At Uber, we've been using GenAI to debug task failures and suggest further mitigation steps to our users. We would love to collaborate on this project and share our learnings & contribute.
On Mon, Jun 2, 2025 at 11:09 AM Amogh Desai <amoghdesai....@gmail.com> wrote: > I agree that a use case driven approach is the way to go too. > > When we go full-blown, it is easy to lose track of the intention we started > with. > > Some of the use cases related to debuggability improvements is something we > already > had a north star for in:https://github.com/apache/airflow/issues/40975, > with a good amount of > analysis already done. Maybe you can get some data here that will be > useful. > > > Thanks & Regards, > Amogh Desai > > > On Fri, May 30, 2025 at 9:27 PM Avi <a...@astronomer.io.invalid> wrote: > > > Hi All, > > > > Had a chat with @Kaxil. And we discussed on use-case first approach > rather > > than opening up to all possibilities, on building and maintaining the MCP > > server. > > > > A few use-cases which I had in mind were: > > - Debugging task failures > > - Schedule sparse across all dags for better resource utilization. > > - Recommend provider usage in place of native python codes. > > - Cross-DAG Dependency Analysis > > - Migration/Refactor Planning > > > > We would need an ongoing effort on this, as every other day something new > > comes up. Could be more optimization, or newer use-cases. We also need to > > maintain the security aspect of if. Like, where do we recommend running, > > auth and transport methods, etc. > > > > I made a new release today with FastMCP and discovery of tools based on > > category. After seeing today that FastMCP mount and sending refresh the > > tools list notification is working (*which it wasn't 3 months back*). > > > > Things I have on my roadmap: > > - HTTP based transport specifically for OAuth currently it is stdio only > > for it to be installed in a plugin (*airflow-wingman*) as a dependency. > > - Waiting for search tools to be implemented. > > - Decide to bake prompts with the server, perhaps. > > - Very minimal Docs as a resource which tells about recent changes in > > Airflow behavior (Example: *every LLM till date still tries to write > > schedule_interval instead of schedule*) > > > > @Shahar feel free to take a lead and see if there are things you would > like > > to cherry-pick from it. > > > > Thanks, > > Avi > > > > On Fri, May 30, 2025 at 9:57 AM Avi <a...@astronomer.io> wrote: > > > > > 💯 agreed > > > > > > On Fri, May 30, 2025 at 9:52 AM Kaxil Naik <kaxiln...@gmail.com> > wrote: > > > > > >> Agreed > > >> > > >> On Fri, 30 May 2025 at 15:18, Jarek Potiuk <ja...@potiuk.com> wrote: > > >> > > >> > Yeah, I think none of us want to just publish the code and be "done" > > >> with > > >> > it ... There is a real work to be done to make MCP much more useful > > and > > >> "AI > > >> > friendly" and the examples you gave Brian are cool, because I think > we > > >> need > > >> > to (and this is mostly the ask from maintainers for the users to > come > > >> and > > >> > participate in the design phase of what the MCP can do). > > >> > It looks like that "backbone" of the MCP and the glue between the > REST > > >> API > > >> > and MCP can be done in a simple (and easy to maintain) way. But the > > >> added > > >> > value is indeed in figuring out what would be useful missing things > - > > >> > starting from what broad use cases we want to address - and whether > > >> some > > >> > help for the agent can be described as prompts, better description > of > > >> the > > >> > API and examples or maybe we need more aggregated, new APIs (maybe > > >> simply > > >> > new REST API calls we need) that will allow the agents to reason > > better > > >> and > > >> > faster. All of that is possible. > > >> > > > >> > J > > >> > > > >> > On Fri, May 30, 2025 at 11:29 AM Kaxil Naik <kaxiln...@gmail.com> > > >> wrote: > > >> > > > >> > > You can easily add as many tools you want: > > >> > > https://gofastmcp.com/servers/tools > > >> > > > > >> > > I would be surprised if there is a thing you can't do with FastMCP > > >> 2.0+ > > >> > > that you can do with the MCP Python SDK. > > >> > > > > >> > > Like I said earlier: This is a simplistic example :) but the gist > is > > >> we > > >> > > should be using the newer abstractions which I am happy to comment > > >> during > > >> > > the development phase too. Like everything else we need to ensure > > >> > > maintainability is worth the value we create. > > >> > > > > >> > > > > >> > > > > >> > > On Fri, 30 May 2025 at 14:48, Kaxil Naik <kaxiln...@gmail.com> > > wrote: > > >> > > > > >> > > > Btw we don’t need to use FastMCP just for create MCP from > OpenApi > > >> spec. > > >> > > > Many of you mighht already be aware - FastMCP 1.0 was adopted in > > the > > >> > > > official mcp python sdk since 1.2 and is recommended high-level > > >> server > > >> > > > framework. > > >> > > > > > >> > > > Check: > > >> > > > > > >> > https://github.com/modelcontextprotocol/python-sdk/releases/tag/v1.2.0 > > >> > > > > > >> > > > @Bryan Coder: I will be surprised if you can’t do the use-case > you > > >> > > > mentioned with FastMCP - either the one donated to MCP Python > SDK > > or > > >> > > > FastMCP 2.0 - have you tried that? It isn’t just a wrapper! > > >> > > > > > >> > > > On Fri, 30 May 2025 at 13:16, Avi <a...@astronomer.io.invalid> > > >> wrote: > > >> > > > > > >> > > >> Yeah FastMCP is nice, I didn't select fast mcp for this > specific > > >> > reason: > > >> > > >> - The sheer number of tools that are created using OpenAPI spec > > >> > doesn't > > >> > > >> need to be passed to AI every single message. > > >> > > >> - Instead, we can do a hierarchical tool discovery based on > > >> > categories. > > >> > > >> And > > >> > > >> let AI select a particular category and then get tools only for > > >> that > > >> > > >> category. > > >> > > >> > > >> > > >> python3 -c " > > >> > > >> > import json > > >> > > >> > with open('path/to/openapi.json') as f: > > >> > > >> > spec = json.load(f) > > >> > > >> > > > >> > > >> > tags = {} > > >> > > >> > for path, methods in spec['paths'].items(): > > >> > > >> > for method, details in methods.items(): > > >> > > >> > if 'tags' in details: > > >> > > >> > for tag in details['tags']: > > >> > > >> > tags[tag] = tags.get(tag, 0) + 1 > > >> > > >> > > > >> > > >> > print('Tags and their counts:') > > >> > > >> > for tag, count in sorted(tags.items(), key=lambda x: x[1], > > >> > > >> reverse=True): > > >> > > >> > print(f'{tag}: {count}') > > >> > > >> > " > > >> > > >> Tags and their counts: > > >> > > >> Task Instance: 19 > > >> > > >> Asset: 13 > > >> > > >> Connection: 8 > > >> > > >> DagRun: 8 > > >> > > >> Backfill: 7 > > >> > > >> DAG: 7 > > >> > > >> Pool: 6 > > >> > > >> Variable: 6 > > >> > > >> XCom: 4 > > >> > > >> Config: 2 > > >> > > >> Event Log: 2 > > >> > > >> Import Error: 2 > > >> > > >> Plugin: 2 > > >> > > >> Task: 2 > > >> > > >> DagVersion: 2 > > >> > > >> Login: 2 > > >> > > >> DagSource: 1 > > >> > > >> DagStats: 1 > > >> > > >> DagReport: 1 > > >> > > >> DagWarning: 1 > > >> > > >> Extra Links: 1 > > >> > > >> Job: 1 > > >> > > >> Provider: 1 > > >> > > >> DAG Parsing: 1 > > >> > > >> Monitor: 1 > > >> > > >> Version: 1 > > >> > > >> > > >> > > >> My last attempt to do a hierarchical discovery with FastMCP > > didn't > > >> go > > >> > as > > >> > > >> expected. > > >> > > >> But this could be short term. There is something cooking in the > > >> model > > >> > > >> context protocol repo for search of a tool. Ref: > > >> > > >> > > >> https://github.com/modelcontextprotocol/modelcontextprotocol/pull/322 > > >> > > >> > > >> > > >> I'll give this a try with FastMCP to see if I can get the > > >> > > >> hierarchical discovery working. > > >> > > >> > > >> > > >> - Avi > > >> > > >> > > >> > > >> On Fri, May 30, 2025 at 1:33 AM Bryan Corder < > > >> bryancor...@gmail.com> > > >> > > >> wrote: > > >> > > >> > > >> > > >> > In order to bring value, we might want to think beyond just > > >> wrapping > > >> > > the > > >> > > >> > API. As Kaxil just showed, it's easy to create something with > > 10 > > >> > lines > > >> > > >> of > > >> > > >> > code and FastMCP. > > >> > > >> > > > >> > > >> > However, the Airflow API was made for Airflow operators' > > >> > consumption, > > >> > > >> not > > >> > > >> > necessarily for LLM consumption. When you have an endpoint > > called > > >> > > >> "Delete > > >> > > >> > DAG" with a description "Delete a specific DAG" that's very > > easy > > >> for > > >> > > any > > >> > > >> > user who has already navigated to the Airflow API spec to > > >> > understand, > > >> > > >> but > > >> > > >> > maybe not the best tool description for an LLM. I think we'd > > >> want to > > >> > > >> either > > >> > > >> > exclude that or add additional context for the LLM to know > it's > > >> > > >> > destructive. > > >> > > >> > > > >> > > >> > In addition, LLMs can struggle with tool selection when you > > give > > >> it > > >> > 80 > > >> > > >> > tools to work with. Things in the middle sometimes get lost > in > > >> the > > >> > > >> context. > > >> > > >> > There are ways to customize the FastMCP ( > > >> > > >> > https://gofastmcp.com/servers/openapi#custom-route-maps) to > > cut > > >> > down > > >> > > >> the > > >> > > >> > list of options, should you choose. > > >> > > >> > > > >> > > >> > However, it may be better to create something more tailored > to > > >> LLMs. > > >> > > >> > Thinking about the use case of getting LLM assistance with > > >> > debugging a > > >> > > >> > failed run, one of the things my teams do is put the "run > book" > > >> for > > >> > > prod > > >> > > >> > support in the doc_md notes right with the DAG, so if a file > > >> never > > >> > > >> shows up > > >> > > >> > they know exactly what to do in that situation (potentially, > do > > >> > > >> nothing). > > >> > > >> > We also include other information like, "xx task can be > flaky. > > If > > >> > you > > >> > > >> get > > >> > > >> > this error, rerunning it will usually resolve it." The goal > is > > >> for > > >> > any > > >> > > >> > engineer armed with the stack trace and the run book to be > able > > >> to > > >> > > solve > > >> > > >> > any error. My team has all that information right in the UI. > To > > >> get > > >> > > that > > >> > > >> > information, the LLM would need to know to hit the DAG > Details > > >> > > endpoint > > >> > > >> for > > >> > > >> > one minor attribute amongst several for the doc_md and get > the > > >> > correct > > >> > > >> dag > > >> > > >> > id, run id, task id and try number to grab the stack trace > from > > >> the > > >> > > >> failed > > >> > > >> > run. It would then need to go elsewhere to find the DAG code > to > > >> > > debug. I > > >> > > >> > think it would be better to just create a "debug_failed_task" > > >> tool > > >> > an > > >> > > >> LLM > > >> > > >> > could call from an MCP server that would string those calls > > >> together > > >> > > and > > >> > > >> > serve them up to the LLM on a silver platter. The LLM could > > focus > > >> > all > > >> > > >> its > > >> > > >> > "reasoning" efforts on solving the problem instead of > figuring > > >> out > > >> > how > > >> > > >> to > > >> > > >> > get the information it needs to even begin. > > >> > > >> > > > >> > > >> > Again, if we just want to wrap the API in FastMCP, we can > share > > >> > > Kaxil's > > >> > > >> 10 > > >> > > >> > lines of code in a Medium article and be done. I think the > real > > >> > value > > >> > > >> is in > > >> > > >> > providing an implementation of a limited set of more complex > > base > > >> > > tools > > >> > > >> > like debug_failed_task (described above), > pause_all_active_DAGs > > >> > > (because > > >> > > >> > I'm about to upgrade!), describe_DAG (grabs only the > > description, > > >> > > >> > dependencies, converts cron schedule to human readable if > > >> > applicable, > > >> > > >> etc) > > >> > > >> > and giving people a way to extend the server. > > >> > > >> > > > >> > > >> > The above is tool focused. As Avi pointed out, there are also > > >> > > resources > > >> > > >> and > > >> > > >> > prompts, but I've only personally worked with tools and have > > >> nothing > > >> > > to > > >> > > >> add > > >> > > >> > there. > > >> > > >> > > > >> > > >> > With all the LLM tools quickly advancing on the development > > side > > >> > (e.g. > > >> > > >> code > > >> > > >> > generation/review), it's great to see the community working > on > > >> > > building > > >> > > >> > tools to help with the operational side. > > >> > > >> > > > >> > > >> > Bryan > > >> > > >> > > > >> > > >> > > > >> > > >> > On Thu, May 29, 2025, 4:50 PM Kaxil Naik < > kaxiln...@gmail.com> > > >> > wrote: > > >> > > >> > > > >> > > >> > > One more comment: MCP SDKs have advanced quite a bit and I > > was > > >> > able > > >> > > to > > >> > > >> > get > > >> > > >> > > an Airflow MCP Server working with just the following code > > >> block. > > >> > I > > >> > > >> was > > >> > > >> > > successfully able to pause/unpause a DAG from Claude and > > other > > >> MCP > > >> > > >> client > > >> > > >> > > as an example. So as much as possible we should utilize > > higher > > >> > level > > >> > > >> > > abstraction like FastMCP which allows creating client from > > >> OpenAPI > > >> > > >> spec > > >> > > >> > > <https://gofastmcp.com/servers/openapi#openapi-integration > >: > > >> > > >> > > > > >> > > >> > > import os > > >> > > >> > > > > >> > > >> > > import httpx > > >> > > >> > > from fastmcp import FastMCP > > >> > > >> > > > > >> > > >> > > token = os.environ.get("AF_ACCESS_TOKEN") > > >> > > >> > > client = httpx.AsyncClient( > > >> > > >> > > base_url="http://localhost:28080";, > > >> > > >> > > headers={"Authorization": f"Bearer {token}"}, > > >> > > >> > > ) > > >> > > >> > > > > >> > > >> > > openapi_spec = httpx.get(" > > >> http://localhost:28080/openapi.json > > >> > > >> > ").json() > > >> > > >> > > > > >> > > >> > > mcp = FastMCP.from_openapi( > > >> > > >> > > openapi_spec=openapi_spec, > > >> > > >> > > client=client, > > >> > > >> > > name="Airflow 3.0 API Server" > > >> > > >> > > ) > > >> > > >> > > > > >> > > >> > > if __name__ == "__main__": > > >> > > >> > > mcp.run() > > >> > > >> > > > > >> > > >> > > > > >> > > >> > > > > >> > > >> > > On Thu, 29 May 2025 at 20:32, Avi > <a...@astronomer.io.invalid > > > > > >> > > wrote: > > >> > > >> > > > > >> > > >> > > > @Shahar -- Yes. Definitely. Feel free to reachout if you > > need > > >> > > >> anything. > > >> > > >> > > > > > >> > > >> > > > I totally agree, it to live as a separate repo. > > >> > > >> > > > > > >> > > >> > > > - Avi > > >> > > >> > > > > > >> > > >> > > > On Thu, May 29, 2025 at 12:50 PM Kaxil Naik < > > >> > kaxiln...@gmail.com> > > >> > > >> > wrote: > > >> > > >> > > > > > >> > > >> > > > > @Shahar -- Absolutely, I think you are driving it with > > this > > >> > > email. > > >> > > >> > So I > > >> > > >> > > > > think you can lead it from here and whoever wants to > join > > >> can > > >> > > >> co-lead > > >> > > >> > > or > > >> > > >> > > > > join in development. > > >> > > >> > > > > > > >> > > >> > > > > Please feel free to drive :) > > >> > > >> > > > > > > >> > > >> > > > > On Thu, 29 May 2025 at 17:07, Aaron Dantley < > > >> > > >> aarondant...@gmail.com> > > >> > > >> > > > > wrote: > > >> > > >> > > > > > > >> > > >> > > > > > Hey All! > > >> > > >> > > > > > > > >> > > >> > > > > > I’d be grateful to be included in the AIP discussions > > to > > >> > help > > >> > > if > > >> > > >> > > > possible > > >> > > >> > > > > > too! Like Shahar, I’ve never worked on any of these > > >> items so > > >> > > >> it’d > > >> > > >> > be > > >> > > >> > > > > great > > >> > > >> > > > > > to see how work gets assigned and goes through a > whole > > >> > > >> development > > >> > > >> > > > cycle! > > >> > > >> > > > > > > > >> > > >> > > > > > Looking forward to it! > > >> > > >> > > > > > Aaron > > >> > > >> > > > > > > > >> > > >> > > > > > On Thu, May 29, 2025 at 7:32 AM Shahar Epstein < > > >> > > >> sha...@apache.org> > > >> > > >> > > > > wrote: > > >> > > >> > > > > > > > >> > > >> > > > > > > If it's ok, I would like to lead the AIP effort (or > > at > > >> > least > > >> > > >> > > > co-lead), > > >> > > >> > > > > as > > >> > > >> > > > > > > I've never written an AIP before. I could start > > >> drafting > > >> > it > > >> > > >> > during > > >> > > >> > > > the > > >> > > >> > > > > > next > > >> > > >> > > > > > > week. > > >> > > >> > > > > > > Avi - please let me know if it works for you. > > >> > > >> > > > > > > > > >> > > >> > > > > > > > > >> > > >> > > > > > > Shahar > > >> > > >> > > > > > > > > >> > > >> > > > > > > > > >> > > >> > > > > > > On Thu, May 29, 2025, 13:09 Kaxil Naik < > > >> > kaxiln...@gmail.com > > >> > > > > > >> > > >> > > wrote: > > >> > > >> > > > > > > > > >> > > >> > > > > > > > Yes separate repo, please and we would need > someone > > >> to > > >> > > lead > > >> > > >> > this > > >> > > >> > > > > effort > > >> > > >> > > > > > > on > > >> > > >> > > > > > > > the proposal & development too. Avi - you are > > >> probably > > >> > > well > > >> > > >> > > > equipped > > >> > > >> > > > > to > > >> > > >> > > > > > > > lead it and I am sure more folks like Aaraon > would > > be > > >> > > eager > > >> > > >> to > > >> > > >> > > work > > >> > > >> > > > > on > > >> > > >> > > > > > > its > > >> > > >> > > > > > > > development and on-going maintenance. > > >> > > >> > > > > > > > > > >> > > >> > > > > > > > Regards, > > >> > > >> > > > > > > > Kaxil > > >> > > >> > > > > > > > > > >> > > >> > > > > > > > On Thu, 29 May 2025 at 15:25, Jarek Potiuk < > > >> > > >> ja...@potiuk.com> > > >> > > >> > > > wrote: > > >> > > >> > > > > > > > > > >> > > >> > > > > > > > > Yep. Having MCP is cool and drawing our > > >> implementation > > >> > > >> from > > >> > > >> > > > > > experiences > > >> > > >> > > > > > > > and > > >> > > >> > > > > > > > > usage of other MCP servers out there is even > > cooler > > >> > > >> > (especially > > >> > > >> > > > > that > > >> > > >> > > > > > we > > >> > > >> > > > > > > > can > > >> > > >> > > > > > > > > have some insights how people already use them > > with > > >> > > >> Airflow) > > >> > > >> > - > > >> > > >> > > if > > >> > > >> > > > > we > > >> > > >> > > > > > > can > > >> > > >> > > > > > > > > bring together a few of those, put some nice, > > >> relevant > > >> > > >> > Airflow > > >> > > >> > > > > > prompts. > > >> > > >> > > > > > > > > Ideally we could have some examples of how MCP > > can > > >> be > > >> > > used > > >> > > >> > > taken > > >> > > >> > > > > from > > >> > > >> > > > > > > > those > > >> > > >> > > > > > > > > who are using airflow (the debugging example by > > >> Avi is > > >> > > >> cool) > > >> > > >> > > > > > > > > > > >> > > >> > > > > > > > > I am not sure implementing it as provider is > > really > > >> > "the > > >> > > >> way" > > >> > > >> > > > > though > > >> > > >> > > > > > - > > >> > > >> > > > > > > I > > >> > > >> > > > > > > > > would rather see `apache-airflow-mcp" separate > > >> repo - > > >> > > >> it's so > > >> > > >> > > > > > different > > >> > > >> > > > > > > > and > > >> > > >> > > > > > > > > distinct from airflow it does not really > require > > >> any > > >> > of > > >> > > >> > Airflow > > >> > > >> > > > > > > internals > > >> > > >> > > > > > > > > and code to be implemented - it makes very > little > > >> > sense > > >> > > >> to be > > >> > > >> > > the > > >> > > >> > > > > > part > > >> > > >> > > > > > > of > > >> > > >> > > > > > > > > airflow "workspace" where we would develop it > > >> together > > >> > > >> with > > >> > > >> > > > > airflow - > > >> > > >> > > > > > > > > because if it will talk over the REST api, all > we > > >> need > > >> > > is > > >> > > >> the > > >> > > >> > > > > > `client` > > >> > > >> > > > > > > > that > > >> > > >> > > > > > > > > might be just a dependency. And there is even > no > > >> > reason > > >> > > >> for > > >> > > >> > MCP > > >> > > >> > > > and > > >> > > >> > > > > > > > airflow > > >> > > >> > > > > > > > > to be installed and developed together (that's > > the > > >> > main > > >> > > >> > reason > > >> > > >> > > > why > > >> > > >> > > > > we > > >> > > >> > > > > > > > want > > >> > > >> > > > > > > > > providers to be kept in monorepo. > > >> > > >> > > > > > > > > > > >> > > >> > > > > > > > > J. > > >> > > >> > > > > > > > > > > >> > > >> > > > > > > > > > > >> > > >> > > > > > > > > On Thu, May 29, 2025 at 8:37 AM Amogh Desai < > > >> > > >> > > > > > amoghdesai....@gmail.com> > > >> > > >> > > > > > > > > wrote: > > >> > > >> > > > > > > > > > > >> > > >> > > > > > > > > > Seems like a promising area to invest in > given > > >> the > > >> > > >> benefits > > >> > > >> > > it > > >> > > >> > > > > can > > >> > > >> > > > > > > > > provide > > >> > > >> > > > > > > > > > to > > >> > > >> > > > > > > > > > the users as mentioned by Shahar and > Abhishek. > > >> > > >> > > > > > > > > > > > >> > > >> > > > > > > > > > Abhishek also has a promising talk submitted > > >> which i > > >> > > am > > >> > > >> > > looking > > >> > > >> > > > > > > forward > > >> > > >> > > > > > > > > to > > >> > > >> > > > > > > > > > this year at the summit. > > >> > > >> > > > > > > > > > > > >> > > >> > > > > > > > > > In any case, this seems to be one of the > first > > of > > >> > the > > >> > > >> very > > >> > > >> > > few > > >> > > >> > > > > > > > > > implementations of trying > > >> > > >> > > > > > > > > > to integrate Airflow officially / > unofficially > > >> with > > >> > an > > >> > > >> MCP > > >> > > >> > > > > server. > > >> > > >> > > > > > > > > > > > >> > > >> > > > > > > > > > Thanks & Regards, > > >> > > >> > > > > > > > > > Amogh Desai > > >> > > >> > > > > > > > > > > > >> > > >> > > > > > > > > > > > >> > > >> > > > > > > > > > On Thu, May 29, 2025 at 2:56 AM Aaron > Dantley < > > >> > > >> > > > > > > aarondant...@gmail.com> > > >> > > >> > > > > > > > > > wrote: > > >> > > >> > > > > > > > > > > > >> > > >> > > > > > > > > > > Hey! > > >> > > >> > > > > > > > > > > > > >> > > >> > > > > > > > > > > I also think this is a great idea! > > >> > > >> > > > > > > > > > > > > >> > > >> > > > > > > > > > > Would it be possible to be included in the > > >> > > development > > >> > > >> > > > process? > > >> > > >> > > > > > > > > > > > > >> > > >> > > > > > > > > > > Sorry I’m new to this group, but would > > >> appreciate > > >> > > any > > >> > > >> > > > > suggestions > > >> > > >> > > > > > > on > > >> > > >> > > > > > > > > how > > >> > > >> > > > > > > > > > to > > >> > > >> > > > > > > > > > > contribute to the MCP server development! > > >> > > >> > > > > > > > > > > > > >> > > >> > > > > > > > > > > Regards! > > >> > > >> > > > > > > > > > > Aaron > > >> > > >> > > > > > > > > > > > > >> > > >> > > > > > > > > > > On Wed, May 28, 2025 at 2:57 PM Avi > > >> > > >> > > > <a...@astronomer.io.invalid > > >> > > >> > > > > > > > >> > > >> > > > > > > > wrote: > > >> > > >> > > > > > > > > > > > > >> > > >> > > > > > > > > > > > Nice to see the idea to incorporate an > > >> official > > >> > > MCP > > >> > > >> > > server > > >> > > >> > > > > for > > >> > > >> > > > > > > > > > > > Airflow. It's been really magical to see > > >> what a > > >> > > >> simple > > >> > > >> > > LLM > > >> > > >> > > > > can > > >> > > >> > > > > > do > > >> > > >> > > > > > > > > with > > >> > > >> > > > > > > > > > an > > >> > > >> > > > > > > > > > > > Airflow MCP server built just from APIs. > > >> > > >> > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > A few things that I noticed in my > > experience: > > >> > > >> > > > > > > > > > > > - The number of tools that the OpenAPI > spec > > >> > > >> generates > > >> > > >> > is > > >> > > >> > > > > quite > > >> > > >> > > > > > > > huge. > > >> > > >> > > > > > > > > > Most > > >> > > >> > > > > > > > > > > > tools (*Claude, VS Code with GitHub > > Copilot, > > >> > > Cursor, > > >> > > >> > > > > Windsurf*) > > >> > > >> > > > > > > > which > > >> > > >> > > > > > > > > > > uses > > >> > > >> > > > > > > > > > > > mcp-client limits it to a number of 100 > > >> tools. > > >> > > (*The > > >> > > >> > > > > read-only > > >> > > >> > > > > > > mode > > >> > > >> > > > > > > > > > > creates > > >> > > >> > > > > > > > > > > > less tools in comparison*.) > > >> > > >> > > > > > > > > > > > - MCP server are just not tools. There > are > > >> other > > >> > > >> things > > >> > > >> > > as > > >> > > >> > > > > > well, > > >> > > >> > > > > > > > like > > >> > > >> > > > > > > > > > > > resources and prompts. Prompts are super > > >> helpful > > >> > > in > > >> > > >> > case > > >> > > >> > > of > > >> > > >> > > > > > > > debugging > > >> > > >> > > > > > > > > > for > > >> > > >> > > > > > > > > > > > example. It is a way of teaching LLM > about > > >> > > Airflow. > > >> > > >> > Say I > > >> > > >> > > > > want > > >> > > >> > > > > > to > > >> > > >> > > > > > > > > have > > >> > > >> > > > > > > > > > a > > >> > > >> > > > > > > > > > > > failing task investigated. A prompt can > be > > >> > helpful > > >> > > >> in > > >> > > >> > > > letting > > >> > > >> > > > > > LLM > > >> > > >> > > > > > > > > know > > >> > > >> > > > > > > > > > a > > >> > > >> > > > > > > > > > > > step-by-step process of carrying out the > > >> > > >> investigation. > > >> > > >> > > > > > > > > > > > - Where do you run the MCP server? I > > wouldn't > > >> > want > > >> > > >> my > > >> > > >> > > > laptop > > >> > > >> > > > > to > > >> > > >> > > > > > > do > > >> > > >> > > > > > > > > the > > >> > > >> > > > > > > > > > > > heavy processing, which would want us to > go > > >> for > > >> > > the > > >> > > >> SSE > > >> > > >> > > > > instead > > >> > > >> > > > > > > of > > >> > > >> > > > > > > > > > stdio. > > >> > > >> > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > This is why I chose two different path of > > >> using > > >> > > mcp > > >> > > >> > > server > > >> > > >> > > > > with > > >> > > >> > > > > > > > > > airflow, > > >> > > >> > > > > > > > > > > > which I intend to talk about at the > summit. > > >> > > >> > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > 1. AI-Augmented Airflow - This helped me > > add > > >> a > > >> > > chat > > >> > > >> > > > interface > > >> > > >> > > > > > > > inside > > >> > > >> > > > > > > > > > > > Airflow using a plugin to talk to an > > Airflow > > >> > > >> instance > > >> > > >> > > (read > > >> > > >> > > > > > only > > >> > > >> > > > > > > > > mode). > > >> > > >> > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > 2. Airflow-Powered AI - Experimenting > with > > >> this > > >> > > has > > >> > > >> > been > > >> > > >> > > > > > totally > > >> > > >> > > > > > > > > > magical, > > >> > > >> > > > > > > > > > > > how powerful AI can become when it has > > >> access to > > >> > > >> > airflow. > > >> > > >> > > > > > Also, a > > >> > > >> > > > > > > > > > > directory > > >> > > >> > > > > > > > > > > > structure to maintain the DAGs, and it > can > > >> write > > >> > > >> DAGs > > >> > > >> > on > > >> > > >> > > > the > > >> > > >> > > > > > > fly. I > > >> > > >> > > > > > > > > > > totally > > >> > > >> > > > > > > > > > > > see a need where LLMs eventually will > need > > a > > >> > > >> scheduler, > > >> > > >> > > > > > although > > >> > > >> > > > > > > a > > >> > > >> > > > > > > > > > > complete > > >> > > >> > > > > > > > > > > > airflow just for an LLM might seem a bit > > >> > overkill > > >> > > to > > >> > > >> > the > > >> > > >> > > > rest > > >> > > >> > > > > > of > > >> > > >> > > > > > > > the > > >> > > >> > > > > > > > > > > > community. > > >> > > >> > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > I chose to build this on top of open API > is > > >> > > because > > >> > > >> > that > > >> > > >> > > > was > > >> > > >> > > > > > the > > >> > > >> > > > > > > > only > > >> > > >> > > > > > > > > > way > > >> > > >> > > > > > > > > > > > to get proper RBAC enabled. > > >> > > >> > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > I have so many points to discuss. Would > > love > > >> to > > >> > > hear > > >> > > >> > from > > >> > > >> > > > the > > >> > > >> > > > > > > > > community > > >> > > >> > > > > > > > > > > and > > >> > > >> > > > > > > > > > > > then take it forward. > > >> > > >> > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > Thanks, > > >> > > >> > > > > > > > > > > > Avi > > >> > > >> > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > On Wed, May 28, 2025 at 6:32 PM Aritra > > Basu < > > >> > > >> > > > > > > > > aritrabasu1...@gmail.com> > > >> > > >> > > > > > > > > > > > wrote: > > >> > > >> > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > I definitely think there's potential to > > >> > interact > > >> > > >> with > > >> > > >> > > an > > >> > > >> > > > > > > airflow > > >> > > >> > > > > > > > > MCP > > >> > > >> > > > > > > > > > > > > server. Though I think I'd be > interested > > to > > >> > see > > >> > > >> how > > >> > > >> > > many > > >> > > >> > > > > and > > >> > > >> > > > > > > how > > >> > > >> > > > > > > > > > > > frequently > > >> > > >> > > > > > > > > > > > > people are making use of MCP servers in > > the > > >> > wild > > >> > > >> > before > > >> > > >> > > > > > > investing > > >> > > >> > > > > > > > > > > effort > > >> > > >> > > > > > > > > > > > in > > >> > > >> > > > > > > > > > > > > building and maintaining one for > airflow. > > >> I'm > > >> > > sure > > >> > > >> > the > > >> > > >> > > > data > > >> > > >> > > > > > is > > >> > > >> > > > > > > > > > > available > > >> > > >> > > > > > > > > > > > > out there, just needs finding. > > >> > > >> > > > > > > > > > > > > -- > > >> > > >> > > > > > > > > > > > > Regards, > > >> > > >> > > > > > > > > > > > > Aritra Basu > > >> > > >> > > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > On Wed, 28 May 2025, 11:18 pm Julian > > >> LaNeve, > > >> > > >> > > > > > > > > > > > <jul...@astronomer.io.invalid > > >> > > >> > > > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > wrote: > > >> > > >> > > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > > I think this would be interesting now > > >> that > > >> > the > > >> > > >> > > > Streamable > > >> > > >> > > > > > > HTTP > > >> > > >> > > > > > > > > > spec < > > >> > > >> > > > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > >> > > >> > > > > > > > > > > > >> > > >> > > > > > > > > > > >> > > >> > > > > > > > > > >> > > >> > > > > > > > > >> > > >> > > > > > > > >> > > >> > > > > > > >> > > >> > > > > > >> > > >> > > > > >> > > >> > > > >> > > >> > > >> > > > > >> > > > >> > > > https://modelcontextprotocol.io/specification/2025-03-26/basic/transports > > >> > > >> > > > >> > > >> > > > > > > > > > > > > > is out. I think in theory we could > > >> publish > > >> > > this > > >> > > >> > first > > >> > > >> > > > as > > >> > > >> > > > > an > > >> > > >> > > > > > > > > Airflow > > >> > > >> > > > > > > > > > > > > > provider that installs a plugin to > > >> expose an > > >> > > MCP > > >> > > >> > > > > endpoint, > > >> > > >> > > > > > > as a > > >> > > >> > > > > > > > > > PoC - > > >> > > >> > > > > > > > > > > > > this > > >> > > >> > > > > > > > > > > > > > becomes a much nicer experience than > a > > >> local > > >> > > >> stdio > > >> > > >> > > one. > > >> > > >> > > > > > > > > > > > > > -- > > >> > > >> > > > > > > > > > > > > > Julian LaNeve > > >> > > >> > > > > > > > > > > > > > CTO > > >> > > >> > > > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > > Email: jul...@astronomer.io > > >> > > >> > > > > > > > > > > > > > <mailto:jul...@astronomer.io > >Mobile: > > >> 330 > > >> > 509 > > >> > > >> 5792 > > >> > > >> > > > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > > > On May 28, 2025, at 1:25 PM, Shahar > > >> > Epstein > > >> > > < > > >> > > >> > > > > > > > sha...@apache.org > > >> > > >> > > > > > > > > > > > >> > > >> > > > > > > > > > > > wrote: > > >> > > >> > > > > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > > > Dear community, > > >> > > >> > > > > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > > > Following the thread on Slack [1], > > >> > initiated > > >> > > >> by > > >> > > >> > > Jason > > >> > > >> > > > > > > > Sebastian > > >> > > >> > > > > > > > > > > > Kusuma, > > >> > > >> > > > > > > > > > > > > > I'd > > >> > > >> > > > > > > > > > > > > > > like to start an effort to > officially > > >> > > support > > >> > > >> MCP > > >> > > >> > > in > > >> > > >> > > > > > > > Airflow's > > >> > > >> > > > > > > > > > > > > codebase. > > >> > > >> > > > > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > > > *Some background * > > >> > > >> > > > > > > > > > > > > > > Model Context Protocol (MCP) is an > > open > > >> > > >> standard, > > >> > > >> > > > > > > open-source > > >> > > >> > > > > > > > > > > > framework > > >> > > >> > > > > > > > > > > > > > > that standardizes the way AI models > > >> like > > >> > LLM > > >> > > >> > > > integrate > > >> > > >> > > > > > and > > >> > > >> > > > > > > > > share > > >> > > >> > > > > > > > > > > data > > >> > > >> > > > > > > > > > > > > > with > > >> > > >> > > > > > > > > > > > > > > external tools, systems and data > > >> sources. > > >> > > >> Think > > >> > > >> > of > > >> > > >> > > it > > >> > > >> > > > > as > > >> > > >> > > > > > a > > >> > > >> > > > > > > > > "USB-C > > >> > > >> > > > > > > > > > > for > > >> > > >> > > > > > > > > > > > > > AI" - > > >> > > >> > > > > > > > > > > > > > > a universal connector that > simplifies > > >> and > > >> > > >> > > > standardizes > > >> > > >> > > > > AI > > >> > > >> > > > > > > > > > > > > integrations. A > > >> > > >> > > > > > > > > > > > > > > notable example of an MCP server is > > >> > GitHub's > > >> > > >> > > official > > >> > > >> > > > > > > > > > > implementation > > >> > > >> > > > > > > > > > > > > > [3], which > > >> > > >> > > > > > > > > > > > > > > allows LLMs such as Claude, > Copilot, > > >> and > > >> > > >> OpenAI > > >> > > >> > > (or: > > >> > > >> > > > > "MCP > > >> > > >> > > > > > > > > > clients") > > >> > > >> > > > > > > > > > > > to > > >> > > >> > > > > > > > > > > > > > > fetch pull request details, analyze > > >> code > > >> > > >> changes, > > >> > > >> > > and > > >> > > >> > > > > > > > generate > > >> > > >> > > > > > > > > > > review > > >> > > >> > > > > > > > > > > > > > > summaries. > > >> > > >> > > > > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > > > *How could an MCP server be useful > in > > >> > > >> Airflow?* > > >> > > >> > > > > > > > > > > > > > > Imagine the possibilities when LLMs > > can > > >> > > >> > seamlessly > > >> > > >> > > > > > interact > > >> > > >> > > > > > > > > with > > >> > > >> > > > > > > > > > > > > > Airflow’s > > >> > > >> > > > > > > > > > > > > > > API: triggering DAGs using natural > > >> > language, > > >> > > >> > > > retrieving > > >> > > >> > > > > > DAG > > >> > > >> > > > > > > > run > > >> > > >> > > > > > > > > > > > > history, > > >> > > >> > > > > > > > > > > > > > > enabling smart debugging, and more. > > >> This > > >> > > kind > > >> > > >> of > > >> > > >> > > > > > > integration > > >> > > >> > > > > > > > > > opens > > >> > > >> > > > > > > > > > > > the > > >> > > >> > > > > > > > > > > > > > door > > >> > > >> > > > > > > > > > > > > > > to a more intuitive, conversational > > >> > > interface > > >> > > >> for > > >> > > >> > > > > > workflow > > >> > > >> > > > > > > > > > > > > orchestration. > > >> > > >> > > > > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > > > *Why do we need to support it > > >> officially?* > > >> > > >> > > > > > > > > > > > > > > Quid pro quo - LLMs become an > > integral > > >> > part > > >> > > of > > >> > > >> > the > > >> > > >> > > > > modern > > >> > > >> > > > > > > > > > > development > > >> > > >> > > > > > > > > > > > > > > experience, while Airflow evolves > > into > > >> the > > >> > > >> go-to > > >> > > >> > > for > > >> > > >> > > > > > > > > > orchestrating > > >> > > >> > > > > > > > > > > AI > > >> > > >> > > > > > > > > > > > > > > workflows. By officially supporting > > it, > > >> > > we’ll > > >> > > >> > > enable > > >> > > >> > > > > > > multiple > > >> > > >> > > > > > > > > > users > > >> > > >> > > > > > > > > > > > to > > >> > > >> > > > > > > > > > > > > > > interact with Airflow through their > > >> LLMs, > > >> > > >> > > > streamlining > > >> > > >> > > > > > > > > automation > > >> > > >> > > > > > > > > > > and > > >> > > >> > > > > > > > > > > > > > > improving accessibility across > > diverse > > >> > > >> workflows. > > >> > > >> > > All > > >> > > >> > > > > of > > >> > > >> > > > > > > that > > >> > > >> > > > > > > > > is > > >> > > >> > > > > > > > > > > > viable > > >> > > >> > > > > > > > > > > > > > > with relatively small development > > >> effort > > >> > > (see > > >> > > >> > next > > >> > > >> > > > > > > > paragraph). > > >> > > >> > > > > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > > > *How should it be implemented?* > > >> > > >> > > > > > > > > > > > > > > As of today, there have been > several > > >> > > >> > > implementations > > >> > > >> > > > of > > >> > > >> > > > > > MCP > > >> > > >> > > > > > > > > > servers > > >> > > >> > > > > > > > > > > > for > > >> > > >> > > > > > > > > > > > > > > Airflow API, the most visible one > [4] > > >> made > > >> > > by > > >> > > >> > > > Abhishek > > >> > > >> > > > > > > Bhakat > > >> > > >> > > > > > > > > > from > > >> > > >> > > > > > > > > > > > > > > Astronomer. > > >> > > >> > > > > > > > > > > > > > > The efforts of implementing it and > > >> > > >> maintaining it > > >> > > >> > > in > > >> > > >> > > > > our > > >> > > >> > > > > > > > > codebase > > >> > > >> > > > > > > > > > > > > > shouldn't > > >> > > >> > > > > > > > > > > > > > > be too cumbersome (at least in > > >> theory), as > > >> > > we > > >> > > >> > could > > >> > > >> > > > > > utilize > > >> > > >> > > > > > > > > > > packages > > >> > > >> > > > > > > > > > > > > like > > >> > > >> > > > > > > > > > > > > > > fastmcp to auto-generate the server > > >> using > > >> > > the > > >> > > >> > > > existing > > >> > > >> > > > > > > > OpenAPI > > >> > > >> > > > > > > > > > > specs. > > >> > > >> > > > > > > > > > > > > I'd > > >> > > >> > > > > > > > > > > > > > > be very happy if Abhishek could > share > > >> his > > >> > > >> > > experience > > >> > > >> > > > in > > >> > > >> > > > > > > this > > >> > > >> > > > > > > > > > > thread. > > >> > > >> > > > > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > > > *Where else could we utilize MCP?* > > >> > > >> > > > > > > > > > > > > > > Beyond the scope of the public > API, I > > >> > could > > >> > > >> also > > >> > > >> > > > > imagine > > >> > > >> > > > > > > > using > > >> > > >> > > > > > > > > it > > >> > > >> > > > > > > > > > > to > > >> > > >> > > > > > > > > > > > > > > communicate with Breeze. > > >> > > >> > > > > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > > > *How do we proceed from here?* > > >> > > >> > > > > > > > > > > > > > > Feel free to share your thoughts > here > > >> in > > >> > > this > > >> > > >> > > > > discussion. > > >> > > >> > > > > > > > > > > > > > > If there are no objections, I'll be > > >> happy > > >> > to > > >> > > >> > start > > >> > > >> > > > > > working > > >> > > >> > > > > > > on > > >> > > >> > > > > > > > > an > > >> > > >> > > > > > > > > > > AIP. > > >> > > >> > > > > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > > > Sincerely, > > >> > > >> > > > > > > > > > > > > > > Shahar Epstein > > >> > > >> > > > > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > > > *References:* > > >> > > >> > > > > > > > > > > > > > > [1] Slack discussion, > > >> > > >> > > > > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > >> > > >> > > > > > > > > > > >> > > >> > > > > > > > > >> > > >> > > > > > > >> > > >> > > > > >> > > >> > > >> > > > https://apache-airflow.slack.com/archives/C06K9Q5G2UA/p1746121916951569 > > >> > > >> > > > > > > > > > > > > > > [2] Introducing the model context > > >> > protocol, > > >> > > >> > > > > > > > > > > > > > > > > >> > > >> > > > https://www.anthropic.com/news/model-context-protocol > > >> > > >> > > > > > > > > > > > > > > [3] GitHub Official MCP server, > > >> > > >> > > > > > > > > > > > > > > > >> https://github.com/github/github-mcp-server > > >> > > >> > > > > > > > > > > > > > > [4] Unofficial MCP Server made by > > >> Abhishek > > >> > > >> Hakat, > > >> > > >> > > > > > > > > > > > > > > > > >> > > >> > > https://github.com/abhishekbhakat/airflow-mcp-server > > >> > > >> > > > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > > >> > > >> > > > > > > > > > > > > >> > > >> > > > > > > > > > > > >> > > >> > > > > > > > > > > >> > > >> > > > > > > > > > >> > > >> > > > > > > > > >> > > >> > > > > > > > >> > > >> > > > > > > >> > > >> > > > > > >> > > >> > > > > >> > > >> > > > >> > > >> > > >> > > > > > >> > > > > >> > > > >> > > > > > >
