Thanks for sending this PR! Will check it later this week.

Does this actually do anything to integrate MCP resources into the agent flow? Or is it up to the implementer to retrieve resources. Seems not very useful?

Tool calls can return links to resources, it seems like it would be more useful to parse tool outputs and use the resource link to return a resource to the LLM.

https://modelcontextprotocol.io/specification/2025-06-18/server/tools#resource-links

Does this actually do anything to integrate MCP resources into the agent flow? Or is it up to the implementer to retrieve resources. Seems not very useful?

Tool calls can return links to resources, it seems like it would be more useful to parse tool outputs and use the resource link to return a resource to the LLM.

https://modelcontextprotocol.io/specification/2025-06-18/server/tools#resource-links

Hey, thanks for the question!
All of the MCP-Resource helper methods live in_MCPServerWithClientSession, so any subclass that inherits from it—MCPServerStdio,MCPServerSse, orMCPServerStreamableHttp—already gets full access in run time to:

• list_resources
• list_resource_templates
• read_resource

Does anyone know if openai plans to support resource helper methods in open ai model calls? I experimented with something like this, which findsResourceLinks in tool results and embeds the resource in the response instead

class MCPServerWithResourceLink(MCPServerStreamableHttp):    def __init__(self, *args, **kwargs):        super().__init__(*args, **kwargs)    async def call_tool(self, tool_name: str, arguments: dict[str, t.Any] | None) -> CallToolResult:        result = await super().call_tool(tool_name, arguments)        new_contents = []        for content in result.content:            match content:                case ResourceLink(                    uri=uri,                    annotations=annotations,                ):                    # Retrieve the resource and return it as an embedded resource                    resource_result = await self.read_resource(uri)                    for content in resource_result.contents:                        new_contents.append(                            EmbeddedResource(annotations=annotations, resource=content, type='resource')                        )                case _:                    new_contents.append(content)        return CallToolResult(            content=new_contents,            structuredContent=result.structuredContent,            isError=result.isError,        )

@artificial-aidan This is a fair question. At the moment, this SDK's agent mechanism does not have plans to directly utilize resources. The proposed resource support here is simply to add methods for using resources within the same code base, but it does not mean your agents can leverage them without additional code from your side.

Hi@seratch. Did you have the chance to review this PR?
Appreciate any feedback to improve.

Thanks for the reminder. As I mentioned above, this SDK does not yet have clear use cases with MCP resources, so I have to say that spending my time on this contribution is not a top priority in my task list. I’d appreciate it if you could be a bit patient until we can get back to this 🙇