Jira MCP Server — 12 AI Tools | Claude, ChatGPT & More

Jira MCP ServerJira MCP server with 12 ready-to-use AI tools. Connect Jira to Claude, ChatGPT, Gemini, or any MCP-compatible AI assistant. Cloud MCP connector — no install, no Docker, works from any browser.Category: Developer Tools. 12 tools available. Authentication: API Key.Create, search, and update Jira tickets through conversationWhy Jira + AI?Jira is essential for tracking work, but the interface is slow for quick lookups and updates. Stop switching to Jira every time you need to check a ticket or update a sprint -- just ask your AI.Example prompts you can send your AI about Jira

Ask: "Show all bugs assigned to me that are unresolved"
AI does: AI runs a JQL query filtering by assignee, type=bug, and resolution=unresolved, returning a prioritized list.

Ask: "Create a task in PROJ: "Migrate database to PostgreSQL 16" with high priority"
AI does: AI creates the issue with the specified summary, priority, and project, returning the issue key.

Ask: "Move PROJ-789 to "Done" and add a comment about the fix"
AI does: AI fetches available transitions, moves the issue to Done, and posts the resolution comment.

Ask: "What is the sprint progress for the current sprint?"
AI does: AI lists the active sprint, shows completed vs remaining issues, and calculates the completion percentage.

Featured Jira Tools

search-issues: Search Jira issues using JQL (Jira Query Language). Returns issue key, summary, status, assignee, priority, type, labels, and created/updated timestamps for each matching issue. This is the primary tool for finding issues in Jira. WHEN TO USE: User asks "find issues", "show my tasks", "what bugs are open?", "what's in the current sprint?", "what did I work on this week?", "show unresolved issues", or any issue search/filter request. JQL CHEAT SHEET: "project = PROJ" (issues in project), "assignee = currentUser()" (my issues), "status = 'In Progress'" (by status — quote multi-word values), "issuetype = Bug AND priority >= High" (high-priority bugs), "created >= -7d" (last 7 days), "created >= -30d" (last 30 days), "sprint in openSprints()" (current sprint), "text ~ 'login error'" (full-text search), "labels = backend" (by label), "resolution = Unresolved" (open issues only), "ORDER BY priority DESC, created DESC" (sorting). CRITICAL: Multi-word status/type values MUST be quoted in JQL: status = 'In Progress' (not status = In Progress). EXAMPLES: "Show my open bugs" → jql="assignee = currentUser() AND issuetype = Bug AND resolution = Unresolved". "What's in the current sprint?" → jql="sprint in openSprints() AND status != Done ORDER BY priority DESC". "Issues created this week" → jql="project = PROJ AND created >= startOfWeek() ORDER BY created DESC".

create-issue: Create a new Jira issue in a project. Returns the new issue key (e.g., "PROJ-456") and URL. Requires: project_key, issue_type, and summary. Optional: description, priority, assignee_id, labels, parent_key. WHEN TO USE: User asks "create a ticket", "log a bug", "add a task", "create a story for...", "make a Jira issue", or any request to create/file/log an issue. ISSUE TYPES: Task (generic work), Bug (defect), Story (user story), Epic (large feature), Sub-task (child of another issue). PRIORITY VALUES: Highest, High, Medium, Low, Lowest. CRITICAL: You must know the project_key. If the user hasn't specified one, call list-projects first. CRITICAL: issue_type values are case-sensitive. Use "Bug" not "bug", "Story" not "story". EXAMPLES: "Create a bug in project DEV" → project_key="DEV", issue_type="Bug", summary="Login page returns 500 error". "Add a task and assign to me" → call get-myself first for account ID, then create-issue with assignee_id. STEP-BY-STEP for sub-tasks: 1) Create or find the parent issue, 2) create-issue with issue_type="Sub-task" and parent_key="PROJ-100".

transition-issue: Change the status of a Jira issue by performing a workflow transition (e.g., "To Do" → "In Progress" → "Done"). Returns confirmation on success. This is the ONLY way to change an issue's status in Jira. WHEN TO USE: User asks "move PROJ-123 to Done", "start working on this issue", "close this ticket", "mark as in progress", "resolve this bug", or any request to change issue status. CRITICAL: ALWAYS call get-transitions first. Transition IDs are workflow-specific and cannot be guessed. WRONG: transition-issue with transition_id="Done" (this is a status name, not a transition ID). CORRECT: get-transitions → find transition where to.name matches desired status → use that transition's id. STEP-BY-STEP: 1) get-transitions for issue_key="PROJ-123", 2) response shows [{id: "21", name: "Start Progress", to: "In Progress"}], 3) transition-issue with issue_key="PROJ-123", transition_id="21". EXAMPLE: "Close PROJ-123" → get-transitions("PROJ-123") → find "Done" transition (e.g., id="31") → transition-issue("PROJ-123", "31").

get-issue: Get full details of a specific Jira issue by its key. Returns summary, description (full text), status, assignee, reporter, priority, type, labels, components, fix versions, comments, subtasks, sprint info, and created/updated timestamps. This returns MORE detail than search-issues — use this when you need the full description, comments, or subtask list. WHEN TO USE: User asks "show me PROJ-123", "what's the description of that issue?", "who reported this bug?", "what comments are on this issue?", or when you need full details after finding an issue via search-issues. EXAMPLE: issue_key="PROJ-123" → returns full issue details including description body text and all comments. STEP-BY-STEP for issue investigation: 1) search-issues to find the issue key, 2) get-issue for full details, 3) get-comments if you need paginated comment history.

list-sprints: List sprints for a Jira Software board. Returns sprint ID, name, state (active/closed/future), start date, end date, complete date, and sprint goal for each sprint. Requires a board_id from list-boards. WHEN TO USE: User asks "what sprint are we in?", "show the current sprint", "when does the sprint end?", "list upcoming sprints", "show sprint history", or any sprint-related question. CRITICAL: You MUST call list-boards first to get the board_id. Sprint listing requires a board context. EXAMPLES: "What's the current sprint?" → state="active" (after getting board_id from list-boards). "Show upcoming sprints" → state="future". "Show completed sprints" → state="closed". STEP-BY-STEP for sprint status report: 1) list-boards to find the board_id, 2) list-sprints with state="active" to get sprint details, 3) search-issues with jql="sprint in openSprints() ORDER BY status ASC" to see all sprint issues by status.

add-comment: Add a comment to a Jira issue. Provide plain text in the body parameter — it is automatically converted to Atlassian Document Format (ADF). Returns the created comment with its ID and timestamp. WHEN TO USE: User asks "add a comment to PROJ-123", "leave a note on this issue", "comment on this ticket", "post an update to the issue", or when you need to document findings, updates, or decisions on an issue. EXAMPLE: issue_key="PROJ-123", body="Investigated and found the root cause is a missing null check in auth.ts. Fix incoming." STEP-BY-STEP for status update with comment: 1) add-comment with the update text, 2) get-transitions, 3) transition-issue to change status.

Frequently Asked Questions about JiraHow do I connect Jira to Claude or ChatGPT?Create a free LearnToSpeak.ai account, add your Jira credentials in the dashboard, and paste the generated OAuth URL into Claude.ai's custom connectors or ChatGPT's developer apps. The integration runs fully in the cloud — no desktop app, no CLI, no local install.Does it cost anything to connect Jira?The Jira integration is free during the LearnToSpeak.ai public beta. You only need a paid plan from Anthropic or OpenAI (Claude Pro/Max/Team or ChatGPT Plus/Pro/Team) since custom connectors require it on the AI provider side.Which AI assistants support the Jira connector?Claude.ai (Pro, Max, Team, Enterprise) and ChatGPT (Plus, Pro, Team) both support the Jira integration via the MCP (Model Context Protocol) standard. The same credentials work across both platforms — add the connector once, use it everywhere.How many Jira tools does my AI get access to?Your AI gets 12 ready-to-use tools for Jira, covering the most common read and write operations. Each tool is a discrete action the AI can call on demand — no multi-step prompting, no screen scraping, no workarounds.Is it safe to give an AI access to my Jira account?Yes. Your Jira credentials are encrypted at rest with AES-256-GCM and only decrypted in memory when the AI makes a request. LearnToSpeak.ai uses OAuth 2.1 with mandatory PKCE for the AI-to-platform connection, and you can revoke access instantly from the dashboard. We never store or log the actual tool responses returned to the AI.Why use LearnToSpeak.ai instead of running an MCP server locally?Cloud MCP servers work from any browser on any device — no Node.js install, no Docker, no local ports, no maintenance. Configure Jira once in the dashboard and your AI connects from claude.ai or chat.openai.com directly. That's the entire value proposition: web AI assistants don't read your filesystem, they read our servers.What is the Jira MCP server?The Jira MCP server is a cloud-hosted integration that gives AI assistants direct access to Jira through 12 tools via the Model Context Protocol (MCP) standard. It works with Claude, ChatGPT, Gemini, and any MCP-compatible AI — no local installation or Docker required.How do I connect Jira to Claude via MCP?Sign up at LearnToSpeak.ai, add your Jira credentials, and copy the generated MCP URL into Claude.ai's custom connectors (Settings → Developer → Custom Connectors). The cloud MCP server handles the connection — no CLI, no local server, no Docker.How do I connect Jira to ChatGPT via MCP?Sign up at LearnToSpeak.ai, add your Jira credentials, and copy the generated MCP URL into ChatGPT's developer apps (Settings → Apps → Advanced → Developer mode). Works with any ChatGPT Plus, Pro, or Team account.What can AI do with Jira through MCP?Jira offers 12 MCP tools covering Search issues, manage projects, track sprints, and update workflows in Jira Cloud. Ask your AI to perform any of these actions in natural language — it calls the right tool automatically.What is MCP (Model Context Protocol)?MCP is an open standard that lets AI assistants like Claude, ChatGPT, and Gemini connect directly to external apps and services. LearnToSpeak.ai hosts cloud MCP servers so you don't need to install anything locally — your AI connects from any browser.Related MCP Servers

GitHub MCP Server — 44 tools

GitLab MCP Server — 90 tools

NetBox MCP Server — 179 tools

Cisco CPNR MCP Server — 36 tools

Grafana MCP Server — 50 tools

Browse all 34 MCP servers