Natural language queries with LLMs via MCP servers

[Chenzhou Cui]

Hi. Tim, Carlo and all,

 From the side of China-VO, we have been put several MCP servers and 
Agent Skills into operation since 2024. Please visit the following links:

  * https://nadc.china-vo.org/agent-platform/
  * https://nadc.china-vo.org/ai/chat/nadc_agent_ep
  * https://nadc.china-vo.org/ai/cms/article/view?id=10&locale=en

For more information, please refer to my talk at the 2026 Spring Interop 
meeting:

  * https://wiki.ivoa.net/internal/IVOA/InterOpJun2026Apps/nadc-ai4s-framework-20260610.pptx

We are very interested in defining related specifications on the topic 
on behalf of the IVOA. A draft document will be available in the coming 
months.

Cheers,

Chenzhou


On 7/28/2026 9:07 PM, czwolf via interop wrote:
> Hi Tim, all,
>
> During the summer 2025 I set up a public MCP server (implementing the 
> Streamable http transport) to expose a SLAP2 data access service in a 
> way that LLM could extract and manipulate data.
>
> It worked just fine, but was not usable: the result from the MCP 
> response directly goes in the context window. Even flagship models 
> have a context of 1Mb and any “real” query produced so many data that 
> the context was immediately saturated.
>
> We adopted then the “skill” approach (this is what you describe as the 
> markdown giving instructions to the LLM). Check the skill folder of 
> https://github.com/VAMDC/pyVAMDC to see what we made. This approach 
> works perfectly, and we are very happy with this, but it requires a 
> sandbox so that the LLM can run system command and download files to 
> parse. This is the case for Claude, ChatGPT and we also achieved this 
> locally using open-wighted models + OpenWebUI with the OpenTerminal 
> extension.
>
> The very true force of LLM is that they can adapt even if the 
> vocabulary of each data provider is slightly different. They can cope 
> with the differences and align the sense - they do not need 
> necessarily a fixed vocabulary. But this can help.
>
> I recently participated in writing a recommendation from the Research 
> Data Alliance where we tried to define some “standard” for agentic 
> tool for research - maybe this could be useful for the IVOA community 
> too : 
> https://www.rd-alliance.org/groups/data-director-agentic-ai-blueprint/outputs/data-director-agentic-ai-tool-blueprint/
>
> All the best,
>
> Carlo.
>
>
>
>> On 27 Jul 2026, at 17:09, Tim Jenness via interop <interop at ivoa.net> 
>> wrote:
>>
>> At the recent SPIE meeting in Copenhagen, Ashley Barnes from ESO gave 
>> a talk on their experiments with teaching an LLM to query their data 
>> archive. They looked at making a dedicated agent taught explicitly 
>> but this cost them real money, and they looked at writing markdown 
>> instructions that the LLM could read to learn about the specifics of 
>> the archive center. This led me to ponder whether we should be 
>> talking about some kind of standardized MCP server interface 
>> (https://modelcontextprotocol.io/docs/getting-started/intro) that an 
>> LLM could query to work things out about the archive.
>>
>> This seems to be the way that many services are heading (my photos 
>> application has an MCP server to let an LLM look for photos 
>> efficiently). On the one hand we have all these open protocols so 
>> that in theory an LLM can work it all out and form the right query 
>> for a TAP server by querying registry and looking at TAP_SCHEMA, and 
>> that should work. MCP /might/ be able to let an agent do the same 
>> thing but using fewer tokens, even if the end point is the agent 
>> sending off a TAP query.
>>
>> Is anyone else thinking about this? Can someone from ESO ask Ashley 
>> to join IVOA Slack to discuss this?
>>
>> Each data center could put their own MCP server up with their own 
>> targeted API and that might be fine, but pooling our experience in 
>> terms of what helped and what made things worse would be really 
>> helpful and if we end up with an IVOA Note containing advice on 
>> natural language queries that would be great. If we ended up with a 
>> standardized vocabulary for MCP servers that might be even better.
>>
>> -- 
>> Tim Jenness
>> Rubin Observatory
>
-- 
===============================================================
Chenzhou Cui
National Astronomical Observatory | Tel: +86-10-64872500
Chinese Academy of Sciences       | FAX: +86-10-64888708
20A Datun Road, Chaoyang District | Email:ccz at bao.ac.cn
Beijing 100101, China             | WWW:www.lamost.org/~cb
===============================================================
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.ivoa.net/pipermail/interop/attachments/20260729/9e8a059a/attachment-0001.htm>