Python: Remove bespoke Foundry toolbox helpers; standardize on MCP for toolbox consumption (#5671)

* Remove Foundry toolbox helpers; standardize on MCP for toolbox consumption - Remove RawFoundryChatClient.get_toolbox() and its fetch_toolbox import - Remove fetch_toolbox, select_toolbox_tools, get_toolbox_tool_name, get_toolbox_tool_type, FoundryHostedToolType, ToolboxToolSelectionInput from agent_framework_foundry._tools - Remove ExperimentalFeature.TOOLBOXES from _feature_stage.py (no consumers) - Drop toolbox re-exports from agent_framework_foundry/__init__.py and agent_framework.foundry namespace - Update _sanitize_foundry_response_tool docstring to remove toolbox framing; sanitization logic itself is unchanged - Update _agent.py docstring: 'toolbox-fetched MCP' → 'hosted MCP' - Delete tests/test_toolbox.py (all tests covered removed helpers) - Update test_foundry_chat_client.py: rename/redoc tests that mentioned toolbox but test sanitization that remains - Delete foundry_chat_client_with_toolbox.py (bespoke toolbox API sample) - Delete foundry_toolbox_context_provider.py (relied on select_toolbox_tools) - Rename foundry_chat_client_with_toolbox_mcp.py → foundry_chat_client_with_toolbox.py (canonical MCP pattern) - Rewrite 04_foundry_toolbox/main.py to use MCPStreamableHTTPTool - Update provider/README, context_providers/README, 04_foundry_toolbox/README Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix(samples): update 06_files sample to consume toolbox via MCP (#5670) Replace removed get_toolbox/select_toolbox_tools APIs with MCPStreamableHTTPTool, using allowed_tools=["code_interpreter"] to select only the code interpreter from the toolbox endpoint. Update .env.example and README to use FOUNDRY_TOOLBOX_ENDPOINT instead of TOOLBOX_NAME. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix(foundry): remove non-existent toolbox helper APIs from README (#5670) Remove the 'fetch, optionally filter, and pass tools directly' pattern from the FoundryChatClient toolbox documentation, as select_toolbox_tools and get_toolbox were removed. Only the MCP endpoint pattern is documented. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix(foundry): remove residual toolbox docstring references and reproduction report Remove REPRODUCTION_REPORT.md (workflow artifact that should not be committed), and update two remaining docstring references that still said 'toolbox reads' /'toolbox definition' after the toolbox helpers were removed. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Python: Remove bespoke Foundry toolbox helpers; standardize on MCP for toolbox consumption Fixes #5670 * fix(#5670): resolve toolbox endpoint from TOOLBOX_NAME fallback; add namespace regression tests - Add _resolve_toolbox_endpoint() helper in 04_foundry_toolbox/main.py and 06_files/main.py that prefers FOUNDRY_TOOLBOX_ENDPOINT but falls back to deriving the MCP URL from FOUNDRY_PROJECT_ENDPOINT + TOOLBOX_NAME — fixing the startup KeyError when agents are deployed via azd provision (which injects TOOLBOX_NAME, not FOUNDRY_TOOLBOX_ENDPOINT). - Update 04_foundry_toolbox/.env.example to use FOUNDRY_TOOLBOX_ENDPOINT (consistent with 06_files). - Add TOOLBOX_NAME env var to 06_files/agent.yaml so deployed agents have it available for the fallback derivation. - Update both READMEs to document the two ways to supply the toolbox endpoint. - Add test_foundry_namespace_no_longer_exposes_toolbox_helpers() with negative assertions for FoundryHostedToolType, get_toolbox_tool_name, get_toolbox_tool_type, and select_toolbox_tools — guarding against accidental re-introduction of removed symbols. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix(samples): fail fast on empty FOUNDRY_TOOLBOX_ENDPOINT; add unit tests Addresses review feedback for #5670: - In _resolve_toolbox_endpoint() (04_foundry_toolbox/main.py and 06_files/main.py) change the walrus-operator check from a truthy test to an explicit 'is not None' guard. An explicitly set empty string now raises ValueError immediately with a clear message instead of silently falling through to the fallback URL construction. - Add tests/samples/hosting/test_toolbox_endpoint.py covering both sample modules: (a) FOUNDRY_TOOLBOX_ENDPOINT set → returned as-is (b) FOUNDRY_TOOLBOX_ENDPOINT set to empty string → ValueError (c) fallback constructs URL from FOUNDRY_PROJECT_ENDPOINT + TOOLBOX_NAME, stripping trailing slashes (d) neither variable group set → KeyError Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address review feedback: remove extraneous test and docstring content - Remove test_foundry_namespace_no_longer_exposes_toolbox_helpers (no longer warranted) - Remove docstring from _agent.py _prepare_tools_for_openai (extraneous) - Trim _chat_client.py _prepare_tools_for_openai docstring to one-liner (toolbox references no longer relevant) Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix: remove remaining extraneous docstring from RawFoundryChatClient._prepare_tools_for_openai Address review comment on PR #5671: reviewer noted the description isn't warranted now that toolbox helpers have been removed. Matches the pattern in RawFoundryAgentChatClient which has no docstring. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <copilot@github.com> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-06-16 21:04:09 +08:00 · 2026-05-07 08:56:16 +09:00
parent 51ad460d5f
commit e56e6dad4d
26 changed files with 314 additions and 1161 deletions
@@ -20,8 +20,7 @@ from openai import OpenAI
 #   https://<your-foundry-resource>.services.ai.azure.com/api/projects/<project>/agents/<agent-name>
 ENDPOINT = os.environ.get(
    "FOUNDRY_AGENT_ENDPOINT",
-    "https://<your-foundry-resource>.services.ai.azure.com"
-    "/api/projects/<project>/agents/<agent-name>",
+    "https://<your-foundry-resource>.services.ai.azure.com/api/projects/<project>/agents/<agent-name>",
 )
 SCOPE = "https://ai.azure.com/.default"
 PROMPT = (
@@ -1,3 +1,3 @@
 FOUNDRY_PROJECT_ENDPOINT="..."
 AZURE_AI_MODEL_DEPLOYMENT_NAME="..."
-TOOLBOX_NAME="..."
+FOUNDRY_TOOLBOX_ENDPOINT="..."
@@ -14,7 +14,7 @@ You can also create a Foundry Toolbox in the Foundry portal. Read more about it

 ### Model Integration

-The agent uses `FoundryChatClient` from the Agent Framework to create an OpenAI-compatible Responses client. It loads a named Foundry Toolbox via `client.get_toolbox(name)` — the toolbox is a server-side bundle of tool configurations (e.g., `code_interpreter`, `web_search`) defined in the Foundry portal or by `azd provision`. Omitting `version` resolves the toolbox's current default version at runtime.
+The agent uses `FoundryChatClient` from the Agent Framework to create an OpenAI-compatible Responses client. It connects to the toolbox's MCP endpoint via `MCPStreamableHTTPTool`, which discovers and invokes the toolbox's tools over MCP at runtime. The endpoint URL is provided through the `FOUNDRY_TOOLBOX_ENDPOINT` environment variable.

 See [main.py](main.py) for the full implementation.

@@ -26,18 +26,29 @@ The agent is hosted using the [Agent Framework](https://github.com/microsoft/age

 Follow the instructions in the [Running the Agent Host Locally](../../README.md#running-the-agent-host-locally) section of the README in the parent directory to run the agent host.

-An extra environment variable `TOOLBOX_NAME` must be set to the name of the Foundry Toolbox that the agent should load at runtime. This allows the agent host to dynamically retrieve the correct toolbox from Foundry when it starts. Run the following:
+An extra environment variable must be set to point to the toolbox MCP endpoint. You can provide it in one of two ways:
+
+**Option A – Set `FOUNDRY_TOOLBOX_ENDPOINT` directly** (recommended for local development):

 ```bash
-export TOOLBOX_NAME="<your-toolbox-name>"
+export FOUNDRY_TOOLBOX_ENDPOINT="https://<account>.services.ai.azure.com/api/projects/<project>/toolsets/<name>/mcp?api-version=v1"
 ```

 Or in PowerShell:

 ```powershell
-$env:TOOLBOX_NAME="<your-toolbox-name>"
+$env:FOUNDRY_TOOLBOX_ENDPOINT="https://<account>.services.ai.azure.com/api/projects/<project>/toolsets/<name>/mcp?api-version=v1"
 ```

+**Option B – Set `TOOLBOX_NAME`** (used automatically by the Foundry hosting scaffolding after `azd provision`):
+
+The agent derives the endpoint at runtime as:
+```
+{FOUNDRY_PROJECT_ENDPOINT}/toolsets/{TOOLBOX_NAME}/mcp?api-version=v1
+```
+
+When deployed via `azd provision`, the scaffolding injects `TOOLBOX_NAME=agent-tools` and `FOUNDRY_PROJECT_ENDPOINT` automatically from the provisioned resources declared in [`agent.manifest.yaml`](agent.manifest.yaml).
+
 ## Interacting with the agent

 > Depending on how you run the agent host, you can invoke the agent using `curl` (`Invoke-WebRequest` in PowerShell) or `azd`. Please refer to the [parent README](../../README.md) for more details. Use this README for sample queries you can send to the agent.
@@ -2,40 +2,76 @@

 import asyncio
 import os
+from collections.abc import Callable
+from typing import Any

-from agent_framework import Agent
+from agent_framework import Agent, MCPStreamableHTTPTool
 from agent_framework.foundry import FoundryChatClient
 from agent_framework_foundry_hosting import ResponsesHostServer
-from azure.identity import DefaultAzureCredential
+from azure.core.credentials import TokenCredential
+from azure.identity import DefaultAzureCredential, get_bearer_token_provider
 from dotenv import load_dotenv

 # Load environment variables from .env file
 load_dotenv()


+def _resolve_toolbox_endpoint() -> str:
+    """Resolve the toolbox MCP endpoint URL.
+
+    Prefers the explicit ``FOUNDRY_TOOLBOX_ENDPOINT`` env var; falls back to
+    constructing the URL from ``FOUNDRY_PROJECT_ENDPOINT`` and ``TOOLBOX_NAME``
+    (the variables injected by the Foundry hosting scaffolding after ``azd provision``).
+    """
+    if (endpoint := os.environ.get("FOUNDRY_TOOLBOX_ENDPOINT")) is not None:
+        if not endpoint:
+            raise ValueError("FOUNDRY_TOOLBOX_ENDPOINT is set but empty")
+        return endpoint
+    project_endpoint = os.environ["FOUNDRY_PROJECT_ENDPOINT"].rstrip("/")
+    toolbox_name = os.environ["TOOLBOX_NAME"]
+    return f"{project_endpoint}/toolsets/{toolbox_name}/mcp?api-version=v1"
+
+
+def make_toolbox_header_provider(credential: TokenCredential) -> Callable[[dict[str, Any]], dict[str, str]]:
+    """Build a header_provider that injects a fresh Azure AI bearer token on every MCP request."""
+    get_token = get_bearer_token_provider(credential, "https://ai.azure.com/.default")
+
+    def provide(_kwargs: dict[str, Any]) -> dict[str, str]:
+        return {
+            "Authorization": f"Bearer {get_token()}",
+        }
+
+    return provide
+
+
 async def main():
+    credential = DefaultAzureCredential()
+
    client = FoundryChatClient(
        project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
        model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
-        credential=DefaultAzureCredential(),
+        credential=credential,
    )

-    # Load the named toolbox from the Foundry project. Omitting `version`
-    # resolves the toolbox's current default version at runtime.
-    toolbox = await client.get_toolbox(os.environ["TOOLBOX_NAME"])
+    toolbox_tool = MCPStreamableHTTPTool(
+        name="foundry_toolbox",
+        description="Tools exposed by the configured Foundry toolbox",
+        url=_resolve_toolbox_endpoint(),
+        header_provider=make_toolbox_header_provider(credential),
+        load_prompts=False,
+    )

-    agent = Agent(
+    async with Agent(
        client=client,
        instructions="You are a friendly assistant. Keep your answers brief.",
-        tools=toolbox,
+        tools=toolbox_tool,
        # History will be managed by the hosting infrastructure, thus there
        # is no need to store history by the service. Learn more at:
        # https://developers.openai.com/api/reference/resources/responses/methods/create
        default_options={"store": False},
-    )
-
-    server = ResponsesHostServer(agent)
-    await server.run_async()
+    ) as agent:
+        server = ResponsesHostServer(agent)
+        await server.run_async()


 if __name__ == "__main__":
@@ -1,3 +1,3 @@
 FOUNDRY_PROJECT_ENDPOINT="..."
 AZURE_AI_MODEL_DEPLOYMENT_NAME="..."
-TOOLBOX_NAME="..."
+FOUNDRY_TOOLBOX_ENDPOINT="..."
@@ -29,18 +29,29 @@ This agent uses four tools:

 Follow the instructions in the [Running the Agent Host Locally](../../README.md#running-the-agent-host-locally) section of the README in the parent directory to run the agent host.

-An extra environment variable `TOOLBOX_NAME` must be set to the name of the Foundry Toolbox that the agent should load at runtime. This allows the agent host to dynamically retrieve the correct toolbox from Foundry when it starts. Run the following:
+An extra environment variable must be set to point to the toolbox MCP endpoint. You can provide it in one of two ways:
+
+**Option A – Set `FOUNDRY_TOOLBOX_ENDPOINT` directly** (recommended for local development):

 ```bash
-export TOOLBOX_NAME="<your-toolbox-name>"
+export FOUNDRY_TOOLBOX_ENDPOINT="https://<account>.services.ai.azure.com/api/projects/<project>/toolsets/<name>/mcp?api-version=v1"
 ```

 Or in PowerShell:

 ```powershell
-$env:TOOLBOX_NAME="<your-toolbox-name>"
+$env:FOUNDRY_TOOLBOX_ENDPOINT="https://<account>.services.ai.azure.com/api/projects/<project>/toolsets/<name>/mcp?api-version=v1"
 ```

+**Option B – Set `TOOLBOX_NAME`** (used automatically by the Foundry hosting scaffolding after `azd provision`):
+
+The agent derives the endpoint at runtime as:
+```
+{FOUNDRY_PROJECT_ENDPOINT}/toolsets/{TOOLBOX_NAME}/mcp?api-version=v1
+```
+
+When deployed via `azd provision`, the scaffolding injects `TOOLBOX_NAME=agent-tools` and `FOUNDRY_PROJECT_ENDPOINT` automatically from the provisioned resources declared in [`agent.manifest.yaml`](agent.manifest.yaml).
+
 ## Interacting with the agent

 > Depending on how you run the agent host, you can invoke the agent using `curl` (`Invoke-WebRequest` in PowerShell) or `azd`. Please refer to the [parent README](../../README.md) for more details. Use this README for sample queries you can send to the agent.
@@ -9,4 +9,6 @@ resources:
  memory: '0.5Gi'
 environment_variables:
  - name: AZURE_AI_MODEL_DEPLOYMENT_NAME
-    value: ${AZURE_AI_MODEL_DEPLOYMENT_NAME}
+    value: ${AZURE_AI_MODEL_DEPLOYMENT_NAME}
+  - name: TOOLBOX_NAME
+    value: "agent-tools"
@@ -2,18 +2,48 @@

 import asyncio
 import os
+from collections.abc import Callable
+from typing import Any

-from agent_framework import Agent, tool
+from agent_framework import Agent, MCPStreamableHTTPTool, tool
 from agent_framework.foundry import FoundryChatClient
-from agent_framework_foundry import select_toolbox_tools
 from agent_framework_foundry_hosting import ResponsesHostServer
-from azure.identity import DefaultAzureCredential
+from azure.core.credentials import TokenCredential
+from azure.identity import DefaultAzureCredential, get_bearer_token_provider
 from dotenv import load_dotenv

 # Load environment variables from .env file
 load_dotenv()


+def _resolve_toolbox_endpoint() -> str:
+    """Resolve the toolbox MCP endpoint URL.
+
+    Prefers the explicit ``FOUNDRY_TOOLBOX_ENDPOINT`` env var; falls back to
+    constructing the URL from ``FOUNDRY_PROJECT_ENDPOINT`` and ``TOOLBOX_NAME``
+    (the variables injected by the Foundry hosting scaffolding after ``azd provision``).
+    """
+    if (endpoint := os.environ.get("FOUNDRY_TOOLBOX_ENDPOINT")) is not None:
+        if not endpoint:
+            raise ValueError("FOUNDRY_TOOLBOX_ENDPOINT is set but empty")
+        return endpoint
+    project_endpoint = os.environ["FOUNDRY_PROJECT_ENDPOINT"].rstrip("/")
+    toolbox_name = os.environ["TOOLBOX_NAME"]
+    return f"{project_endpoint}/toolsets/{toolbox_name}/mcp?api-version=v1"
+
+
+def make_toolbox_header_provider(credential: TokenCredential) -> Callable[[dict[str, Any]], dict[str, str]]:
+    """Build a header_provider that injects a fresh Azure AI bearer token on every MCP request."""
+    get_token = get_bearer_token_provider(credential, "https://ai.azure.com/.default")
+
+    def provide(_kwargs: dict[str, Any]) -> dict[str, str]:
+        return {
+            "Authorization": f"Bearer {get_token()}",
+        }
+
+    return provide
+
+
@tool(description="Get the current working directory.", approval_mode="never_require")
 def get_cwd() -> str:
    """Get the current working directory."""
@@ -43,40 +73,43 @@ def read_file(file_path: str) -> str:


 async def main():
+    credential = DefaultAzureCredential()
+
    client = FoundryChatClient(
        project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
        model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
-        credential=DefaultAzureCredential(),
+        credential=credential,
    )

-    # Load the named toolbox from the Foundry project. Omitting `version`
-    # resolves the toolbox's current default version at runtime.
-    toolbox = await client.get_toolbox(os.environ["TOOLBOX_NAME"])
+    # Connect to the toolbox MCP endpoint and expose only the code_interpreter tool.
    # The toolbox deployed has two tools: (see agent.manifest.yaml)
    # - `code_interpreter`
    # - `web_search`
-    # We only need the `code_interpreter` tool for this sample
-    selected_tools = select_toolbox_tools(
-        toolbox,
-        include_names=["code_interpreter"],
+    # We only need the `code_interpreter` tool for this sample.
+    toolbox_tool = MCPStreamableHTTPTool(
+        name="foundry_toolbox",
+        description="Tools exposed by the configured Foundry toolbox",
+        url=_resolve_toolbox_endpoint(),
+        header_provider=make_toolbox_header_provider(credential),
+        load_prompts=False,
+        allowed_tools=["code_interpreter"],
    )

-    agent = Agent(
+    async with Agent(
        client=client,
        instructions=(
            "You are a friendly assistant. Keep your answers brief. "
            "Make sure all mathematical calculations are performed using the code interpreter "
            "instead of mental arithmetic."
        ),
-        tools=[get_cwd, list_files, read_file] + selected_tools,
+        tools=[get_cwd, list_files, read_file, toolbox_tool],
        # History will be managed by the hosting infrastructure, thus there
        # is no need to store history by the service. Learn more at:
        # https://developers.openai.com/api/reference/resources/responses/methods/create
        default_options={"store": False},
-    )
-
-    server = ResponsesHostServer(agent)
-    await server.run_async()
+    ) as agent:
+        server = ResponsesHostServer(agent)
+        await server.run_async()


 if __name__ == "__main__":