add mcp runtime as default to all providers (#816)

# What does this PR do?

This is needed to have the notebook work with MCP

distributions/dependencies.json

@@ -1,9 +1,43 @@
 {
-  "bedrock": [
+  "hf-serverless": [
+    "aiohttp",
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "huggingface_hub",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pypdf",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "tqdm",
+    "transformers",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "together": [
     "aiosqlite",
     "autoevals",
     "blobfile",
-    "boto3",
     "chardet",
     "chromadb-client",
     "datasets",
@@ -12,6 +46,75 @@
     "fire",
     "httpx",
     "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pypdf",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "together",
+    "tqdm",
+    "transformers",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "vllm-gpu": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pypdf",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "tqdm",
+    "transformers",
+    "uvicorn",
+    "vllm",
+    "sentence-transformers --no-deps",
+    "torch --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "remote-vllm": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "matplotlib",
+    "mcp",
     "nltk",
     "numpy",
     "openai",
@@ -45,6 +148,7 @@
     "fireworks-ai",
     "httpx",
     "matplotlib",
+    "mcp",
     "nltk",
     "numpy",
     "openai",
@@ -65,7 +169,7 @@
     "sentence-transformers --no-deps",
     "torch --index-url https://download.pytorch.org/whl/cpu"
   ],
-  "hf-endpoint": [
+  "tgi": [
     "aiohttp",
     "aiosqlite",
     "autoevals",
@@ -79,6 +183,7 @@
     "httpx",
     "huggingface_hub",
     "matplotlib",
+    "mcp",
     "nltk",
     "numpy",
     "openai",
@@ -99,11 +204,11 @@
     "sentence-transformers --no-deps",
     "torch --index-url https://download.pytorch.org/whl/cpu"
   ],
-  "hf-serverless": [
+  "bedrock": [
-    "aiohttp",
     "aiosqlite",
     "autoevals",
     "blobfile",
+    "boto3",
     "chardet",
     "chromadb-client",
     "datasets",
@@ -111,8 +216,8 @@
     "fastapi",
     "fire",
     "httpx",
-    "huggingface_hub",
     "matplotlib",
+    "mcp",
     "nltk",
     "numpy",
     "openai",
@@ -148,6 +253,7 @@
     "httpx",
     "lm-format-enforcer",
     "matplotlib",
+    "mcp",
     "nltk",
     "numpy",
     "openai",
@@ -172,6 +278,38 @@
     "sentence-transformers --no-deps",
     "torch --index-url https://download.pytorch.org/whl/cpu"
   ],
+  "nvidia": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "datasets",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pypdf",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "tqdm",
+    "transformers",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch --index-url https://download.pytorch.org/whl/cpu"
+  ],
   "meta-reference-quantized-gpu": [
     "accelerate",
     "aiosqlite",
@@ -188,6 +326,7 @@
     "httpx",
     "lm-format-enforcer",
     "matplotlib",
+    "mcp",
     "nltk",
     "numpy",
     "openai",
@@ -213,6 +352,39 @@
     "sentence-transformers --no-deps",
     "torch --index-url https://download.pytorch.org/whl/cpu"
   ],
+  "cerebras": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "cerebras_cloud_sdk",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "matplotlib",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pypdf",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "tqdm",
+    "transformers",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch --index-url https://download.pytorch.org/whl/cpu"
+  ],
   "ollama": [
     "aiohttp",
     "aiosqlite",
@@ -247,7 +419,7 @@
     "sentence-transformers --no-deps",
     "torch --index-url https://download.pytorch.org/whl/cpu"
   ],
-  "tgi": [
+  "hf-endpoint": [
     "aiohttp",
     "aiosqlite",
     "autoevals",
@@ -261,168 +433,7 @@
     "httpx",
     "huggingface_hub",
     "matplotlib",
-    "nltk",
+    "mcp",
-    "numpy",
-    "openai",
-    "opentelemetry-exporter-otlp-proto-http",
-    "opentelemetry-sdk",
-    "pandas",
-    "pillow",
-    "psycopg2-binary",
-    "pypdf",
-    "redis",
-    "requests",
-    "scikit-learn",
-    "scipy",
-    "sentencepiece",
-    "tqdm",
-    "transformers",
-    "uvicorn",
-    "sentence-transformers --no-deps",
-    "torch --index-url https://download.pytorch.org/whl/cpu"
-  ],
-  "together": [
-    "aiosqlite",
-    "autoevals",
-    "blobfile",
-    "chardet",
-    "chromadb-client",
-    "datasets",
-    "faiss-cpu",
-    "fastapi",
-    "fire",
-    "httpx",
-    "matplotlib",
-    "nltk",
-    "numpy",
-    "openai",
-    "opentelemetry-exporter-otlp-proto-http",
-    "opentelemetry-sdk",
-    "pandas",
-    "pillow",
-    "psycopg2-binary",
-    "pypdf",
-    "redis",
-    "requests",
-    "scikit-learn",
-    "scipy",
-    "sentencepiece",
-    "together",
-    "tqdm",
-    "transformers",
-    "uvicorn",
-    "sentence-transformers --no-deps",
-    "torch --index-url https://download.pytorch.org/whl/cpu"
-  ],
-  "remote-vllm": [
-    "aiosqlite",
-    "autoevals",
-    "blobfile",
-    "chardet",
-    "chromadb-client",
-    "datasets",
-    "faiss-cpu",
-    "fastapi",
-    "fire",
-    "httpx",
-    "matplotlib",
-    "nltk",
-    "numpy",
-    "openai",
-    "opentelemetry-exporter-otlp-proto-http",
-    "opentelemetry-sdk",
-    "pandas",
-    "pillow",
-    "psycopg2-binary",
-    "pypdf",
-    "redis",
-    "requests",
-    "scikit-learn",
-    "scipy",
-    "sentencepiece",
-    "tqdm",
-    "transformers",
-    "uvicorn",
-    "sentence-transformers --no-deps",
-    "torch --index-url https://download.pytorch.org/whl/cpu"
-  ],
-  "cerebras": [
-    "aiosqlite",
-    "autoevals",
-    "blobfile",
-    "cerebras_cloud_sdk",
-    "chardet",
-    "chromadb-client",
-    "datasets",
-    "faiss-cpu",
-    "fastapi",
-    "fire",
-    "httpx",
-    "matplotlib",
-    "nltk",
-    "numpy",
-    "openai",
-    "opentelemetry-exporter-otlp-proto-http",
-    "opentelemetry-sdk",
-    "pandas",
-    "pillow",
-    "psycopg2-binary",
-    "pypdf",
-    "redis",
-    "requests",
-    "scikit-learn",
-    "scipy",
-    "sentencepiece",
-    "tqdm",
-    "transformers",
-    "uvicorn",
-    "sentence-transformers --no-deps",
-    "torch --index-url https://download.pytorch.org/whl/cpu"
-  ],
-  "vllm-gpu": [
-    "aiosqlite",
-    "autoevals",
-    "blobfile",
-    "chardet",
-    "chromadb-client",
-    "datasets",
-    "faiss-cpu",
-    "fastapi",
-    "fire",
-    "httpx",
-    "matplotlib",
-    "nltk",
-    "numpy",
-    "openai",
-    "opentelemetry-exporter-otlp-proto-http",
-    "opentelemetry-sdk",
-    "pandas",
-    "pillow",
-    "psycopg2-binary",
-    "pypdf",
-    "redis",
-    "requests",
-    "scikit-learn",
-    "scipy",
-    "sentencepiece",
-    "tqdm",
-    "transformers",
-    "uvicorn",
-    "vllm",
-    "sentence-transformers --no-deps",
-    "torch --index-url https://download.pytorch.org/whl/cpu"
-  ],
-  "nvidia": [
-    "aiosqlite",
-    "autoevals",
-    "blobfile",
-    "chardet",
-    "datasets",
-    "faiss-cpu",
-    "fastapi",
-    "fire",
-    "httpx",
-    "matplotlib",
     "nltk",
     "numpy",
     "openai",

docs/source/distributions/remote_hosted_distro/nvidia.md

@@ -12,7 +12,7 @@ The `llamastack/distribution-nvidia` distribution consists of the following prov
 | safety | `inline::llama-guard` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
-| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime` |
+| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime`, `remote::model-context-protocol` |
 
 
 ### Environment Variables

docs/source/distributions/self_hosted_distro/bedrock.md

@@ -19,7 +19,7 @@ The `llamastack/distribution-bedrock` distribution consists of the following pro
 | safety | `remote::bedrock` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
-| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime` |
+| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime`, `remote::model-context-protocol` |
 
 
 

docs/source/distributions/self_hosted_distro/fireworks.md

@@ -22,7 +22,7 @@ The `llamastack/distribution-fireworks` distribution consists of the following p
 | safety | `inline::llama-guard` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
-| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime` |
+| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime`, `remote::model-context-protocol` |
 
 
 ### Environment Variables

docs/source/distributions/self_hosted_distro/meta-reference-gpu.md

@@ -22,7 +22,7 @@ The `llamastack/distribution-meta-reference-gpu` distribution consists of the fo
 | safety | `inline::llama-guard` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
-| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime` |
+| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime`, `remote::model-context-protocol` |
 
 
 Note that you need access to nvidia GPUs to run this distribution. This distribution is not compatible with CPU-only machines or machines with AMD GPUs.

docs/source/distributions/self_hosted_distro/meta-reference-quantized-gpu.md

@@ -22,7 +22,7 @@ The `llamastack/distribution-meta-reference-quantized-gpu` distribution consists
 | safety | `inline::llama-guard` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
-| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime` |
+| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime`, `remote::model-context-protocol` |
 
 
 The only difference vs. the `meta-reference-gpu` distribution is that it has support for more efficient inference -- with fp8, int4 quantization, etc.

docs/source/distributions/self_hosted_distro/remote-vllm.md

@@ -21,7 +21,7 @@ The `llamastack/distribution-remote-vllm` distribution consists of the following
 | safety | `inline::llama-guard` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
-| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime` |
+| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime`, `remote::model-context-protocol` |
 
 
 You can use this distribution if you have GPUs and want to run an independent vLLM server container for running inference.

docs/source/distributions/self_hosted_distro/tgi.md

@@ -23,7 +23,7 @@ The `llamastack/distribution-tgi` distribution consists of the following provide
 | safety | `inline::llama-guard` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
-| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime` |
+| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime`, `remote::model-context-protocol` |
 
 
 You can use this distribution if you have GPUs and want to run an independent TGI server container for running inference.

docs/source/distributions/self_hosted_distro/together.md

@@ -22,7 +22,7 @@ The `llamastack/distribution-together` distribution consists of the following pr
 | safety | `inline::llama-guard` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
-| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime` |
+| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime`, `remote::model-context-protocol` |
 
 
 ### Environment Variables

llama_stack/templates/bedrock/bedrock.py

@@ -30,6 +30,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::tavily-search",
             "inline::code-interpreter",
             "inline::memory-runtime",
+            "remote::model-context-protocol",
         ],
     }
     name = "bedrock"

llama_stack/templates/bedrock/build.yaml

@@ -28,4 +28,5 @@ distribution_spec:
     - remote::tavily-search
     - inline::code-interpreter
     - inline::memory-runtime
+    - remote::model-context-protocol
 image_type: conda

llama_stack/templates/bedrock/run.yaml

@@ -81,6 +81,9 @@ providers:
   - provider_id: memory-runtime
     provider_type: inline::memory-runtime
     config: {}
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+    config: {}
 metadata_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/bedrock}/registry.db

llama_stack/templates/fireworks/build.yaml

@@ -28,4 +28,5 @@ distribution_spec:
     - remote::tavily-search
     - inline::code-interpreter
     - inline::memory-runtime
+    - remote::model-context-protocol
 image_type: conda

llama_stack/templates/fireworks/fireworks.py

@@ -39,6 +39,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::tavily-search",
             "inline::code-interpreter",
             "inline::memory-runtime",
+            "remote::model-context-protocol",
         ],
     }
 

llama_stack/templates/fireworks/run-with-safety.yaml

@@ -92,6 +92,9 @@ providers:
   - provider_id: memory-runtime
     provider_type: inline::memory-runtime
     config: {}
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+    config: {}
 metadata_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/registry.db

llama_stack/templates/fireworks/run.yaml

@@ -86,6 +86,9 @@ providers:
   - provider_id: memory-runtime
     provider_type: inline::memory-runtime
     config: {}
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+    config: {}
 metadata_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/registry.db

llama_stack/templates/hf-endpoint/build.yaml

@@ -28,4 +28,5 @@ distribution_spec:
     - remote::tavily-search
     - inline::code-interpreter
     - inline::memory-runtime
+    - remote::model-context-protocol
 image_type: conda

llama_stack/templates/hf-endpoint/hf_endpoint.py

@@ -34,6 +34,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::tavily-search",
             "inline::code-interpreter",
             "inline::memory-runtime",
+            "remote::model-context-protocol",
         ],
     }
     name = "hf-endpoint"

llama_stack/templates/hf-endpoint/run-with-safety.yaml

@@ -91,6 +91,9 @@ providers:
   - provider_id: memory-runtime
     provider_type: inline::memory-runtime
     config: {}
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+    config: {}
 metadata_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/registry.db

llama_stack/templates/hf-endpoint/run.yaml

@@ -86,6 +86,9 @@ providers:
   - provider_id: memory-runtime
     provider_type: inline::memory-runtime
     config: {}
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+    config: {}
 metadata_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/registry.db

llama_stack/templates/hf-serverless/build.yaml

@@ -28,4 +28,5 @@ distribution_spec:
     - remote::tavily-search
     - inline::code-interpreter
     - inline::memory-runtime
+    - remote::model-context-protocol
 image_type: conda

llama_stack/templates/hf-serverless/hf_serverless.py

@@ -34,6 +34,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::tavily-search",
             "inline::code-interpreter",
             "inline::memory-runtime",
+            "remote::model-context-protocol",
         ],
     }
 

llama_stack/templates/hf-serverless/run-with-safety.yaml

@@ -91,6 +91,9 @@ providers:
   - provider_id: memory-runtime
     provider_type: inline::memory-runtime
     config: {}
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+    config: {}
 metadata_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/registry.db

llama_stack/templates/hf-serverless/run.yaml

@@ -86,6 +86,9 @@ providers:
   - provider_id: memory-runtime
     provider_type: inline::memory-runtime
     config: {}
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+    config: {}
 metadata_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/registry.db

llama_stack/templates/meta-reference-gpu/build.yaml

@@ -28,4 +28,5 @@ distribution_spec:
     - remote::tavily-search
     - inline::code-interpreter
     - inline::memory-runtime
+    - remote::model-context-protocol
 image_type: conda

llama_stack/templates/meta-reference-gpu/meta_reference.py

@@ -38,6 +38,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::tavily-search",
             "inline::code-interpreter",
             "inline::memory-runtime",
+            "remote::model-context-protocol",
         ],
     }
     name = "meta-reference-gpu"

llama_stack/templates/meta-reference-gpu/run-with-safety.yaml

@@ -93,6 +93,9 @@ providers:
   - provider_id: memory-runtime
     provider_type: inline::memory-runtime
     config: {}
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+    config: {}
 metadata_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/registry.db

llama_stack/templates/meta-reference-gpu/run.yaml

@@ -87,6 +87,9 @@ providers:
   - provider_id: memory-runtime
     provider_type: inline::memory-runtime
     config: {}
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+    config: {}
 metadata_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/registry.db

llama_stack/templates/meta-reference-quantized-gpu/build.yaml

@@ -28,4 +28,5 @@ distribution_spec:
     - remote::tavily-search
     - inline::code-interpreter
     - inline::memory-runtime
+    - remote::model-context-protocol
 image_type: conda

llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py

@@ -33,6 +33,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::tavily-search",
             "inline::code-interpreter",
             "inline::memory-runtime",
+            "remote::model-context-protocol",
         ],
     }
     default_tool_groups = [

llama_stack/templates/meta-reference-quantized-gpu/run.yaml

@@ -89,6 +89,9 @@ providers:
   - provider_id: memory-runtime
     provider_type: inline::memory-runtime
     config: {}
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+    config: {}
 metadata_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/registry.db

llama_stack/templates/nvidia/build.yaml

@@ -26,4 +26,5 @@ distribution_spec:
     - remote::tavily-search
     - inline::code-interpreter
     - inline::memory-runtime
+    - remote::model-context-protocol
 image_type: conda

llama_stack/templates/nvidia/nvidia.py

@@ -29,6 +29,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::tavily-search",
             "inline::code-interpreter",
             "inline::memory-runtime",
+            "remote::model-context-protocol",
         ],
     }
 

llama_stack/templates/nvidia/run.yaml

@@ -83,6 +83,9 @@ providers:
   - provider_id: memory-runtime
     provider_type: inline::memory-runtime
     config: {}
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+    config: {}
 metadata_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/registry.db

llama_stack/templates/remote-vllm/build.yaml

@@ -28,4 +28,5 @@ distribution_spec:
     - remote::tavily-search
     - inline::code-interpreter
     - inline::memory-runtime
+    - remote::model-context-protocol
 image_type: conda

llama_stack/templates/remote-vllm/run-with-safety.yaml

@@ -93,6 +93,9 @@ providers:
   - provider_id: memory-runtime
     provider_type: inline::memory-runtime
     config: {}
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+    config: {}
 metadata_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/registry.db

llama_stack/templates/remote-vllm/run.yaml

@@ -87,6 +87,9 @@ providers:
   - provider_id: memory-runtime
     provider_type: inline::memory-runtime
     config: {}
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+    config: {}
 metadata_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/registry.db

llama_stack/templates/remote-vllm/vllm.py

@@ -36,6 +36,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::tavily-search",
             "inline::code-interpreter",
             "inline::memory-runtime",
+            "remote::model-context-protocol",
         ],
     }
     name = "remote-vllm"

llama_stack/templates/tgi/build.yaml

@@ -28,4 +28,5 @@ distribution_spec:
     - remote::tavily-search
     - inline::code-interpreter
     - inline::memory-runtime
+    - remote::model-context-protocol
 image_type: conda

llama_stack/templates/tgi/run-with-safety.yaml

@@ -86,6 +86,9 @@ providers:
   - provider_id: memory-runtime
     provider_type: inline::memory-runtime
     config: {}
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+    config: {}
 metadata_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/tgi}/registry.db

llama_stack/templates/tgi/run.yaml

@@ -85,6 +85,9 @@ providers:
   - provider_id: memory-runtime
     provider_type: inline::memory-runtime
     config: {}
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+    config: {}
 metadata_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/tgi}/registry.db

llama_stack/templates/tgi/tgi.py

@@ -36,6 +36,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::tavily-search",
             "inline::code-interpreter",
             "inline::memory-runtime",
+            "remote::model-context-protocol",
         ],
     }
     name = "tgi"

llama_stack/templates/together/build.yaml

@@ -28,4 +28,5 @@ distribution_spec:
     - remote::tavily-search
     - inline::code-interpreter
     - inline::memory-runtime
+    - remote::model-context-protocol
 image_type: conda

llama_stack/templates/together/run-with-safety.yaml

@@ -92,6 +92,9 @@ providers:
   - provider_id: memory-runtime
     provider_type: inline::memory-runtime
     config: {}
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+    config: {}
 metadata_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/registry.db

llama_stack/templates/together/run.yaml

@@ -86,6 +86,9 @@ providers:
   - provider_id: memory-runtime
     provider_type: inline::memory-runtime
     config: {}
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+    config: {}
 metadata_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/registry.db

llama_stack/templates/together/together.py

@@ -39,6 +39,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::tavily-search",
             "inline::code-interpreter",
             "inline::memory-runtime",
+            "remote::model-context-protocol",
         ],
     }
     name = "together"

llama_stack/templates/vllm-gpu/build.yaml

@@ -28,4 +28,5 @@ distribution_spec:
     - remote::tavily-search
     - inline::code-interpreter
     - inline::memory-runtime
+    - remote::model-context-protocol
 image_type: conda

llama_stack/templates/vllm-gpu/run.yaml

@@ -89,6 +89,9 @@ providers:
   - provider_id: memory-runtime
     provider_type: inline::memory-runtime
     config: {}
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+    config: {}
 metadata_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/vllm-gpu}/registry.db

llama_stack/templates/vllm-gpu/vllm.py

@@ -33,6 +33,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::tavily-search",
             "inline::code-interpreter",
             "inline::memory-runtime",
+            "remote::model-context-protocol",
         ],
     }