We would love to be able to import tableau data directly into our workflow to take action from.
We have experimented doing this via tableau’s rest API, however the data is not formatted the same way as the report views we have in tableau. This means we need to transpose the data, using many tokens for large datasets.
We also would ideally like to be able to apply filters to the report in tableau and then pull that output into Gumploop too.
Has anyone had any success doing this? OR Is there a tableau MCP on the way that will solve these issues?
Hey @Josiah! If you’re reporting an issue with a flow or an error in a run, please include the run link and make sure it’s shareable so we can take a look.
Find your run link on the history page. Format: https://www.gumloop.com/pipeline?run_id={{your_run_id}}&workbook_id={{workbook_id}}
Make it shareable by clicking “Share” → ‘Anyone with the link can view’ in the top-left corner of the flow screen.
Provide details about the issue—more context helps us troubleshoot faster.
Hey @Josiah – Since Tableau has a REST API, we can definitely add Tableau MCP to the roadmap. That said, since you mentioned using the output from the REST API directly wasn’t formatted as expected, I’m not sure if an MCP server would resolve that, since it’s essentially an LLM interacting with the API and fetching information directly. The output format wouldn’t change, but you could use an ‘Ask AI’ node alongside Tableau MCP to reformat the data.
Would something like that work for your use case, or do you have more examples? If you can share more context on how you’d expect the data to be available via the API, and how you’d want to transform it, that would help us get a better sense of what you need.
A Tableu MCP would be game changing for us, I’ve seen they recently released their own Official Tableau MCP. This would allow us to filter reports and extract specific subsets of data required in a number of our workflows.
Is this MCP something we can utilise in Gumploop today or will we need to wait for the team to build it out?
Hey @Josiah – If you check out the API output, you’ll see that it’s just a string of characters – it’s not a formatted output or an actual file object. For the file reader node to work, the file needs to be uploaded to the Gumloop workspace first via the API, or you can provide a file link directly to the file reader node.
I’m not sure what the expected output is for your API call, but if Tableau provides you with an Excel file object, you can upload it somewhere accessible – like S3 or any public storage service – and output the link. That link can then be fed into any file operation node on Gumloop. I’d recommend using the Run Code node for this.
Regarding the MCP feature for Tableau, this is something we would need to build out on our side. Technically, you can add any remote MCP server to an Ask AI node and start using it, but it doesn’t look like Tableau currently supports a remote MCP server.
