[AI-interop] Thoughts following ADASS

Schaaff Andre andre.schaaff at astro.unistra.fr
Fri Nov 6 07:24:10 CET 2026


Hello

just for information, to prepare my short talk at IVOA i found this kind 
of things : https://pipeworx.io/registry/

it contains MCP servers for Simbad, VizieR, NASA ADS, arxiv, etc.

i checked, it's a real person but just one person

it's becoming so easy to create a piece  of code or a website to access 
our data !

in this case it's a try to make money with the work of others, see 
pricing part

regards

André


Le 06/11/2026 à 06:43, Tim Jenness via AI-interop a écrit :
> I’ve just attended ADASS and I’m currently at the IVOA meeting. I was 
> chatting with Marco about the role of the IVOA in the AI future and I 
> have some thoughts.
>
> At ADASS there were at least 3 separate presentations on MCP servers 
> that provide a way for AIs to ask about VO resources. Kelle Cruz set 
> up a Slack channel on her ORCA Slack that seems to list even more. 
> It’s clearly not worth the IVOA getting involved in MCP server 
> interface specifications but I do think there is a path forward for 
> some kind of IVOA Note about the topic.
>
> Specifically, we should look at each MCP server and see what their 
> pain points are and whether there is anything that can make the 
> implementation of these servers more straightforward. I know that the 
> NOIRLab MANNA server is having to work around bad TAP implementations, 
> but those clearly need fixing regardless of whether an AI is involved 
> or not.
>
> The other side of this is thinking how we can make it easier for an AI 
> agent to interpret the results. In many cases we do not provide enough 
> information in our TAP services for agents to be able to understand 
> whether or how flux measurements from one instrument can be compared 
> with another. It seems to me that we need to make sure that we have 
> the ability for TAP services to be able to link their results from 
> filters to filter profiles and also to give enough citation 
> information (DataOrigin per column?) to determine which algorithm was 
> used for a set of columns. Obviously TAP results with DataOrigin 
> information are more useful to an AI than those without since they can 
> download relevant description papers. It’s always been true that the 
> VO services improve the more semantic linkage there is but now AIs can 
> really make use of those linkages to improve how they use the results 
> they find.
>
> Thoughts?
>
> —
> Tim Jenness
>


More information about the AI-interop mailing list