New advertisers: 50% off your first month with code FIRSTMONTHSee slots
bitwarden avatar

bitwarden-atlassian-tools

Atlassian MCP server giving Claude Code read access to Jira, Confluence, and opt-in Jira writes.

version
2.9.1
GitHub stars
165
View on GitHub

What it does

  • Adds get_issue, search_issues, get_sprints, and get_create_fields tools for Jira, plus CQL search and page reads for Confluence
  • Includes a researching-jira-issues skill for deep issue context, a filing-jira-tickets skill, and an assessing-jira-issue-relevance skill
  • Keeps reads on by default; Jira writes such as create_issue and transition_issue refuse live execution without ATLASSIAN_JIRA_WRITE_TOKEN
  • Designed for teams that want least-privilege scoped Atlassian tokens and dry-run previews before any ticket is changed

Atlassian access via MCP server with deep Jira issue research skill, JQL search, Confluence pages, CQL search, attachments, and opt-in Jira write tools

Add marketplace

/plugin marketplace add bitwarden/ai-plugins

Run it inside Claude Code once, then install the plugin below.

Install

/plugin install bitwarden-atlassian-tools@bitwarden-marketplace

Run it inside Claude Code after adding the marketplace.

Files

Discovered from source

Assessing a Jira Issue for Relevance

Determine whether a Jira issue still applies to the current codebase. Fetch the ticket, locate the specific code path it describes, compare current behavior against the ticket's description, and return a verdict with evidence.

Workflow

Step 1: Fetch the Ticket and Its Context

Use get_issue with expand: ["renderedFields", "names"]. Extract:

  • The specific problem or task: Read beyond the summary. The description, acceptance criteria, and replication steps are more precise. For bugs: what is the actual broken behavior and what is expected? For tasks: what specific code change is required?
  • Technical identifiers: Method names, class names, file paths, API endpoint routes, UI strings that appear in source, config keys, feature flag names — anything named in the ticket that can be searched in code. Note these explicitly before moving on.
  • Filed date: Used to scope git log searches.
  • Repo scope evidence: Gather what the ticket says about where the code lives, and note how strong that evidence is. Do not settle on a repo here — Step 2 decides.
    • Strong: a literal repo name, a github.com/bitwarden/<repo> URL, or a linked PR/commit.
    • Weaker: team field, component labels, language or platform keywords, file paths in the description.

Also note these staleness signals from the ticket fields before moving on:

  • Age: How many months since the ticket was filed?
  • Priority and assignee: Is it Low/Lowest priority? Unassigned?
  • Parent epic: Does the ticket have a parent epic? If so, fetch it (get_issue) and check whether all other child tickets are resolved. A lone surviving task in an otherwise-completed epic is a strong signal that the work may have been intentionally deferred or forgotten — not that it's still needed.

After fetching the ticket, always do both of the following:

Fetch issue comments (get_issue_comments): Comments often contain decisions that never made it back into the description — root cause findings, "we decided not to fix this", priority calls, or pointers to where the fix landed. Read them before building search targets.

Fetch linked issues (get_issue_remote_links and the issuelinks field): Look specifically for blocking relationships — issues this ticket blocks or is blocked by. A ticket blocked by unresolved work may not be actionable yet; a blocker that has since been resolved may mean this ticket is now ready. Fetch (get_issue) any directly linked issues to check their current status and extract additional technical context. Do not traverse more than one level deep.

Step 2: Establish Repo Scope

Settle which repositories are in scope and confirm they are readable before searching anything. Do not begin Step 3 until all three checks below pass.

Bitwarden has many repositories — clients, server, sdk-internal, sdk-sm, android, ios, mcp-server, and others. Treat the candidate set as open; never assume a ticket must belong to one of the repos you have seen before.

1. Determine the repos.

If the ticket carries strong evidence (a literal repo name, a github.com/bitwarden/<repo> URL, or a linked PR/commit), use it and move on.

Otherwise, infer the most likely repo(s) from the weaker signals and present that inference for confirmation with AskUserQuestion. State what you inferred and the signal it rests on, offer the plausible alternatives you considered, and allow multiple selections — tickets legitimately span repos. Never search a repo the user has not confirmed.

2. Resolve each repo to a path.

Use the current working directory if it is that repo; otherwise look for a sibling directory of the same name; otherwise ask for the path. Confirm each resolved path is a real checkout:

git -C <path> rev-parse --show-toplevel

3. Verify the repo is cloned, and stop if it is not.

If a repo in scope has no checkout on disk, ask whether to clone it. On approval, clone it and continue.

If the user declines to clone, stop immediately. Return no verdict. State which repo was unavailable and that the assessment could not be completed. This halt applies even when other repos in scope are present — do not assess the available half and do not downgrade to a weaker verdict. Searching a repo that is not on disk returns no matches, which is indistinguishable from the code having been removed; proceeding would produce a confident "No longer relevant" on a ticket that is still live.

This halt is distinct from the Cannot determine verdict in Step 5. "Cannot determine" means the ticket was too vague to trace. This means the evidence was never accessible.

Step 3: Build Search Targets

From the ticket, identify 2–5 specific identifiers to search for in code. Prioritize:

  • Method or function names mentioned in the ticket (e.g., ValidateLegacyMigrationAsync, unlockViaBiometrics, validateCanManagePermission)
  • Class or component names (e.g., BaseRequestValidator, LockComponent, CollectionDialog)
  • API route strings (e.g., "trial/send-verification-email", "verify-email-token")
  • UI strings that appear in source or i18n JSON (e.g., "managePermissionRequired")
  • Config or feature flag keys (e.g., DenyLegacyUserMinimumVersion)

If the ticket names no specific identifiers, derive them from the described behavior: what function would implement this, what component would render this UI, what endpoint would serve this request?

Step 4: Search the Code

Run searches in the repo(s) confirmed in Step 2.

First, orient yourself in each repo: read its CLAUDE.md and README to find the source roots, module layout, and test locations. Do this rather than relying on remembered directory names — layouts differ per repo and change over time.

Then:

  1. Grep for each identifier in the relevant source directories. Don't stop at confirming existence — read the surrounding code to understand current behavior. A symbol that still exists but now behaves differently may mean the bug is already fixed.

  2. Read the actual implementation at each match. The grep result shows where; the file content shows what it currently does. Confirm whether the behavior the ticket describes is still present, partially changed, or gone.

  3. Check git history on affected files since the ticket was filed:

    git log --oneline --since="<filed-date>" -- <file-path>
    

    Look for commits that might have silently addressed the issue — refactors, renames, feature flag removals, component rewrites. If a commit looks relevant, read its diff on the affected lines.

  4. Trace refactored paths: If a named symbol no longer exists, find what replaced it. A deleted method does not mean the bug is fixed — the logic may have moved. Search for the behavior, not just the original name.

Step 5: Deliver Verdict

Compare what the ticket describes against what the code does today. Reach a conclusion.

Verdict options:

  • Still relevant — The described problem exists unchanged in the current code. Show the specific file:line that proves it.
  • Partially addressed — Some part of the described problem was fixed, but a gap remains. State precisely what was fixed and what remains open, with evidence for each.
  • No longer relevant — The problem no longer exists. Explain what changed and cite the current code or commit that proves it. Note whether the ticket is safe to close.
  • Technically relevant, but question whether still needed — The gap exists in code, but staleness signals are strong enough that the work should be confirmed with the reporter or PM before picking it up. Use this when multiple signals combine: ticket is significantly old (> ~9 months), unassigned, low priority, and/or is the lone surviving task in an otherwise-completed epic. State the code evidence and the staleness signals separately so the reader can weigh both.
  • Cannot determine — The ticket description is too vague to trace to specific code, and git log provides no signal. State what you searched and why it was inconclusive. Only use this after exhausting the search targets.

Format: Lead with the verdict and its justification in plain prose. Cite file:line references as evidence. If still relevant, state what specifically remains to be done — do not just restate the ticket. If staleness signals are present even for a "Still relevant" verdict, note them at the end: ticket age, epic completion state, priority, and assignee. Keep it tight; a verdict paragraph with supporting evidence is sufficient.

What NOT to Do

  • Don't traverse linked issues more than one level — fetch directly linked issues (blocks, is blocked by, parent epic) but do not follow their links further
  • Don't skip the parent epic check for task tickets — one extra get_issue call often changes the recommendation from "build this" to "confirm whether this is still wanted"
  • Don't read Confluence pages unless the ticket has no description and a Confluence link is the only available context
  • Don't return "cannot determine" without first checking both the named symbols AND git log on the relevant files
  • Don't treat "symbol still exists" as "bug still present" — read the current behavior, not just the name
  • Don't restate the ticket description as the verdict — the verdict must reflect what the code says today

Examples

examples/relevance_assessment_workflow.md

Four worked examples: a bug where the described code path was silently refactored away, a task whose implementation gap is confirmed present, a spike made obsolete by later work, and a ticket whose repo is not cloned locally, where the skill halts without a verdict.

Readme

Bitwarden Atlassian Tools

Overview

Atlassian access via a custom MCP server providing Jira issue retrieval, JQL search, Confluence page reading, CQL search, and attachment downloads.

Read access is the default and always available. Jira write access (creating work items, links, and comments, and transitioning issues) is opt-in per install: create_issue, link_issues, add_issue_comment, and transition_issue are always listed and their dry-run preview always works, but without ATLASSIAN_JIRA_WRITE_TOKEN a live write refuses to execute. Confluence remains read-only with no write path.

Installation

Configure the following environment variables:

# Required — Atlassian Cloud ID (find yours at https://bitwarden.atlassian.net/_edge/tenant_info)
export ATLASSIAN_CLOUD_ID="your-cloud-id"
export ATLASSIAN_EMAIL="your-email@company.com"
export ATLASSIAN_JIRA_READ_ONLY_TOKEN="your-jira-scoped-token"
export ATLASSIAN_CONFLUENCE_READ_ONLY_TOKEN="your-confluence-scoped-token"

# Optional — enables the Jira write tools (create_issue, link_issues, add_issue_comment, transition_issue).
# Omit to keep this install read-only.
export ATLASSIAN_JIRA_WRITE_TOKEN="your-jira-write-scoped-token"

API requests are routed through the Atlassian API gateway (api.atlassian.com), which supports both classic and scoped API tokens.

Required Atlassian Permissions

Use scoped (granular) API tokens for least-privilege access. Create them at id.atlassian.com/manage-profile/security/api-tokens. Scoped tokens require the API gateway (api.atlassian.com) and your Cloud ID.

Confluence token scopes
ScopeRequired for
read:space:confluenceSpace listing and metadata
read:space.property:confluenceSpace property access
read:page:confluencePage retrieval by ID
read:label:confluenceLabel metadata on pages
read:hierarchical-content:confluenceChild page navigation
read:folder:confluenceFolder content access
read:embed:confluenceEmbedded content rendering
read:custom-content:confluenceCustom content types
read:content.property:confluenceContent properties
read:content:confluencePages, blogposts, attachments, comments, templates
read:content-details:confluenceContent details and associated properties
read:confluence-space.summarySpace summary information
read:confluence-propsConfluence properties
read:confluence-content.summaryContent summaries
read:confluence-content.allFull content including body text
read:comment:confluencePage comments (footer and inline)
read:blogpost:confluenceBlog post content
read:attachment:confluenceAttachment metadata and downloads
read:accountUser display names on content
Jira token scopes
ScopeRequired for
read:jira-workIssues, comments, projects, attachments
read:jira-userUser display names on issues and comments

The Jira Agile (Software) endpoints behind list_boards, get_sprints, and get_sprint_issues require granular scopes — the classic read:jira-work scope does not grant access to the /rest/agile/1.0 API. Add these granular scopes to the Jira token if you use the board/sprint tools:

Granular scopeRequired for
read:board-scope:jira-softwarelist_boards
read:project:jiralist_boards (board project details)
read:sprint:jira-softwareget_sprints, get_sprint_issues
read:issue-details:jiraget_sprint_issues (issue fields)
read:jql:jiraget_sprint_issues (sprint issue lookup)

MCP Tools

Jira

ToolPurpose
get_issueRead a Jira issue by key or ID
search_issuesSearch issues using JQL
get_issue_commentsGet comments for an issue
get_issue_remote_linksGet remote links for an issue (Confluence pages, PRs, external URLs)
list_projectsList accessible Jira projects
list_boardsList Agile boards, optionally filtered by project
get_sprintsList sprints for a board (filter by active/future/closed)
get_sprint_issuesList all issues in a sprint
download_attachmentDownload a Jira attachment as Base64
get_create_fieldsReport a project's creatable issue types, and a type's create-screen fields with ids, required flags, and allowed values

Jira (write, requires ATLASSIAN_JIRA_WRITE_TOKEN)

All four tools default to a dry run that returns the exact payload without sending it. A live write requires an explicit dryRun: false. Dry runs need no write token.

ToolPurpose
create_issueCreate one work item in any project. Carries no project-specific field knowledge: pass anything beyond the common core through fields, keyed by field id from get_create_fields
link_issuesLink two work items. For a dependency, takes blockerKey and blockedKey and maps them onto Jira's inward/outward sides internally so the direction cannot be inverted
add_issue_commentAdd a comment to an existing issue. The body is markdown: emphasis, links, inline and fenced code, lists, and tables all render
transition_issueMove an issue to a status by name. Finds the transition that reaches it, does nothing if the issue is already there, and lists the reachable statuses if none does

The classic write:jira-work scope alone covers all four write tools — it grants creating and editing issues and posting comments as the user. For a scoped (granular) write token, add these instead, on top of the read scopes above:

ScopeRequired for
read:issue:jiracreate_issue
read:issue:jira-softwarecreate_issue
write:issue:jiracreate_issue, link_issues, transition_issue
write:issue:jira-softwarecreate_issue, link_issues
write:issue-link:jiralink_issues
write:comment:jiracreate_issue, link_issues (scope-only), add_issue_comment
write:comment.property:jiracreate_issue (required even though it never sends a comment)
write:attachment:jiracreate_issue (required even though it never sends an attachment)

Grant the whole set, not a subset — a token holding only some of them fails every write with 401 Unauthorized; scope does not match. For a scoped write token covering all four write tools, that's:

read:issue:jira
read:issue:jira-software
write:attachment:jira
write:comment.property:jira
write:comment:jira
write:issue-link:jira
write:issue:jira-software
write:issue:jira

get_create_fields needs no additional scope. It calls the createmeta endpoints, which the existing read-only token already satisfies.

Token scope is separate from Jira project permission. Creating also requires the Create Issues permission in the target project, linking requires Link Issues, commenting requires Add Comments, and transitioning requires Transition Issues. In a project where the user lacks Create Issues, Jira answers You cannot create issues in this project, which get_create_fields reports as an ordinary result rather than an error.

A leaked write token permits more than any one tool uses: write:comment.property:jira and write:attachment:jira are granted only because Atlassian rejects a narrower scope set, so the token can also set comment properties and add attachments across every project the user can reach, in addition to the comments add_issue_comment itself sends. Treat this token as higher-blast-radius than the read-only token and rotate it accordingly.

Confluence

ToolPurpose
get_confluence_pageRead a Confluence page by ID
get_confluence_page_commentsGet comments on a Confluence page
get_child_pagesGet child pages of a Confluence page
search_confluenceSearch Confluence by space/title
search_confluence_cqlSearch Confluence using CQL
list_spacesList accessible Confluence spaces

Usage

The MCP tools are available as mcp__bitwarden-atlassian__<tool_name>. Examples:

  • Read an issue: mcp__bitwarden-atlassian__get_issue with issueIdOrKey: "PROJ-123"
  • Search with JQL: mcp__bitwarden-atlassian__search_issues with jql: "project = PROJ AND status = Open"
  • Read a Confluence page: mcp__bitwarden-atlassian__get_confluence_page with pageId: "123456789"
  • Search Confluence: mcp__bitwarden-atlassian__search_confluence_cql with cql: "space = EN AND text ~ \"search term\""
  • Preview a ticket before creating it: mcp__bitwarden-atlassian__create_issue with project: "PM", issueType: "Story", summary: "Add CSV export to the item list" — omit dryRun (defaults to true) to get the payload back without creating anything
  • Preview a comment before posting it: mcp__bitwarden-atlassian__add_issue_comment with issueIdOrKey: "PROJ-123", body: "Looks good to me, one nit: the **guard** is inverted." — omit dryRun (defaults to true) to get the payload back without posting anything
  • Preview a status change: mcp__bitwarden-atlassian__transition_issue with issueIdOrKey: "PROJ-123", status: "In Progress" — omit dryRun (defaults to true) to see which transition would apply without moving the issue

Skills

researching-jira-issues

Orchestrates a deep read of a Jira issue by traversing linked issues, remote links, and supporting Confluence documentation, then synthesizing everything into a structured summary. Triggered by mentioning a Jira issue key with intent to understand it deeply (e.g., "Read PROJ-123", "What's blocking PROJ-123?").

Features:

  • Graph traversal with depth control (2 hops) and cycle detection
  • Custom field awareness for 16 Bitwarden-specific fields across 6 issue types
  • Next-gen epic children discovery via JQL
  • Automatic Confluence page follow-through from remote links
  • Context budget guidance and graceful degradation

filing-jira-tickets

Files Jira work items that stand on their own. Reads the target project's create screen before drafting, so no project's field layout is assumed, previews each payload before writing it, then wires and verifies dependency links. Triggered by intent to create or link tickets (e.g., "file a bug for this", "create a story for this work", "wire the blocked-by relationship").

Features:

  • Discovers issue types, required fields, and allowed values per project rather than hardcoding them, which matters because Bitwarden's projects differ (PM and SM expose an Acceptance criteria field, QA and VULN do not; VULN has no Story type; PLT's only creatable type is Platform Initiative)
  • Dry-run preview of the exact payload before every live write
  • Approval required before each create, unless explicitly told to skip it
  • Role-named link arguments (blockerKey, blockedKey) so dependency direction cannot be inverted

Live creation requires ATLASSIAN_JIRA_WRITE_TOKEN; without it the skill can still draft and preview.

Requirements

  • Claude Code with MCP support
  • Atlassian API credentials (see Installation)
  • Node.js 24+ — on first run the bundled MCP server installs and builds itself with pnpm, resolved through the npm that ships with every Node release

Details

Marketplace
bitwarden/ai-plugins
Source
plugins/bitwarden-atlassian-tools
Category
Community

More from bitwarden/ai-plugins

All 25

Similar to bitwarden-atlassian-tools

More Productivity & Planning