custom-atlassian-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ATLASSIAN_SITE | Yes | Your Atlassian Cloud host (no protocol, no trailing slash) | |
| ATLASSIAN_EMAIL | Yes | Email of the account that owns the API token | |
| ATLASSIAN_API_TOKEN | Yes | API token from the Atlassian profile page |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| jira_searchA | Search Jira issues with a JQL query. Returns a compact list (key, summary, status, assignee, priority, updated). |
| jira_get_issueA | Fetch a single Jira issue by key, including description and recent comments. |
| jira_add_commentB | Add a plain-text comment to a Jira issue. |
| jira_update_issueA | Update editable fields on a Jira issue. Description is converted from plain text to ADF. |
| jira_list_sprintsA | List sprints for a Jira Software board (Agile API). Filter by state to find the active sprint. |
| jira_add_issues_to_sprintA | Move one or more issues into a sprint (Agile API). |
| jira_create_issueA | Create a new Jira issue. Description is converted from plain text to ADF. Use epicKey to link the issue to an epic (company-managed projects) or parentKey to nest it under a parent issue (team-managed projects or defect grouping). Stories and defects go in the NUTLA project; CAKE issues are Feature-type epics only. |
| jira_transition_issueA | List available transitions for an issue, or apply a transition by id or name. |
| confluence_searchA | Search Confluence content with CQL (e.g. 'space = ENG AND title ~ "onboarding"'). Returns title, space, and URL. |
| confluence_get_pageA | Fetch a Confluence page by id, including body (storage format converted to plain text). |
| confluence_create_pageA | Create a new Confluence page. Body is treated as Confluence storage-format XHTML — pass HTML-ish markup, not markdown. |
| confluence_update_pageA | Update a Confluence page. Preserves draft/current status by default; drafts stay at version 1 (Confluence constraint). Pass status='current' to publish a draft. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 12 tools
Each tool targets a distinct resource and action: Jira issues vs sprints vs comments, Confluence pages vs search. No two tools have overlapping purposes, and descriptions clarify even similar verbs like update_issue vs transition_issue.
All tools follow a consistent snake_case pattern with a domain prefix (jira_/confluence_) and verb. Minor deviations: search omits an object (e.g., jira_search vs jira_get_issue) and add_issues uses plural, but the pattern is still predictable.
12 tools is well-scoped for an Atlassian server covering Jira and Confluence. Each tool earns its place, covering search, read, create, update, and specialized actions without bloat.
Core CRUD and lifecycle operations are covered for both Jira (search, get, create, update, transition, comment, sprint management) and Confluence (search, get, create, update). Missing delete operations and project/space listing are minor gaps that agents can work around.