Connect Atlassian MCP to your AI agents, securely.
One secured endpoint for every Atlassian call your AI agents make, scoped per user, inspected, and logged.Try Atlassian MCP now
What your agents can ask once Atlassian MCP is connected.
“Find the Jira issues assigned to me this sprint”
“Create a Confluence page summarising this decision”
“What changed on this issue since last week?”
“Search Confluence for the onboarding runbook”
“Show the open pull requests in this Bitbucket repository”
“Who is on call right now?”
Select the tools your AI agents can call
248 tools from the Atlassian MCP schema.
Showing 248 tools
What Atlassian MCP exposes
Atlassian MCP groups its 248 tools into 12 categories, each with a suggested starting policy.
| Category | Covers | Access | Suggested policy |
|---|---|---|---|
| Confluence | Pages, blogs, spaces, comments, attachments, templates, permissions and tasks | Read / Write | Scope spaces; require approval for permission changes |
| Jira | Work items, boards, sprints, versions and projects | Read / Write | Audit changes; keep delete and manage groups disabled |
| Bitbucket | Repositories, branches, commits, pull requests, pipelines and deployments | Read / Write | Require approval for merges and pipeline runs |
| Loom | Videos and meeting recordings, transcripts, comments and reactions, folders, visibility and sharing | Read / Write | Review before changing visibility |
| Talent & Capacity | Positions, skills, headcount metrics and capacity plan allocations | Read / Write | Limit access to HR data |
| Assets | Assets objects, schemas, object types and AQL queries | Read | Limit access to intended schemas |
| Goals & Projects | Goals, projects, their updates and connections | Read / Write | Audit status updates |
| Teams & Focus | Teams, members and focus areas with their status updates | Read / Write | Limit organization access |
| Teamwork Graph | Connected context across Atlassian and third-party objects, people and work activity | Read / Write | Limit third-party data traversal |
| Common | User info, accessible sites, tool discovery and deferred execution | Read / Write | Required for every other call |
| Search | Semantic search across Atlassian, plus code search and symbol lookup | Read | Limit access to intended repositories |
| Jira Service Management | Customer requests, request types, transitions, approvals, Request Resolver plans, agent availability, operations alerts, on-call schedules and teams | Read / Write | Audit alert actions |
Connect Atlassian MCP to your AI agent
Four steps, under ten minutes.
- 01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
- 02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
- 03
Connect Atlassian
Find Atlassian in the tool list and connect it.
- 04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.
Permissions down to the single tool
You do not allow Atlassian MCP or block it. You allow the exact tools each agent can call, one by one.
| Atlassian MCP | 248 TOOLS AVAILABLE |
|---|---|
| Code review agent | 4 tools, read only |
| Issue triage bot | 9 tools |
| Platform team assistant | all 248 tools |
- Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
- Default denyA tool you have not enabled is never exposed to the agent.
- Approval on writesTools that change or delete things can require a human to confirm.
Is Atlassian MCP secure?
One endpoint instead of raw credentials. Every call is checked against policy and logged.
| AI agentsConnect through your MCP client configuration. | NeuralTrustApply controls based on your configuration. | Atlassian MCP248 documented tools. 9 more Jira tools in the delete_jira and manage_jira permission groups are disabled by default and can be enabled by an admin. |
|---|---|---|
| Coding assistants | Connection & credentialsper user | Confluence65 tools |
| Internal copilots | Tool access policiesdeny by default | Jira43 tools |
| Workflow automations | Request & response inspectioninline | Bitbucket38 tools |
| Compatible MCP clients | Activity monitoringalerts and logs | All other tools102 tools |
Use Atlassian MCP with any AI agent framework
Setup guides for the tools your team already uses.
- Claude CodeSetup guide
- CursorSetup guide
- CodexSetup guide
- WindsurfSetup guide
- Gemini CLISetup guide
- Google AntigravitySetup guide
- GitHub CopilotSetup guide
- Claude EnterpriseSetup guide
- Microsoft Copilot StudioSetup guide
- Open WebUISetup guide
- LangChainSetup guide
- HaystackSetup guide
- Strands AgentsSetup guide
- Vercel AI SDKSetup guide
- n8nSetup guide
Common questions about running Atlassian MCP through TrustGate.
Other MCP servers
More servers from the catalog.
GitHub
Securely connect your AI agents to GitHub through TrustGate: repositories, issues, pull requests, Actions, and 92 more tools, scoped per agent and logged.
96 toolsViewLinear
Securely connect your AI agents to Linear through TrustGate: issues, projects, cycles, documents and teams, scoped per agent and logged.
78 toolsViewNotion
Securely connect your AI agents to Notion through TrustGate: pages, databases, comments, files and agent sessions, scoped per agent and logged.
65 toolsView
Connect Atlassian MCP instantly
Pick the tools, point your agent at TrustGate, and Atlassian MCP is live: scoped, inspected, logged.