Bragproof

← Reports

g-jira-mcp

Starts with no setup2.18.0npm

Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.

Needs to start: nothing
Returns a result when called with no setup: 0 of 1 tool tried
Contacts while installing and starting: nothing

28tools listed
0hosts contacted
0files written
0.1 sto start
0dependencies

Its tool definitions changed since version 2.16.0. If you approved the earlier ones, read them again.

What it contacted

Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.

Starting it

npx -y g-jira-mcp@2.18.0

Installing a package runs its code. Use a sandbox for anything you have not read.

Calling its tools

1 tool that takes no input and looks read-only was called once with nothing. 0 returned a result.

list_worklogsNo usable answer tool reported an error: Failed to parse URL from /rest/api/2/myself

During the calls it contacted nothing it had not already contacted.

Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.

What its tools tell an agent

In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.

Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.

Tools

get_ticket image_limit, include_comments, include_images, include_worklogs, ticket_id
Get full details of a Jira ticket by its key. For a single comment (a ?focusedCommentId= link), use get_comment instead.
transition_ticket status, ticket_id
Change a Jira ticket's status. Matches the transition name or its target status; common aliases (Closed/Resolved -> Done, Reopen -> Re-Open) resolve to whatever the workflow offers. Valid options vary per issue and are listed in the error when no match is found.
transition_tickets status, ticket_ids
Change the status of several Jira tickets to the same status, with the same matching as transition_ticket. Tickets are processed in order; a failure on one does not stop the rest, and the result lists each ticket's outcome.
update_ticket allow_field_loss, assignee, description, due_date, epic_key, implementation_notes, issue_type, labels, original_estimate, parent_key, priority, start_date, summary, ticket_id
Update fields of a Jira ticket. Changing issue_type to or from a sub-task type, or parent_key of an existing sub-task, goes through Jira's Move/Convert wizards; converting to a sub-task needs parent_key. It stops instead of deleting field values the new type cannot hold, unless allow_field_loss is true.
update_tickets assignee, due_date, epic_key, labels, original_estimate, priority, start_date, ticket_ids
Apply the same field values (assignee, priority, labels, dates, estimate, epic_key) to several Jira tickets. Tickets are processed in order; a failure on one does not stop the rest, and the result lists each ticket's outcome. Use update_ticket for per ticket text or type changes.
23 more tools
add_comment body, ticket_id
Add a comment to a Jira ticket
update_comment body, comment_id, ticket_id
Replace the text of an existing comment on a Jira ticket. Comment IDs are shown by get_ticket with include_comments.
delete_comment comment_id, ticket_id
Delete a comment from a Jira ticket. This cannot be undone. Comment IDs are shown by get_ticket with include_comments.
get_comment comment_id, include_images, ticket_id
Get one comment of a Jira ticket by its ID, e.g. from a ?focusedCommentId= link. Cheaper than get_ticket when only that comment matters.
search_tickets jql, max_results
Search Jira tickets using JQL query language
create_ticket assignee, body, due_date, issue_type, labels, original_estimate, parent_key, project, start_date, summary
Create a new Jira ticket
generate_release_notes fix_version, project
Generate Markdown release notes for a fix version, grouped by issue type
link_issues inward_issue, link_type, outward_issue
Create a link between two Jira tickets
link_tickets inward_issue, link_type, outward_issues
Link one Jira ticket to several others with the same link type. Links are created in order; a failure on one does not stop the rest, and the result lists each link's outcome.
unlink_issues link_type, linked_ticket_id, ticket_id
Remove a link between two Jira tickets. Direction does not matter. If several links connect them, pass link_type to pick one.
log_work activity, comment, started, ticket_id, time_spent, work_type
Log work (time) on a Jira ticket, optionally setting WorklogPRO Type of Work and Type of Activity. Check list_worklogs for that day first to avoid a duplicate.
list_worklogs date, user
List one user's worklogs on one day across all tickets (default: yours), with worklog IDs and the day's total. Call it before log_work to avoid logging the same work twice. REST cannot read WorklogPRO Type of Work/Activity, so they are not shown.
update_worklog comment, started, ticket_id, time_spent, worklog_id
Edit a worklog's time, start or comment. Worklog IDs are shown by get_ticket with include_worklogs. To change Type of Work/Activity, delete the worklog and log_work again.
delete_worklog ticket_id, worklog_id
Delete a worklog from a Jira ticket. This cannot be undone. Worklog IDs are shown by get_ticket with include_worklogs.
add_watcher ticket_id, username
Add a user as a watcher of a Jira ticket
add_watchers ticket_ids, username
Add a user as a watcher of several Jira tickets. Tickets are processed in order; a failure on one does not stop the rest, and the result lists each ticket's outcome.
remove_watcher ticket_id, username
Remove a user from the watchers of a Jira ticket
move_to_sprint sprint, ticket_ids
Move Jira tickets into an active or future sprint, by sprint name or ID
list_sprints project
List the active and future sprints of a project's scrum boards, with the IDs move_to_sprint takes
find_user max_results, query
Find Jira users by part of a username, display name or email. Returns the username that assignee and watcher fields take
add_attachment file_path, ticket_id
Upload a local file to a Jira ticket as an attachment. Embed an uploaded image in a comment or description with !filename.png!
delete_attachment attachment_id
Delete an attachment from Jira. This cannot be undone. Attachment IDs are shown by get_ticket in the Attachments line.
download_attachment attachment_id, dir
Download a Jira attachment to a local directory, saved under its Jira filename. Attachment IDs are shown by get_ticket in the Attachments line.

Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.

Install facts

LicenseMIT
Needsnot stated
Sourcegithub.com/ameforge/atlassian-mcp
Install scriptsNone declared by it or anything installed with it.
Tarballsha512-nn5Y5Em0RLCY0wd17N9BzcnEwWVCjl3vHTMPPmfujbP2mZJBu7+HuJCZ12dU4dWYOl/W+80dEQEuAQL0wdUv5g==

Versions reported

VersionRunResultTools
2.18.02026-11-16Starts with no setup28
2.16.02026-11-12Starts with no setup23

Check this report yourself

This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.

Show it on your README

Bragproof: Starts with no setup

[![Bragproof](https://bragproof.smaverk.com/badge/g-jira-mcp.svg)](https://bragproof.smaverk.com/r/g-jira-mcp)

New version out? Ask for a fresh report.