Atlassian MCP. Run complex Jira and Confluence queries from chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Atlassian (Jira & Confluence) MCP Server. Manage projects, agile boards, and documentation directly from your AI client. Use the server to search complex Jira issues via JQL, pull full text from Confluence pages, and audit active sprints and project backlogs.
It connects your AI agent to your entire Atlassian ecosystem.
What your AI agents can do
Get issue
Retrieves the full details of a single Jira issue when given its exact key.
Get myself
Gets and returns the current authenticated user's identity information.
Get page
Fetches the complete, rich text content from a specified Confluence page.
You pass an issue key, and the server returns the full details of that specific Jira ticket.
You provide a complex JQL string, and the server returns a list of matching Jira issues.
You give the server a page identifier, and it streams the full, rendered text content of that wiki page into your chat context.
The server lists all available Jira boards and all Confluence spaces so your agent knows where to search.
You ask for active sprints on a specific board, and the server provides the list and status of the current sprint cycle.
You provide a CQL query, and the server pulls relevant documentation pages from Confluence.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Atlassian (Jira & Confluence) MCP Server: 9 Tools
These tools give your AI agent direct API access to all your Jira tickets, Confluence documentation, and project boards.
019d7554get issue
Retrieves the full details of a single Jira issue when given its exact key.
019d7554get myself
Gets and returns the current authenticated user's identity information.
019d7554get page
Fetches the complete, rich text content from a specified Confluence page.
019d7554list boards
Lists all active Jira agile boards available in your account.
019d7554list projects
Lists every project in your Jira instance, providing project keys for targeted queries.
019d7554list spaces
Lists all available Confluence spaces to narrow down content searches.
019d7554list sprints
Lists the active and historical sprints for a specified Jira board.
019d7554search content
Searches documentation across Confluence using specific CQL query syntax.
019d7554search issues
Searches Jira tickets using complex JQL query syntax.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Atlassian (Jira & Confluence), then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
This server connects your AI client directly to your whole Atlassian ecosystem. You'll use it to manage projects, run through agile boards, and pull documentation from Confluence—all without leaving your chat window.
get_issue lets you pull the full details for any single Jira issue, provided you give it the exact key. search_issues handles the heavy lifting, letting you search Jira tickets using complex JQL queries. You can also pull a list of every project available with list_projects, or find all active Jira boards using list_boards.
For Confluence, you can use list_spaces to see all available spaces before running a search. search_content pulls relevant documentation pages from Confluence when you provide a CQL query. If you know the page ID, get_page streams the complete, rich text content of that specific wiki page right into your chat.
Need to know where you are? list_sprints provides the list and status of active and historical sprints for a given Jira board. get_myself returns the current authenticated user's identity information. search_content lets you search documentation across Confluence using specific CQL query syntax.
How Atlassian MCP Works
- 1 Subscribe to the MCP Server and provide your Atlassian credentials (Domain, Email, API Token).
- 2 Your AI client sends a natural language request (e.g., 'Show me bugs in the checkout flow').
- 3 The server executes the necessary tools (
search_issuesorsearch_content) and returns the data payload to your client for a natural language summary.
The bottom line is, your AI client acts like a direct API wrapper for Atlassian, letting you run complex queries without leaving your chat window.
Who Is Atlassian MCP For?
The engineering team that spends hours clicking through Jira boards and tabs just to find a spec document. The product manager who needs to summarize a whole epic across multiple tickets. The scrum master who has to manually audit sprint blockers across three different boards.
Uses the server to pull spec documents from Confluence and trace related bugs in Jira without switching from their IDE.
Asks the agent to summarize all criteria from a whole epic, then drafts release notes based on the aggregated ticket data.
Runs audits across multiple boards to aggregate blockers and get a real-time view of project health.
What Changes When You Connect
- See the full context of a bug instantly. Instead of opening Jira and navigating to the ticket, use
get_issueto pull all details by key directly into your conversation. - Find buried documentation fast. Use
search_contentto run CQL queries against Confluence, pulling full text from documentation pages instead of relying on keyword matching. - Audit project status without clicking. Use
list_boardsandlist_sprintsto quickly map out active boards and current sprint statuses across your portfolio. - Keep your context clean. The
get_pagetool streams the full rendered text of a Confluence page, eliminating the need to copy and paste massive amounts of text. - Understand who you are.
get_myselfalways provides your current identity, which is critical when running reports or auditing permissions. - Target your search precisely. Use
search_issueswith JQL to filter tickets down to specific criteria, like 'bugs in the payment module assigned to me'.
Real-World Use Cases
Need to check the status of a bug and its requirements.
A developer needs to know the status of BUG-123 and the associated API specs. They ask the agent to use get_issue for the ticket details, and then use search_content to find the relevant 'Payment API Spec' documentation. The agent chains both tools, giving the developer a single, unified answer.
Auditing a sprint's progress and blockers.
The scrum master wants an overview of the current sprint. They ask the agent to use list_boards to find all active boards, then use list_sprints on the relevant board, and finally use search_issues to aggregate all tickets labeled 'Blocker' in that sprint.
Drafting release notes for a major project.
The product manager asks the agent to summarize the entire epic. The agent uses search_issues to pull all tickets related to the epic, then uses get_issue on each one to pull the description, compiling a draft of release notes.
Finding a guide for a niche technical problem.
A support agent is stuck on a customer call. They ask the agent to search Confluence for 'Troubleshooting Payment Gateway'. The agent uses search_content and then uses get_page on the top result, giving the support agent the full, usable text to paste into the customer reply.
The Tradeoffs
Manual dashboard hopping
A PM has to open Jira, navigate to the board, click the filter, then copy the ticket key. Then they open Confluence, search for the spec, and copy the text. It's slow and involves five different apps.
→
Ask your agent to handle the whole flow. For example, 'Find all tickets related to the Payment Gateway spec.' The agent uses search_issues (Jira) and search_content (Confluence) in one go.
Using vague search terms
Searching Jira for 'login bug' or Confluence for 'api info' only gets general results. You need to narrow the scope to get actionable data.
→
Be specific with the tools. Use search_issues and provide the full JQL. For Confluence, use search_content and include the necessary CQL syntax. This forces the agent to search the right place.
Ignoring project boundaries
Asking for 'all bugs' without specifying which project. The results will be a massive, unusable dump of data from every single project.
→
First, use list_projects to identify the project key. Then, use search_issues by adding the project key to your JQL query. This scopes the search correctly.
When It Fits, When It Doesn't
Use this server if your job requires constantly cross-referencing data between structured project tickets (Jira) and unstructured knowledge documentation (Confluence). It's for the knowledge worker who lives in the Atlassian ecosystem. Don't use it if you just need to check a single email or perform a basic CRM lookup—those are single-point tools. If your goal is purely to manage tasks in a single view, you might find a dedicated project management tool better. However, if that goal is 'Get the specs for the tasks,' this is the right fit. Always remember to use get_myself if your request depends on your current user permissions or identity.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Atlassian. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 9 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Finding documentation shouldn't require logging into three different apps.
Today, tracking down a specific API requirement means logging into Jira to find the ticket, then opening Confluence and manually searching for the corresponding spec page. You copy the ticket key, then you copy the page URL, and you spend time pasting them into your chat to ask for a summary. It's a copy-paste, multi-app headache.
With the Atlassian MCP Server, you just ask your agent: 'What are the payment requirements for ticket ABC-123?'. The agent runs `search_issues` and `search_content` simultaneously, pulling the data from both systems and giving you a single, summarized answer.
Atlassian (Jira & Confluence) MCP Server: Get project data in your chat.
You eliminate the need to manually run JQL queries on the Jira interface or spend time clicking through space lists to find the right wiki. The server handles the complex API calls for you.
It's direct. You ask for a project status, and you get the real-time, structured data payload. No more dashboard hopping.
Common Questions About Atlassian MCP
How do I use the `search_issues` tool to find a specific bug? +
You must provide a JQL query to the agent. Example: search_issues(jql='project = XYZ AND issuetype = Bug AND status = To Do'). This filters results precisely.
Does the `search_content` tool search all of my Confluence spaces? +
Yes, it searches across your defined spaces. You can start by using list_spaces to confirm the scope, but the search_content tool handles the broad query using CQL.
What is the difference between `get_issue` and `search_issues`? +
get_issue requires the exact ticket key (e.g., ABC-123). search_issues runs a query (JQL) and returns a list of matching tickets, which may include multiple results.
How can I list all my available Jira boards? +
Use the list_boards tool. This gives you an overview of all active agile boards, which is usually the first step before you can use list_sprints.
Can I find out what my user permissions are using `get_myself`? +
Yes, calling get_myself returns your current authenticated user information, which is helpful for checking identity and context before running sensitive queries.
How do I use `list_projects` to find the correct project key for a specific board? +
It first lists all available Jira projects. You use this output to get the exact project key, which you then pass to other tools like list_boards or search_issues.
What information does `get_page` retrieve from Confluence? +
It retrieves the full, rich text content of a single Confluence page. This means you get the actual text, not just a summary or title.
When should I use `list_spaces` versus `search_content`? +
Use list_spaces first to get a list of available documentation areas. Then, use search_content with CQL to narrow your search within those specific spaces.
Can my AI write JQL or CQL queries for me automatically? +
Yes. AI models are exceptionally good at transforming natural phrases like 'find all high-priority bugs open in project X' into structurally valid JQL (project = X AND priority = High AND status = Open). The same applies to CQL searches in Confluence.
How does the agent handle Confluence pages with heavy formatting or macros? +
The integration extracts the core text node data of the page. This guarantees that your AI agent only consumes dense factual text (like code snippets and bullet instructions) without wasting token context on layout elements.
Am I limited to only Jira Software or does this include Jira Service Management? +
The unified underlying Atlassian API allows JQL queries across almost all generic issue types within your authorized Domain instance. You can search bugs in Jira Software or service requests residing structurally alongside them equally.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Maxar (Satellite Imagery)
Access high-resolution satellite imagery and geospatial data from Maxar — search discovery catalogs, order data products, and retrieve streaming endpoints.
Baidu Translate / 百度翻译
China's leading machine translation service — translate text and detect languages via AI.
GitHub
Manage repositories, track issues, and search code via AI agents with GitHub.
You might also like
WhatsApp Chat Export Parser
Turn messy WhatsApp chat exports into clean, structured JSON instantly. Let your AI search years of conversations, find lost addresses, and summarize long threads local.
Casdoor (IAM)
Manage identity and access control via Casdoor — list users, manage organizations, and configure applications directly from any AI agent.
U.S. Treasury Debt — National Debt & Interest Rates
Access real-time data on the U.S. National Debt (currently $34T+). Retrieve 'Debt to the Penny', monitor average interest rates on Treasury securities, and access results from Treasury auctions.