store Example](../../examples/mcp_feature_store/).
+
 ## Learn More
 
 For more detailed information and examples:
 
 * [Vector Database Reference](../reference/alpha-vector-database.md)
 * [RAG Tutorial with Docling](../tutorials/rag-with-docling.md)
 * [Milvus Quickstart Example](https://github.com/feast-dev/feast/tree/master/examples/rag/milvus-quickstart.ipynb)
+* [MCP Feature Store Example](../../examples/mcp_feature_store/)
+* [MCP Feature Server Reference](../reference/feature-servers/mcp-feature-server.md)
 * [Spark Data Source](../reference/data-sources/spark.md)
 * [Spark Offline Store](../reference/offline-stores/spark.md)
 * [Spark Batch Materialization](../reference/batch-materialization/spark.md)
diff --git a/examples/mcp_feature_store/README.md b/examples/mcp_feature_store/README.md
@@ -10,13 +10,14 @@ This example demonstrates how to enable MCP (Model Context Protocol) support in
 
 ## Installation
 
-1. Install Feast if you haven't already:
+1. Install Feast with MCP support:
 ```bash
-pip install feast
+pip install feast[mcp]
 ```
 
-2. Install the MCP dependencies:
+Alternatively, you can install the dependencies separately:
 ```bash
+pip install feast
 pip install fastapi_mcp
 ```
 
@@ -35,12 +36,6 @@ This will create a `data` subdirectory and a `feature_repo` subdirectory if they
 
 3. Apply the feature store configuration:
 ```bash
-# Make sure you are in the directory where feature_store.yaml is located
-# (examples/mcp_feature_store after running 'feast init .')
-# Then, navigate into the 'feature_repo' directory created by 'feast init'
-# This is where your feature definitions would typically reside.
-# For this example, we don't have separate feature definition files yet,
-# but 'feast apply' still needs to be run from within a Feast project context.
 cd feature_repo 
 feast apply
 cd .. # Go back to examples/mcp_feature_store for the next steps
@@ -62,43 +57,11 @@ INFO:feast.feature_server:MCP support has been enabled for the Feast feature ser
 
 ## Available MCP Tools
 
-The server exposes the following MCP tools that can be used by AI agents:
-
-- `get_online_features`: Retrieve feature values for entities
-- `list_feature_views`: List all available feature views
-- `list_feature_services`: List all available feature services  
-- `get_feature_store_info`: Get information about the feature store
-
-## Available MCP Resources
-
-- `feast://feature-views`: JSON resource with all feature views
-- `feast://feature-services`: JSON resource with all feature services
-
-## Testing MCP Functionality
+The fastapi_mcp integration automatically exposes your Feast feature server's FastAPI endpoints as MCP tools. This means AI assistants can:
 
-You can test the MCP functionality by connecting an MCP-compatible client to the server endpoint. The exact method depends on your MCP client.
+- **Call `/get-online-features`** to retrieve features from the feature store
+- **Use `/health`** to check server status  
 
-## Example MCP Client Interaction
-
-```python
-# Example of how an MCP client might interact with the server
-# (This would be implemented by your MCP client library)
-
-# Get feature store information
-store_info = await mcp_client.call_tool("get_feature_store_info")
-print(f"Feature store: {store_info}")
-
-# List available feature views
-feature_views = await mcp_client.call_tool("list_feature_views") 
-print(f"Available feature views: {feature_views}")
-
-# Get features for specific entities
-features = await mcp_client.call_tool("get_online_features", {
-    "entities": {"driver_id": [1001, 1002]},
-    "features": ["driver_hourly_stats:conv_rate", "driver_hourly_stats:acc_rate"]
-})
-print(f"Features: {features}")
-```
 
 ## Configuration Details
 
diff --git a/setup.py b/setup.py
@@ -173,6 +173,8 @@
 
 CLICKHOUSE_REQUIRED = ["clickhouse-connect>=0.7.19"]
 
+MCP_REQUIRED = ["fastapi_mcp"]
+
 CI_REQUIRED = (
     [
         "build",
@@ -247,6 +249,7 @@
     + DOCLING_REQUIRED
     + TORCH_REQUIRED
     + CLICKHOUSE_REQUIRED
+    + MCP_REQUIRED
 )
 MINIMAL_REQUIRED = (
     GCP_REQUIRED
@@ -346,6 +349,7 @@
         "pytorch": TORCH_REQUIRED,
         "nlp": NLP_REQUIRED,
         "clickhouse": CLICKHOUSE_REQUIRED,
+        "mcp": MCP_REQUIRED,
     },
     include_package_data=True,
     license="Apache",
