MCP100 Assessment

Editorial verdict

Recommended for permission-scoped Atlassian work when product access and OAuth scopes are narrow, enterprise content exposure is acceptable, and write actions require user approval.

Reviewed September 5, 2026

Task Fit

Mapped

Team productivity

Trust

Reviewed

A dated editorial review is published on the MCP detail page.

Maintenance

Date unavailable

No dated repository or package update is currently stored.

Popularity

Signals unavailable

No independently comparable adoption metric is currently stored.

Best for

Searching and summarizing Jira and Confluence knowledge
Creating and updating Jira work items or Confluence content with approval
Connecting supported AI clients to Atlassian Cloud without self-hosting a server

Not ideal for

Atlassian Server or Data Center deployments
Organizations that do not allow enterprise content to pass through an external AI client
Headless use when organization administrators do not permit API-token authentication

Avoid if

The AI client is not approved for the Jira, Confluence, Bitbucket, Compass, or connected third-party data involved
Existing Atlassian user permissions are too broad for agent use
Write and bulk actions cannot require review

Trade-offs

The hosted service honors existing product permissions and provides audit events, but it can expose broad enterprise knowledge to the connected AI client.
OAuth 2.1 is recommended; API tokens support headless workflows but require admin enablement and careful scope management.
Some Teamwork Graph and search tools are Beta and may later consume paid Rovo credits.
Rovo MCP v2 adds additional supported Atlassian apps through a documented upgrade path; v1 remains documented and is not described as shut down.

Evidence scope

Evidence

Current source snapshot

Popularity

No MCP-specific repository metric is stored

No MCP-specific package metric is stored

Stars observation date unavailable · Downloads observation date unavailable

Hosted MCP/service has no reviewed public MCP-specific repository metric; do not substitute parent-product or sibling implementation stars.

Hosted MCP/service has no reviewed comparable public MCP-specific package-download metric.

Maintenance

Publisher activity observed September 24, 2026

Current source snapshot

Trust review

Source relationship: First-party MCP

Reviewed September 5, 2026

Sources

Official setup docs ↗

Supporting evidence (1)

Evidence source ↗

Evidence-backed setup

Install & Agents

Choose your MCP client. A client connects to the MCP server; the language model is selected inside that client. Only stored, source-backed configurations are shown.

Claude Code

Streamable HTTP

MCP100 logic checked

claude mcp add --transport http atlassian "https://mcp.atlassian.com/v1/mcp"

The publisher connection details were combined with this client's official MCP transport configuration; installation was not executed by MCP100.

Verify safely: Reconnect Claude Code, complete the publisher OAuth or authentication flow if prompted, confirm atlassian tools are listed, and perform one read-only test.

Uninstall and revoke

Remove atlassian from Claude Code, clear its stored MCP OAuth credentials, and revoke the publisher authorization if it is no longer needed.

Evidence & methodology

Publisher-documented setup is not the same as MCP100 execution testing. “MCP100 logic checked” means the stored configuration shape was reviewed, not that third-party MCP software was run.

Evidence checked 2026-07-24

Evidence 1 ↗Evidence 2 ↗

Show source-catalog configuration

{"mcpServers":{"atlassian":{"command":"npx","args":["-y","mcp-remote","https://mcp.atlassian.com/v1/mcp/authv2"]}}}

Capability

What it does

Connect supported AI clients to Jira and Confluence.

Productivity & CollaborationManufacturing & IndustrialSoftware & Technology

Representative uses

Searching and summarizing Jira and Confluence knowledge
Creating and updating Jira work items or Confluence content with approval
Connecting supported AI clients to Atlassian Cloud without self-hosting a server

Important limits

Atlassian Server or Data Center deployments
Organizations that do not allow enterprise content to pass through an external AI client

Tools55 toolsView tools

Jira Issues & Project Work14 tools
Investigate and manage Jira work from issue discovery through status changes. Review issue metadata and links, search with JQL, create or edit issues, add comments or worklogs, and move work through available transitions.
Confluence Knowledge & Collaboration12 tools
Find, read, create, and update Confluence content across spaces and page hierarchies. Work with page comments and search with CQL when documentation needs to be explored or maintained.
JSM Operations4 tools
When Jira Service Management Operations tools are enabled through the required API-token authentication, inspect operational alerts, schedules, and team context and update alerts as incidents or on-call situations progress.
Bitbucket Development8 tools
When Bitbucket API-token scopes and an organization-linked workspace are available, inspect workspaces, repositories, pull requests, source content, pipelines, deployments, and environments.
Compass Components & Architecture10 tools
Explore software components and the metadata that describes their ownership, type, activity, and relationships. Create components, relationships, and custom fields to keep the software catalog aligned with the system architecture.
Atlassian Search & Teamwork Context7 tools
Discover accessible Atlassian resources, search across supported products, and fetch specific resources without first knowing which product owns them. Teamwork Graph context adds cross-product relationships that help connect people, work, and objects.

View tool names (55)

getJiraIssue
getJiraIssueRemoteIssueLinks
getJiraIssueTypeMetaWithFields
getJiraProjectIssueTypesMetadata
getIssueLinkTypes
getTransitionsForJiraIssue
getVisibleJiraProjects
lookupJiraAccountId
addCommentToJiraIssue
addWorklogToJiraIssue
createJiraIssue
editJiraIssue
transitionJiraIssue
searchJiraIssuesUsingJql
getConfluencePage
getConfluencePageDescendants
getConfluencePageFooterComments
getConfluencePageInlineComments
getConfluenceCommentChildren
getConfluenceSpaces
getPagesInConfluenceSpace
createConfluencePage
updateConfluencePage
createConfluenceFooterComment
createConfluenceInlineComment
searchConfluenceUsingCql
getJsmOpsAlerts
getJsmOpsScheduleInfo
getJsmOpsTeamInfo
updateJsmOpsAlert
bitbucketWorkspace
bitbucketRepository
bitbucketUser
bitbucketDeployment
bitbucketPullRequest
bitbucketRepoContent
bitbucketPipeline
bitbucketEnvironment
getCompassComponent
getCompassComponents
getCompassComponentActivityEvents
getCompassComponentLabels
getCompassComponentTypes
getCompassCustomFieldDefinitions
getCompassComponentsOwnedByMyTeams
createCompassComponent
createCompassComponentRelationship
createCompassCustomFieldDefinition
atlassianUserInfo
getAccessibleAtlassianResources
getTeamworkGraphContext
getTeamworkGraphObject
addTeamworkGraphContext
searchAtlassian
fetchAtlassian

Context Footprint

~11K estimated schema tokens

Context impact: High

Estimated token footprint of the MCP tool schemas exposed to the agent.

Approx. estimate

Whole-profile rough estimate only. Do not synthesize per-tool token values from this heuristic.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: OAuth 2.1 browser authorization is the default and recommended method. Admin-enabled, scoped personal API tokens support headless use and are required for Jira Service Management and Bitbucket Cloud tools; Compass tools require OAuth.
Permissions: Tools are grouped by product and read, write, or search intent. Organization admins grant or revoke permission groups, and calls also honor the connected user's Jira, Confluence, Jira Service Management, Bitbucket, Compass, project, space, IP-allowlist, and OAuth or API-token scopes.
Data handling: The Atlassian-hosted server retrieves and returns authorized Atlassian Cloud content to the external MCP client. Teamwork Graph tools can aggregate relationships across Atlassian products and connected third-party apps and may use AI processing. Traffic uses HTTPS/TLS, and Atlassian records tool-use events in the organization audit log.
Cost: The core connection has no separately stated MCP fee. Users need applicable Atlassian Cloud products and an AI client. Beta tools are currently free; Atlassian says some may later be billed in Rovo credits with notice, and Teamwork Graph calls are expected to consume credits at general availability.
Risk and cautions: The integration can read and modify enterprise work and knowledge across several Atlassian products. Approve client domains, use least privilege, restrict permission groups and token scopes, retain write confirmation, review audit logs, and evaluate the external AI client's data policy. This review does not claim MCP100 execution testing.

Related reviewed MCPs

Other options

Windows-MCP

MCP100 Recommended

An MCP Server for computer-use in Windows OS

Choose this instead if

Choose Windows-MCP instead if using an AI client to inspect and operate Windows applications when no safer application API exists.

Suitable for supervised Windows desktop automation in a disposable or tightly scoped session, not for unattended control of a personal workstation.

Compare with Atlassian Remote MCP View Windows-MCP details

Notion MCP

MCP100 Recommended

Connect AI tools to Notion workspaces through Notion's MCP server.

Choose this instead if

Choose Notion MCP instead if reading and updating explicitly shared Notion pages.

Connect AI tools to Notion workspaces through Notion's MCP server.

Compare with Atlassian Remote MCP View Notion MCP details

HubSpot MCP

MCP100 Recommended

Connect OAuth-capable AI tools to HubSpot CRM data and supported read/write workflows.

Choose this instead if

Choose HubSpot MCP instead if querying CRM records, activities, marketing content, and organizational context.

Connect OAuth-capable AI tools to HubSpot CRM data and supported read/write workflows.

Compare with Atlassian Remote MCP View HubSpot MCP details

Read publisher documentation

Publisher documentation

MCP100 source-backed summary

A concise MCP100 summary built from the reviewed publisher sources. It is not a publisher README; use the original link for the latest full documentation.

View original documentation ↗

Atlassian Remote MCP

Connect supported AI clients to Jira and Confluence.

What it can help with

Searching and summarizing Jira and Confluence knowledge
Creating and updating Jira work items or Confluence content with approval
Connecting supported AI clients to Atlassian Cloud without self-hosting a server

Important limits

Atlassian Server or Data Center deployments
Organizations that do not allow enterprise content to pass through an external AI client
Headless use when organization administrators do not permit API-token authentication

Loading optional publisher documentation…

FAQ

What can Atlassian MCP do with Jira and Confluence?

Connect supported AI clients to Jira and Confluence.

Can Atlassian MCP create or update Jira issues?

Yes. The reviewed Jira tool surface includes creating and editing issues, adding comments and worklogs, searching with JQL, and moving issues through available transitions. Access remains limited by the authenticated Atlassian account and enabled product scopes.

Does Atlassian MCP work with Codex?

Yes. MCP100 reviewed an evidence-backed setup for Codex, but has not independently verified it with a live runtime test.

How does Atlassian MCP authenticate to Jira and Confluence?

OAuth 2.1 browser authorization is the default and recommended method. Admin-enabled, scoped personal API tokens support headless use and are required for Jira Service Management and Bitbucket Cloud tools; Compass tools require OAuth.

What access does Atlassian MCP give an AI agent?

The integration can read and modify enterprise work and knowledge across several Atlassian products. Approve client domains, use least privilege, restrict permission groups and token scopes, retain write confirmation, review audit logs, and evaluate the external AI client's data policy. This review does not claim MCP100 execution testing.

Is this an official MCP?

Atlassian is listed as First-party MCP in MCP100’s current evidence.

Current official resources:

Publisher documentation ↗