Jira + Confluence MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| JIRA_BASE_URL | Yes | Base URL for the internal Jira Server/Data Center instance, e.g. https://jira.sitename.ir or https://jira.sitename.ir/jira. Include any context path. | |
| CONFLUENCE_BASE_URL | Yes | Base URL for the internal Confluence Server/Data Center instance, e.g. https://confluence.sitename.ir or https://wiki.sitename.ir/confluence. Include any context path. | |
| NODE_EXTRA_CA_CERTS | No | Path to a company CA certificate PEM file when an internal server uses a private CA. TLS verification remains enabled. | |
| MCP_ALLOW_INSECURE_HTTP | No | Set to true only when the internal Jira/Confluence service is intentionally HTTP-only and the network is trusted. Defaults to false. | false |
| JIRA_PERSONAL_ACCESS_TOKEN | Yes | Personal access token for the internal Jira instance, sent as Authorization: Bearer. | |
| CONFLUENCE_PERSONAL_ACCESS_TOKEN | Yes | Personal access token for the internal Confluence instance, sent as Authorization: Bearer. |
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_get_current_userA | Return the authenticated Jira user. The Jira server and personal access token are read from this MCP process's private environment. |
| jira_search_issuesB | Search issues using Jira Query Language (JQL). Use startAt and maxResults for pagination; fields can restrict returned data. |
| jira_get_issueB | Read one issue by key or numeric ID. |
| jira_create_issueB | Create an issue. Provide Jira's fields object, including project, issuetype, and summary as required by your configuration. |
| jira_update_issueC | Update an issue's fields. Jira applies the authenticated user's permissions and workflow rules. |
| jira_delete_issueA | Permanently delete an issue. This is destructive and depends on the user's Jira permissions. |
| jira_list_projectsC | List visible Jira projects with pagination. |
| jira_add_commentB | Add a comment to an issue as the authenticated Jira user. |
| jira_list_commentsC | List comments visible to the authenticated Jira user. |
| jira_list_transitionsB | Return workflow transitions currently available for an issue. |
| jira_transition_issueA | Move an issue through a currently available workflow transition. Call jira_list_transitions first to find a valid transition ID. |
| jira_add_worklogB | Record work against an issue. Use Jira's duration syntax for timeSpent and an ISO date-time for started. |
| jira_list_boardsB | List visible Jira Software boards. Jira Software must be installed for this endpoint. |
| jira_list_sprintsC | List sprints for a Jira Software board. Optionally filter by active, future, or closed state. |
| jira_add_issue_linkB | Create an issue link. Use an issue-link type name available in your Jira instance, such as Blocks or Relates. |
| jira_restA | Call any JSON Jira Data Center REST endpoint on the configured Jira host. apiPath is relative to /rest/, for example api/2/issue/ABC-1, agile/1.0/board, or servicedeskapi/request. Supports GET, POST, PUT, PATCH, DELETE. Never put credentials in apiPath, query, or body. Write and delete calls act as the configured user. |
| confluence_get_current_userA | Return the authenticated Confluence user. |
| confluence_searchB | Search pages, blog posts, comments, and other content with Confluence Query Language (CQL). Use start and limit for pagination. |
| confluence_list_spacesB | List spaces visible to the authenticated user. Use start and limit for pagination. |
| confluence_get_pageB | Read a Confluence content item by ID, including body, version, space, and ancestors by default. |
| confluence_create_pageA | Create a page in a space. bodyStorage must be Confluence Storage Format markup, commonly HTML with Confluence macros. Optionally set parentPageId to create a child page. |
| confluence_update_pageA | Update a page's title and/or storage-format body. The server reads the current version and increments it. Set expectedVersion to prevent overwriting a page that changed since you read it. |
| confluence_delete_pageC | Delete or archive a Confluence content item according to the server's REST API and permissions. This is destructive. |
| confluence_list_commentsC | List comments on a content item. Use start and limit for pagination. |
| confluence_add_commentC | Add a comment to a Confluence content item as the authenticated user. |
| confluence_list_attachmentsC | List attachments on a Confluence content item. Use start and limit for pagination. |
| confluence_restA | Call any JSON Confluence Server/Data Center REST endpoint on the configured Confluence host. apiPath is relative to /rest/, for example api/content, api/content/123/child/attachment, or api/search. Supports GET, POST, PUT, PATCH, DELETE. Never put credentials in apiPath, query, or body. Write and delete calls act as the configured user. |
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 27 tools
Most tools target a clear resource/action pair, and the jira_/confluence_ prefixes keep domains separate. The main ambiguity is the two generic *_rest tools, which overlap with every dedicated tool, though their escape-hatch role is clearly described.
All tools use snake_case with a domain prefix and predictable verb_noun phrasing (list/get/create/update/delete/add/search). The generic REST tools are the only nonstandard action but still fit the prefix convention.
27 tools is on the heavy side, especially with generic REST catch-alls that can perform many of the same operations as dedicated tools. The dual Jira+Confluence scope makes the breadth defensible, but it is still borderline heavy.
Core issue/page CRUD, search, comments, transitions, projects, spaces, boards, sprints, worklogs, and attachments listing are covered. Gaps like comment update/delete, worklog listing/removal, issue-link removal, and attachment mutation exist but are workable through the generic REST tools.