Switches to FastMCP and adds resource support #12
Add this suggestion to a batch that can be applied as a single commit. This suggestion is invalid because no changes were made to the code. Suggestions cannot be applied while the pull request is closed. Suggestions cannot be applied while viewing a subset of changes. Only one suggestion per line can be applied in a batch. Add this suggestion to a batch that can be applied as a single commit. Applying suggestions on deleted lines is not supported. You must change the existing code in this line in order to create a valid suggestion. Outdated suggestions cannot be applied. This suggestion has been applied or marked resolved. Suggestions cannot be applied from pending reviews. Suggestions cannot be applied on multi-line comments. Suggestions cannot be applied while the pull request is queued to merge. Suggestion cannot be applied right now. Please check back later.
Hi team, super excited to be working on this with you. I apologise for the major overhaul to the code here, I understand if you are hesitant to accept it off the bat.
While I researching MCPs to figure out how to best utilise it in my workflow, I found a few good reasons for switching to the FastMCP framework. The 1.0 version of FastMCP is found in the Python
mcp
SDK, but they've continued iterating on it and just launched 2.2.0.It has a lot of helpful features around logging/error handling/resource handling that I think will help us design a really useful tool.
The brunt of this PR was doing work to replace some scripts i'd been using to download ticket information (and comments/artifacts) for the LLM to analyze.
Please let me know if you have any questions. I've only just begun implementing some early stuff, I hope to add much deeper tooling as well.
Testing instructions
Things to try asking a model connected to it
Example of it in use