jira-confluence-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DRY_RUN | No | When set to 1, refuses all write operations (read-only mode). | 0 |
| SI_DATA_DIR | No | Directory where downloaded attachments and logs are stored. Default is ./si_data. | ./si_data |
| ALLOW_WRITES | No | When set to 0, refuses write operations even outside dry-run. | 1 |
| HTTP_TIMEOUT | No | HTTP request timeout in seconds. Default is not shown. | |
| ATLASSIAN_EMAIL | Yes | Your Atlassian account email address. | |
| HTTP_MAX_RETRIES | No | Maximum number of retries for HTTP requests with 429/5xx responses. Default is not shown. | |
| MAX_ATTACHMENT_MB | No | Maximum attachment size in megabytes to download. Default is 50. | 50 |
| ATLASSIAN_BASE_URL | Yes | The base URL of your Atlassian site, e.g. https://your-domain.atlassian.net. Automatically normalised. | |
| AUTO_DOWNLOAD_LOGS | No | When set to 1 (default), automatically downloads attachments that look like logs. | 1 |
| ATLASSIAN_API_TOKEN | Yes | Atlassian API token generated at id.atlassian.com/manage-profile/security/api-tokens. | |
| LOG_ATTACHMENT_SUFFIXES | No | Comma-separated list of file extensions considered as log attachments. Default is .log,.txt,.gz,.out,.err. | .log,.txt,.gz,.out,.err |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_ticketA | Fetch a Jira ticket (summary, description, comments, attachments, metadata). Automatically downloads log-like attachments into the shared data directory so the Log Intelligence MCP can ingest them. Set download_logs=false to skip. |
| get_attachmentA | Download a specific Jira attachment by id into the ticket's log directory. |
| search_ticketsA | Search Jira issues with JQL (e.g. to find similar historical defects). |
| post_commentA | Post a comment on a Jira ticket. Guarded by DRY_RUN / ALLOW_WRITES env vars. |
| update_ticket_fieldB | Update a single Jira field value. Guarded by DRY_RUN / ALLOW_WRITES env vars. |
| search_confluenceA | Search the Confluence knowledge base; returns ranked, normalised results. Uses CQL full-text search. Results include title, url, excerpt, and relevance score in the same shape as Jira search results. When mechanism_signal (an exception/error class or quoted error string) is supplied, hits with no token overlap against it are dropped, since a broad site search can match an unrelated write-up on topical vocabulary alone. |
| get_pageA | Fetch a Confluence page as clean plain text plus metadata (cached). |
| get_child_pagesB | List the direct child pages of a Confluence page. |
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 8 tools
Each tool has a clearly distinct purpose: Jira actions target tickets, comments, fields, and attachments, while Confluence actions target pages, child pages, and search. Overlap is minor and resolved by descriptions, such as get_ticket for whole-ticket data and get_attachment for one specific attachment.
All tools follow a consistent snake_case verb_noun pattern: get_*, search_*, post_*, update_*. There are no one-word verbs, version suffixes, or mixed conventions, making the tool set predictable.
Eight tools is well-scoped for a server spanning Jira and Confluence. Each tool serves a distinct purpose and none are redundant, keeping the surface compact while covering meaningful retrieval and update workflows.
The set supports the core investigation workflow: search and read Jira tickets, download attachments, add comments, update fields, and search/read Confluence pages. Missing issue creation, issue deletion, and Confluence write operations are notable as general CRUD gaps, but they appear to be intentionally outside the workflow described by this server.