MCP Jira Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| JIRA_PAT | Yes | Your Jira Personal Access Token | |
| JIRA_BASE_URL | Yes | The base URL of your self-hosted Jira instance (e.g., https://jira.domain.com) | |
| JIRA_USER_AGENT | No | Optional custom User-Agent header for Jira instances behind reverse proxies (oauth2-proxy, nginx, etc.) that filter requests by User-Agent. If your API requests get redirected to SSO login despite valid PAT, your reverse proxy may require a specific User-Agent to bypass authentication for API clients. |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| jira_get_issueA | Get details of a specific Jira issue by its key (e.g., PROJ-123) |
| jira_search_issuesA | Search for Jira issues using JQL (Jira Query Language). Examples: "project = PROJ AND status = Open", "assignee = currentUser() AND status != Done" |
| jira_create_issueB | Create a new Jira issue in a specified project |
| jira_update_issueC | Update an existing Jira issue |
| jira_add_commentB | Add a comment to a Jira issue |
| jira_get_commentsB | Get all comments from a Jira issue |
| jira_get_projectsA | List all available Jira projects |
| jira_get_projectA | Get details of a specific Jira project |
| jira_get_issue_typesA | Get available issue types for a project |
| jira_assign_issueB | Assign a Jira issue to a user |
| jira_delete_issueA | Delete a Jira issue permanently |
| jira_get_current_userA | Get information about the currently authenticated 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 12 tools
Each tool targets a distinct entity or operation: get vs search vs create vs update vs delete for issues, plus separate comment, project, issue type, assignment, and user tools. The singular/plural distinction between get_project and get_projects is clear from context, and no two tools overlap in purpose.
All tools follow a consistent jira_ prefix with a verb_noun snake_case pattern (e.g., get_issue, create_issue, add_comment). The convention is predictable throughout, with no deviations.
12 tools is well-scoped for a Jira server, covering core issue CRUD, comments, projects, issue types, assignment, and user lookup without inflating the surface with redundant operations.
Core issue lifecycle (create, read, update, delete) and comment read/write are covered, but notable gaps exist for workflow transitions (changing status), attachments, issue links, and comment update/delete. These gaps are manageable for basic use but could cause failures for status-change workflows.