Python: Add BGPT MCP sample using MCPStreamableHttpPlugin#14154
Python: Add BGPT MCP sample using MCPStreamableHttpPlugin#14154MoeenAsim wants to merge 2 commits into
Conversation
|
@MoeenAsim please read the following Contributor License Agreement(CLA). If you agree with the CLA, please reply with the following information.
Contributor License AgreementContribution License AgreementThis Contribution License Agreement (“Agreement”) is agreed to by the party signing below (“You”),
|
There was a problem hiding this comment.
Pull request overview
Adds a new Python MCP concept sample that connects Semantic Kernel agents to the BGPT hosted MCP server via MCPStreamableHttpPlugin, plus a README entry to document how to run it. This expands the MCP samples to include evidence-oriented scientific literature retrieval via a remote MCP transport.
Changes:
- Added
agent_with_bgpt_mcp_plugin.pydemonstrating BGPT MCP connection over Streamable HTTP. - Updated the MCP concepts README to include instructions for running the BGPT sample.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
| python/samples/concepts/mcp/README.md | Documents the new BGPT MCP sample and how to run it. |
| python/samples/concepts/mcp/agent_with_bgpt_mcp_plugin.py | New sample showing an agent using MCPStreamableHttpPlugin against BGPT’s hosted Streamable HTTP endpoint. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| It uses the Azure OpenAI service to create an agent. Make sure the | ||
| following environment variables are configured: | ||
|
|
||
| - AZURE_OPENAI_CHAT_DEPLOYMENT_NAME | ||
| - Optionally: AZURE_OPENAI_API_KEY | ||
|
|
||
| If no API key is configured, AzureCliCredential can also be used. | ||
| """ |
| Before running the sample, configure the required Azure OpenAI | ||
| environment variables as described in the sample file. | ||
|
|
Summary
This PR adds a new Python sample showing how to connect Semantic Kernel to the BGPT MCP server using
MCPStreamableHttpPlugin.Changes
agent_with_bgpt_mcp_plugin.pypython/samples/concepts/mcp/README.mdThe sample demonstrates how to use a remote MCP server for evidence-based scientific literature retrieval.
Fixes #14076