mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00

Files

T

semenshi-m c6951c21f6 Python: Add MCP-based skills discovery (McpSkillsSource) (#6169 )

* Add MCP-based skills discovery (McpSkill, McpSkillsSource, McpSkillResource)

Implement Agent Skills discovery over MCP following the SEP-2640 convention:
- McpSkillsSource: reads skill://index.json to discover skills served by an MCP server
- McpSkill: lazily fetches SKILL.md content via resources/read on demand
- McpSkillResource: wraps MCP resource results (text and binary)
- Path traversal protection in get_resource for defense in depth
- Samples for Foundry Toolbox and standalone MCP skills server
- Comprehensive unit tests (514 lines)

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* 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>

* Restore debug logging for McpError in get_resource()

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Use AzureCliCredential in Foundry toolbox skills sample for consistency

Replace DefaultAzureCredential with AzureCliCredential to match the
credential convention used in all other samples.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Use MCPStreamableHTTPTool in MCP skills sample

Replace raw mcp library imports (ClientSession, streamable_http_client)
with the framework's MCPStreamableHTTPTool to keep MCP server connections
consistent regardless of whether skills are enabled.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Branch on McpError.error.code so only not-found errors return empty

Previously _try_read_index() and get_resource() swallowed every McpError
as 'no skills available', making auth failures, server crashes, and
connection drops indistinguishable from a server that simply has no
skills.

Now only two codes are treated as not-found:
- -32002 (MCP-spec Resource not found)
- -32601 (METHOD_NOT_FOUND — server lacks resources/read)

All other McpError codes and non-McpError exceptions propagate with a
warning log, surfacing real failures visibly.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Add tests for non-McpError and non-not-found error propagation in MCP skills

Cover the re-raise branch in MCPSkill.get_resource for plain
ConnectionError/TimeoutError, the generic McpError (code 0) propagation
on get_resource, and TimeoutError propagation in _try_read_index.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Revert "Use MCPStreamableHTTPTool in MCP skills sample"

This reverts commit f31ed0ded9.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Introduce MCP_SKILLS experimental feature for MCP skill classes

Add a separate MCP_SKILLS feature ID to ExperimentalFeature enum and
use it for MCPSkillResource, MCPSkill, and MCPSkillsSource, since their
promotion timeline is partly outside of our control.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

c6951c21f6 · 2026-06-03 18:09:50 +00:00

History

mcp_based_skill.py

Python: Add MCP-based skills discovery (McpSkillsSource) (#6169 )

2026-06-03 18:09:50 +00:00

README.md

Python: Add MCP-based skills discovery (McpSkillsSource) (#6169 )

2026-06-03 18:09:50 +00:00

README.md

MCP-Based Agent Skills Sample

This sample demonstrates how to discover Agent Skills served over MCP with an Agent.

What it demonstrates

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 skill://index.json (SEP-2640 canonical discovery) and constructs skills from the index entries.
The progressive disclosure pattern across MCP: advertise → load → read resources, exactly as for filesystem-backed skills.

Running the Sample

Prerequisites

Python 3.10+
An Azure AI Foundry project with a deployed model
Azure CLI authentication (az login)
A running MCP server that hosts SEP-2640 skill resources (see "Providing an MCP server" below)

Setup

Set the following environment variables (in a .env file or your shell):

$env:FOUNDRY_PROJECT_ENDPOINT="https://your-endpoint.services.ai.azure.com/api/projects/your-project"
$env:FOUNDRY_MODEL="gpt-4o-mini"
$env:MCP_SKILLS_SERVER_URL="https://your-mcp-server.example.com/mcp"

Run

python mcp_based_skill.py

Providing an MCP server

This sample is a consumer: it does not host an MCP server itself. To try it end-to-end you need an MCP server that exposes the SEP-2640 skill resources (skill://index.json plus per-skill SKILL.md).

See samples/02-agents/mcp/agent_as_mcp_server.py for an example of hosting an MCP server via the Agent Framework.
The Model Context Protocol working group maintains reference MCP-skills servers at modelcontextprotocol/experimental-ext-skills.