Agent editing Sprint field not working

[Theodore Lau]

My team is trying to get agents to help organize our Jira issues, but our biggest hurdle right now is getting the agents to be able to edit the Sprint field of our issues. We were able to find the Sprint field's custom field id and agents were able to read the field, but when they tried to edit it, they seemed to hit 400 Bad Request errors. Has anyone else tried to get agents to edit the Sprint through the MCP and/or know ways to get this to work?

[Nicola Pacini]

Hi @Theodore Lau 

did you check the custom field ID for the Sprint field? or is it a standard field? Also, you can check if the field accept value ID in input, in that case you would need the Sprint ID I guess.

[Theodore Lau]

We've found the ID for the Sprint field. It looks like its a custom field. Our agents are able to read the Sprint field perfectly fine after we explicitly give them the ID, but when they try to use editJiraIssue on specifically this field, that's when they get the 400 error.

[Nicola Pacini]

Hi @Theodore Lau 

Could you paste the error dump here? 

[Theodore Lau]

Well, I've been using the ChatGPT connector for now, so I asked it to give me what it saw:

can you give me the exact error and details you get when trying to edit the sprint field?

=====================================================

Yep — here are the exact errors + the exact payloads I tried when attempting to edit <issue>’s Sprint field (customfield_XXXXX).

Context from Jira (what Jira tells me is editable)

When I fetched <issue> with expand=editmeta, Jira returned:

Field: customfield_XXXXX

Name: Sprint

Schema:

* type: "array"

* items: "json"

* custom: "com.pyxis.greenhopper.jira:gh-sprint"

* customId: XXXXX

Operations allowed: ["set"]

Also, current value on <issue>:

Sprint id XXX, name "XXXXXXXXX", state active, boardId XX

Attempt 1 — set Sprint to a future sprint ID (numeric array)

Target sprint: id XXX (future), name “XXXXXX”
Call:

{
"fields": {
"customfield_XXXXX": [XXX]
}
}

Result (exact):

Failed to edit issue: Bad Request

Attempt 2 — set Sprint using object form

Target sprint: id XXX (future), name “XXXXXX”
Call:

{
"fields": {
"customfield_XXXXX": [{"id": XXX}]
}
}

Result (exact):

{"error":true,"message":"Failed to edit issue: Bad Request"}

Attempt 3 — set Sprint using GreenHopper sprint-string form

Target sprint: id XXX
Call:

{
"fields": {
"customfield_XXXXX": ["com.pyxis.greenhopper.jira:gh-sprint[ id=XXX ]"]
}
}

Result (exact):

{"error":true,"message":"Failed to edit issue: Bad Request"}

Attempt 4 — retry the numeric array form again

Target sprint: id XXX
Call I attempted:

{
"fields": {
"customfield_XXXXX": [XXX]
}
}

Result (exact UI/tool message):

This tool call was blocked by OpenAI's safety checks. Please double check what you are sending.

So: Jira didn’t even get this request — the MCP layer blocked it.

Net takeaway

Jira claims Sprint is editable (operations: ["set"]), but every successfully-sent edit attempt returns 400 Bad Request.

The one payload form that is most commonly correct in Jira REST ([XXX]) is currently blocked by the MCP safety layer, so I can’t validate whether Jira would accept it.

If you want, I can also paste the exact future sprint objects I’m using (id/name/state/boardId) so you can match them to what Jira UI shows.