William Easton

Add response limiting middleware

2

### Enhancement Let's add middleware that limits the response size of tool calls, either trimming the response if it's not a structured response or just raising a tool error

ToolResult should be a Dataclass or BaseModel

1

### Enhancement ``` class ToolResult: def __init__( self, content: list[ContentBlock] | Any | None = None, structured_content: dict[str, Any] | Any | None = None, ): ``` this is annoying

Documentation for using FastMCP as an MCP Client

1

### Enhancement We should advertise FastMCP Client as a great way to add MCP tools to your existing code, chat application or AI agent framework. We should include examples use...

Document logging with OpenTelemetry

3

### Enhancement We should probably document emitting logs with OpenTelemetry, we may also be able to emit spans via middleware

As reported here: https://github.com/run-llama/llama_index/issues/19218

Table plugin lacks Markdown rendering

1

It would be very nice if the Table plugin supported rendering the table back to markdown to simplify table extraction during `markdown -> ast -> markdown` workflows. It seems like...