spiceai · lukekim · Mar 31, 2025 · Mar 17, 2025 · Mar 17, 2025 · Mar 18, 2025
diff --git a/website/docs/components/tools/index.md b/website/docs/components/tools/index.md
@@ -12,20 +12,22 @@ For details on tool specifications, see the [Tools Spicepod Reference](/docs/ref
 
 ### Available Tools
 
-| Name                      | Description                                                       | Default Group     |
-| ------------------------- | ----------------------------------------------------------------- | ----------------- |
-| `list_datasets`           | List all available datasets in the runtime.                       | `auto`               |
-| `sql`                     | Execute SQL queries on the runtime.                               | `auto`               |
-| `table_schema`            | Get the schema of a specific SQL table.                           | `auto`               |
-| `document_similarity`     | Retrieve documents based on an input query.                       | `auto`               |
-| `sample_distinct_columns` | Generate a synthetic sample of data with distinct values.         | `auto`               |
-| `random_sample`           | Sample random rows from a table.                                  | `auto`               |
-| `top_n_sample`            | Sample the top N rows from a table based on a specified ordering. | `auto`               |
-| `memory:load`             | Retrieve all stored memories from the last time period.           | `memory`                |
-| `memory:store`            | Store information from LLM interaction(s) for future reference.   | `memory`                |
+| Name                      | Description                                                       | Default Group |
+| ------------------------- | ----------------------------------------------------------------- | ------------- |
+| `list_datasets`           | List all available datasets in the runtime.                       | `auto`        |
+| `sql`                     | Execute SQL queries on the runtime.                               | `auto`        |
+| `table_schema`            | Get the schema of a specific SQL table.                           | `auto`        |
+| `document_similarity`     | Retrieve documents based on an input query.                       | `auto`        |
+| `sample_distinct_columns` | Generate a synthetic sample of data with distinct values.         | `auto`        |
+| `random_sample`           | Sample random rows from a table.                                  | `auto`        |
+| `top_n_sample`            | Sample the top N rows from a table based on a specified ordering. | `auto`        |
+| `memory:load`             | Retrieve all stored memories from the last time period.           | `memory`      |
+| `memory:store`            | Store information from LLM interaction(s) for future reference.   | `memory`      |
 
 ### Tool Groups
+
 Tool groups are predefined sets of tools that can be provided to LLMs in a single tool name. For example, the `auto` tool group provides all default tools to the LLM (see above table).
+
 ```yaml
 models:
   - name: full-runtime
@@ -34,6 +36,12 @@ models:
       tools: auto # Use all default tools
 ```
 
-Available tool groups:
- - `auto`: All default tools (see above table).
- - `memory`: Memory tools for storing and retrieving information across conversations.
+#### Available tool groups
+
+| Name         | Description                                                                                  |
+| ------------ | -------------------------------------------------------------------------------------------- |
+| `auto`       | All default tools (see above table)                                                          |
+| `memory`     | Memory tools for storing and retrieving information across conversations.                    |
+| [`MCP`][mcp] | Tools provided from an MCP server. Can be run within Spice, or connected to over HTTP(s) SSE |
+
+[mcp]: /docs/components/tools/mcp
diff --git a/website/docs/components/tools/mcp.md b/website/docs/components/tools/mcp.md
@@ -0,0 +1,109 @@
+---
+title: 'Model Context Protocol Tools'
+sidebar_label: 'MCP Tools'
+---
+
+Spice integrates with tools and services using the [Model Context Protocol](https://modelcontextprotocol.io/) (MCP). MCP tools can be configured to run internally or connect to external servers over HTTP using the Server-Sent Events (SSE) protocol.
+
+## Overview
+
+MCP helps extend the capabilities of the Spice runtime by enabling integration with external tools and services. This includes:
+
+1. Running stdio-based MCP servers internally.
+2. Connecting to external MCP servers over SSE.
+
+## Configuring MCP Tools
+
+To configure MCP tools, define them in the `tools` section of your `spicepod.yaml` file. The `from` field specifies the transport mechanism, such as `mcp:npx` for stdio-based tools or an HTTP URL for SSE-based tools.
+
+### Example: Adding an MCP Tool (Stdio)
+
+The following example demonstrates how to configure an MCP tool using `npx` to run a Google Maps MCP server:
+
+```yaml
+tools:
+  - name: google_maps
+    from: mcp:npx
+    params:
+      mcp_args: -y @modelcontextprotocol/server-google-maps
+```
+
+### Example: Connecting to an External MCP Server (SSE)
+
+This example shows how to connect to an external MCP server over SSE:
+
+```yaml
+tools:
+  - name: external_mcp_server
+    from: mcp:http://example.com/v1/mcp/sse
+```
+
+## Using MCP Tools with Models
+
+Once configured, MCP tools can be assigned to models via the `tools` parameter. For example:
+
+```yaml
+models:
+  - name: model_with_mcp
+    from: openai:gpt-4o
+    params:
+      tools: google_maps
+```
+
+## Spice as an MCP Server
+
+Spice can also act as an MCP server, exposing its tools over SSE. This enables other Spice instances or external systems to connect and use the tools.
+
+### Example: Connecting to Another Spice Instance via MCP
+
+```yaml
+tools:
+  - name: spice_instance
+    from: mcp:http://localhost:8090/v1/mcp/sse
+```
+
+## Configuration Options
+
+### `from`
+
+The `from` field specifies the transport mechanism for the MCP tool:
+
+- **SSE**: Use an HTTP URL ending with `/sse` (e.g., `http://localhost:8090/v1/mcp/sse`).
+- **Stdio**: Use commands like `mcp:npx` or `mcp:docker`. Additional arguments can be passed via `params.mcp_args`.
+
+### `params`
+
+The `params` field provides additional configuration for MCP tools. For stdio-based tools, use `mcp_args` to specify command-line arguments.
+
+```yaml
+tools:
+  - name: custom_tool
+    from: mcp:npx
+    params:
+      mcp_args: -y @custom/tool
+```
+
+### `env`
+
+For stdio-based MCP tools, environment variables can be set using the `env` field.
+
+```yaml
+tools:
+  - name: tool_with_env
+    from: mcp:docker
+    env:
+      API_KEY: your_api_key
+```
+
+### `description`
+
+The `description` field provides a textual description of the tool. This description is passed to any language model that uses the tool.
+
+```yaml
+tools:
+  - name: google_maps
+    from: mcp:npx
+    description: Provides geocoding and mapping capabilities.
+```
+
+For more details, see the [MCP Tools Reference](/docs/reference/spicepod/tools).
diff --git a/website/docs/features/large-language-models/evals.md b/website/docs/features/large-language-models/evals.md
@@ -2,7 +2,7 @@
 title: 'Evaluating Language Models'
 sidebar_label: 'Evals'
 description: 'Learn how Spice evaluates, tracks, compares, and improves language model performance for specific tasks'
-sidebar_position: 3
+sidebar_position: 4
 pagination_prev: null
 pagination_next: null
 tags:

diff --git a/website/docs/features/large-language-models/mcp.md b/website/docs/features/large-language-models/mcp.md
@@ -0,0 +1,106 @@
+---
+title: 'Model Context Protocol (MCP)'
+sidebar_label: 'MCP'
+description: 'Learn how to use the Model Context Protocol (MCP) with Spice.'
+sidebar_position: 2
+pagination_prev: null
+pagination_next: null
+tags:
+  - models
+  - tools
+  - mcp
+---
+
+The Model Context Protocol (MCP) helps integrate external tools and services into the Spice runtime. MCP tools can be run internally or connected over HTTP using the Server-Sent Events (SSE) protocol.
+
+![Spice.ai Open Source Model-Context-Protocol (MCP) support](/img/features/mcp.png)
+
+## Overview
+
+MCP enables Spice to:
+
+1. Run stdio-based MCP servers internally.
+2. Connect to external MCP servers over SSE.
+
+This flexibility helps extend the capabilities of language models by providing access to external tools and services.
+
+## Configuring MCP Tools
+
+To configure MCP tools, define them in the `tools` section of your `spicepod.yaml` file. The `from` field specifies the transport mechanism (e.g., `mcp:npx` for stdio or an HTTP URL for SSE).
+
+### Example: Adding an MCP Tool
+
+```yaml
+tools:
+  - name: google_maps
+    from: mcp:npx
+    params:
+      mcp_args: -y @modelcontextprotocol/server-google-maps
+```
+
+### Example: Connecting to an External MCP Server
+
+```yaml
+tools:
+  - name: external_mcp_server
+    from: mcp:http://example.com/v1/mcp/sse
+```
+
+## Using MCP Tools with Models
+
+Once configured, MCP tools can be assigned to models via the `tools` parameter.
+
+```yaml
+models:
+  - name: model_with_mcp
+    from: openai:gpt-4o
+    params:
+      tools: google_maps
+```
+
+## Spice as an MCP Server
+
+Spice can also act as an MCP server, exposing its tools over SSE. This enables other Spice instances or external systems to connect and use the tools.
+
+### Example: Connecting to another Spice instance via MCP
+
+```yaml
+tools:
+  - name: spice_instance
+    from: mcp:http://localhost:8090/v1/mcp/sse
+```
+
+## Additional Configuration Options
+
+### `from`
+
+The `from` field specifies the transport mechanism for the MCP tool:
+
+- **SSE**: Use an HTTP URL ending with `/sse` (e.g., `http://localhost:8090/v1/mcp/sse`).
+- **Stdio**: Use commands like `mcp:npx` or `mcp:docker`. Additional arguments can be passed via `params.mcp_args`.
+
+### `params`
+
+The `params` field provides additional configuration for MCP tools. For stdio-based tools, use `mcp_args` to specify command-line arguments.
+
+```yaml
+tools:
+  - name: custom_tool
+    from: mcp:npx
+    params:
+      mcp_args: -y @custom/tool
+```
+
+### `env`
+
+For stdio-based MCP tools, environment variables can be set using the `env` field.
+
+```yaml
+tools:
+  - name: tool_with_env
+    from: mcp:docker
+    env:
+      API_KEY: your_api_key
+```
+
+For more details, see the [MCP Tools Reference](/docs/components/tools/mcp).
diff --git a/website/docs/features/large-language-models/memory.md b/website/docs/features/large-language-models/memory.md
@@ -2,7 +2,7 @@
 title: 'Language Model Memory'
 sidebar_label: 'Memory'
 description: 'Learn how to provide LLMs with memory'
-sidebar_position: 2
+sidebar_position: 3
 pagination_prev: null
 pagination_next: null
 tags:

diff --git a/website/docs/features/large-language-models/parameter_overrides.md b/website/docs/features/large-language-models/parameter_overrides.md
@@ -2,7 +2,7 @@
 title: 'Language Model Overrides'
 sidebar_label: 'Parameter Overrides'
 description: 'Learn how to override default LLM hyperparameters in Spice.'
-sidebar_position: 4
+sidebar_position: 5
 pagination_prev: null
 pagination_next: null
 tags:

diff --git a/website/docs/features/large-language-models/tools.md b/website/docs/features/large-language-models/tools.md
@@ -26,11 +26,12 @@ models:
 ```
 
 ### Example: Specifying tools via a Tool Group
+
 ```yaml
-  - name: full-runtime
-    from: openai:gpt-4o
-    params:
-      tools: auto # Use all default tools
+- name: full-runtime
+  from: openai:gpt-4o
+  params:
+    tools: auto # Use all default tools
 ```
 
 For details on tool groups, see [Tool Components](/docs/components/tools#tool-groups).

diff --git a/website/docs/index.mdx b/website/docs/index.mdx
@@ -3,20 +3,21 @@ sidebar_position: 0
 title: Home
 ---
 
-import ReactPlayer from 'react-player';
-import ThemeBasedImage from '@site/src/components/ThemeBasedImage';
+import ReactPlayer from 'react-player'
+import ThemeBasedImage from '@site/src/components/ThemeBasedImage'
 
 # Spice.ai Open Source
 
 **Spice** is an open-source SQL query and AI compute engine, written in Rust, for data-driven apps and agents.
 
 ![Spice.ai Open Source Data Query & AI-Inference Compute Engine](/img/spice.ai-compute-engine.png)
 
-Spice provides three industry standard APIs in a lightweight, portable runtime (single ~140 MB binary):
+Spice provides four industry standard APIs in a lightweight, portable runtime (single ~140 MB binary):
 
-1. **SQL Query APIs**: HTTP, Arrow Flight, Arrow Flight SQL, ODBC, JDBC, and ADBC.
-2. **OpenAI-Compatible APIs**: HTTP APIs compatible the OpenAI SDK, AI SDK with local model serving (CUDA/Metal accelerated) and gateway to hosted models.
-3. **Iceberg Catalog REST APIs**: A unified Iceberg Catalog API.
+1. **SQL Query APIs**: Supports HTTP, Arrow Flight, Arrow Flight SQL, ODBC, JDBC, and ADBC.
+2. **OpenAI-Compatible APIs**: Provides HTTP APIs for OpenAI SDK compatibility, local model serving (CUDA/Metal accelerated), and hosted model gateway.
+3. **Iceberg Catalog REST APIs**: Offers a unified API for Iceberg Catalog.
+4. **MCP HTTP+SSE APIs**: Enables integration with external tools via Model Context Protocol (MCP) using HTTP and Server-Sent Events (SSE).
 
 :::tip[Goal 🎯]
 Developers can focus on building data apps and AI agents confidently, knowing they are grounded in data.
@@ -34,7 +35,7 @@ Spice is primarily used for:
 
 Spice is built-on industry leading technologies including [Apache DataFusion](https://datafusion.apache.org), Apache Arrow, Arrow Flight, SQLite, and DuckDB. If you want to build with DataFusion or using DuckDB, Spice provides a simple, flexible, and production-ready engine you can just use.
 
-<div style={{display: 'flex', justifyContent: 'center'}}>
+<div style={{ display: 'flex', justifyContent: 'center' }}>
   <ThemeBasedImage
     width='600'
     alt='OGP'
@@ -47,7 +48,7 @@ Spice is built-on industry leading technologies including [Apache DataFusion](ht
 
 Spice makes it fast and easy to query data from one or more sources using SQL. You can co-locate a managed dataset with your application or machine learning model, and accelerate it with Arrow in-memory, SQLite/DuckDB, or with attached PostgreSQL for fast, high-concurrency, low-latency queries. Accelerated engines give you flexibility and control over query cost and performance.
 
-<div style={{display: 'flex', justifyContent: 'center'}}>
+<div style={{ display: 'flex', justifyContent: 'center' }}>
   <ThemeBasedImage
     width='800'
     alt='Before Spice'
@@ -94,7 +95,7 @@ Spice simplifies building data-driven AI applications and agents by making it fa
 | **Unified Data + AI Runtime** | ✅                                   | ―                  | ―          | ―                | ―                             |
 | **Federated Data Query**      | ✅                                   | ―                  | ―          | ―                | ―                             |
 | **Accelerated Data Access**   | ✅                                   | ―                  | ―          | ―                | ―                             |
-| **Tools/Functions**           | ✅                                   | ✅                 | ✅         | Limited          | Limited                       |
+| **Tools/Functions**           | ✅ (MCP HTTP+SSE)                    | ✅                 | ✅         | Limited          | Limited                       |
 | **LLM Memory**                | ✅                                   | ✅                 | ―          | ✅               | ―                             |
 | **Evaluations (Evals)**       | ✅                                   | Limited            | ―          | Limited          | ―                             |
 | **Search**                    | ✅ (VSS)                             | ✅                 | ✅         | Limited          | Limited                       |
@@ -136,7 +137,7 @@ Limited = Partial or restricted support
 
 ### Watch a quick BI dashboard acceleration demo
 
-<div style={{display: 'flex', justifyContent: 'center', marginBottom: '15px'}}>
+<div style={{ display: 'flex', justifyContent: 'center', marginBottom: '15px' }}>
   <ReactPlayer
     controls
     url='https://www.youtube.com/watch?v=t3B2AyshVY0&list=PLesJrUXEx3U-dQul0PqLV3TGTdUmr3B6e&index=1&pp=gAQBiAQB'

diff --git a/website/docs/reference/spicepod/tools.md b/website/docs/reference/spicepod/tools.md
@@ -26,6 +26,10 @@ Optional. A textual description of the tool's function.
 
 Optional. A map of key-value pairs for additional parameters specific to the tool.
 
+### `env`
+
+Optional. A map of key-value pairs of arbitrary environment variables to set when running the tool. Only useable if the tool requires a subprocess to run (e.g. MCP over stdio) .
+
 ### `dependsOn`
 
 Optional. A list of dependencies that must be available before this tool can be used.
diff --git a/website/static/img/features/mcp.png b/website/static/img/features/mcp.png