Address PR review comments: rename to MCP* convention, fix error handling and samples

- Rename McpSkill/McpSkillResource/McpSkillsSource to MCPSkill/MCPSkillResource/MCPSkillsSource
- Add data-URI prefix stripping for blob resource decoding
- Let non-McpError exceptions propagate from get_resource()
- Fix contradictory test comment
- Use interactive input() in mcp_based_skill sample
- Remove misleading sample output block

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
SergeyMenshykh
2026-05-29 11:23:59 +01:00
Unverified
parent b1b79d5cca
commit 6e8f7aa03f
8 changed files with 92 additions and 103 deletions
@@ -27,7 +27,7 @@ This folder contains Azure AI Foundry and Foundry Local samples for Agent Framew
| [`foundry_chat_client_with_local_mcp.py`](foundry_chat_client_with_local_mcp.py) | Foundry Chat Client with local MCP |
| [`foundry_chat_client_with_session.py`](foundry_chat_client_with_session.py) | Foundry Chat Client with session management |
| [`foundry_chat_client_with_toolbox.py`](foundry_chat_client_with_toolbox.py) | Foundry Chat Client connected to a toolbox via its MCP endpoint using `MCPStreamableHTTPTool` |
| [`foundry_chat_client_with_toolbox_skills.py`](foundry_chat_client_with_toolbox_skills.py) | Foundry Chat Client that discovers MCP-based skills from a Foundry Toolbox endpoint via `McpSkillsSource` (uses an Azure AD bearer token and the toolbox preview header) |
| [`foundry_chat_client_with_toolbox_skills.py`](foundry_chat_client_with_toolbox_skills.py) | Foundry Chat Client that discovers MCP-based skills from a Foundry Toolbox endpoint via `MCPSkillsSource` (uses an Azure AD bearer token and the toolbox preview header) |
## FoundryLocalClient Samples
@@ -5,7 +5,7 @@ import os
from collections.abc import Generator
import httpx
from agent_framework import Agent, McpSkillsSource, SkillsProvider
from agent_framework import Agent, MCPSkillsSource, SkillsProvider
from agent_framework.foundry import FoundryChatClient
from azure.core.credentials import TokenCredential
from azure.identity import DefaultAzureCredential, get_bearer_token_provider
@@ -20,7 +20,7 @@ load_dotenv()
Foundry Chat Client with Toolbox-Hosted Skills
Discover Agent Skills served by a Microsoft Foundry Toolbox MCP endpoint
and inject them into a ``FoundryChatClient`` agent via ``McpSkillsSource``.
and inject them into a ``FoundryChatClient`` agent via ``MCPSkillsSource``.
The toolbox's discovery document (``skill://index.json``) is read once at
startup; SKILL.md bodies are fetched on demand as the agent uses them.
@@ -72,11 +72,11 @@ async def main() -> None:
await session.initialize()
# Discover skills served by the toolbox and inject them as a context provider.
skills_provider = SkillsProvider(McpSkillsSource(client=session))
skills_provider = SkillsProvider(MCPSkillsSource(client=session))
async with Agent(
client=FoundryChatClient(credential=credential),
name="ToolboxMcpSkillsAgent",
name="ToolboxMCPSkillsAgent",
instructions="You are a helpful assistant. Use available skills to answer the user.",
context_providers=[skills_provider],
) as agent:
+1 -1
View File
@@ -12,7 +12,7 @@ Start with file-based or code-defined skills, then explore combining them and ad
| [**code_defined_skill**](code_defined_skill/) | Define skills entirely in Python code using `Skill`, `@skill.resource`, and `@skill.script` decorators. Uses a code-defined unit-converter skill. |
| [**class_based_skill**](class_based_skill/) | Define skills as Python classes using `ClassSkill` with `@ClassSkill.resource` and `@ClassSkill.script` decorators for auto-discovery. Uses a class-based unit-converter skill. |
| [**mixed_skills**](mixed_skills/) | Combine code-defined, class-based, and file-based skills in a single agent. Uses a code-defined volume-converter, a class-based temperature-converter, and a file-based unit-converter. |
| [**mcp_based_skill**](mcp_based_skill/) | Discover skills served over the [Model Context Protocol (MCP)](https://modelcontextprotocol.io) via `McpSkillsSource`. Connects to a remote MCP server that exposes skills as `skill://...` resources following the SEP-2640 convention. |
| [**mcp_based_skill**](mcp_based_skill/) | Discover skills served over the [Model Context Protocol (MCP)](https://modelcontextprotocol.io) via `MCPSkillsSource`. Connects to a remote MCP server that exposes skills as `skill://...` resources following the SEP-2640 convention. |
| [**script_approval**](script_approval/) | Require human-in-the-loop approval before executing skill scripts |
## Key Concepts
@@ -6,7 +6,7 @@ This sample demonstrates how to discover **Agent Skills served over MCP** with a
- Connecting to a remote MCP server (over streamable HTTP) that exposes skill
resources following the SEP-2640 convention.
- Building a `SkillsProvider` from an `McpSkillsSource`, which reads
- Building a `SkillsProvider` from an `MCPSkillsSource`, which reads
`skill://index.json` (SEP-2640 canonical discovery) and constructs skills from
the index entries.
- The progressive disclosure pattern across MCP: advertise → load → read
@@ -7,7 +7,7 @@ import os
# using the sample's Skills APIs.
# import warnings
# warnings.filterwarnings("ignore", message=r"\[SKILLS\].*", category=FutureWarning)
from agent_framework import Agent, McpSkillsSource, SkillsProvider
from agent_framework import Agent, MCPSkillsSource, SkillsProvider
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
@@ -18,7 +18,7 @@ from mcp.client.streamable_http import streamable_http_client
MCP-Based Agent Skills
This sample demonstrates how to discover Agent Skills served over the
Model Context Protocol (MCP) using :class:`McpSkillsSource`.
Model Context Protocol (MCP) using :class:`MCPSkillsSource`.
The sample connects to a remote MCP server that exposes skill resources
under the ``skill://`` URI scheme:
@@ -47,10 +47,10 @@ async def main() -> None:
await session.initialize()
# 2. Build a SkillsProvider that discovers skills over MCP.
# McpSkillsSource reads skill://index.json and creates one
# McpSkill per skill-md entry; SKILL.md bodies are fetched
# MCPSkillsSource reads skill://index.json and creates one
# MCPSkill per skill-md entry; SKILL.md bodies are fetched
# on demand via resources/read.
skills_provider = SkillsProvider(McpSkillsSource(client=session))
skills_provider = SkillsProvider(MCPSkillsSource(client=session))
# 3. Run the agent.
client = FoundryChatClient(
@@ -64,25 +64,13 @@ async def main() -> None:
instructions="You are a helpful assistant. Use available skills to answer the user.",
context_providers=[skills_provider],
) as agent:
response = await agent.run(
"What skills do you have?"
)
query = input("User: ").strip() # noqa: ASYNC250
if not query:
return
response = await agent.run(query)
print(f"Agent: {response}\n")
if __name__ == "__main__":
asyncio.run(main())
"""
Sample output:
Discovering MCP-based skills
------------------------------------------------------------
Agent: Here are your conversions:
1. **26.2 miles -> 42.16 km** (a marathon distance)
2. **75 kg -> 165.35 lbs**
Conversion factors used: miles * 1.60934 and kilograms * 2.20462.
"""