Atlassian (Jira, Confluence)

This connector bridges the Atlassian Rovo MCP Server, Atlassian's official remote MCP server at https://mcp.atlassian.com/v2/mcp. Atlassian's server provides the tools: Jira work items, boards and sprints, Confluence pages and spaces, Rovo search across Jira, Confluence and connected apps, Teamwork Graph and, where your organization has them, Jira Service Management, Bitbucket Cloud, Loom and Goals. AnythingMCP signs in with your personal API token and puts the tools behind your MCP endpoint with OAuth for Claude and ChatGPT, per-tool roles, the audit log and response mapping, next to your other systems.

The tools come from the server. At install AnythingMCP asks Atlassian's server which tools it offers your token, so you get exactly what your organization and token allow. Atlassian lists a small set of primary tools directly (getJiraIssue, searchJiraIssuesUsingJql, createJiraIssue, getConfluenceContent, search and a few more) and reaches the rest of its catalogue through discover (find an operation by describing it) and executeRead / executeWrite / executeDestructive (run it by name). When Atlassian adds tools or your admin enables another permission group, open the connector and click Discover tools.

Setup (about 10 minutes, step 1 needs an Atlassian organization admin):

1. An organization admin enables API-token authentication for the MCP server: Atlassian Administration > Rovo > Rovo MCP server settings, turn on authentication via API token. Without it every call is refused and only OAuth clients can connect. The same settings control the permission groups; delete_jira and manage_jira are off by default.
2. Signed in as the person the AI should act as, open https://id.atlassian.com/manage-profile/security/api-tokens and choose Create API token with scopes. Pick the agent-interface scopes of the apps you want, for example read:jira:agent-interface, write:jira:agent-interface, search:jira:agent-interface, read:confluence:agent-interface, write:confluence:agent-interface, search:confluence:agent-interface and search:rovo:agent-interface. Copy the token: Atlassian shows it once.
3. Fill in the variables and install:
   • ATLASSIAN_EMAIL: the email address of the Atlassian account that owns the token.
   • ATLASSIAN_API_TOKEN: the token from step 2, stored encrypted. AnythingMCP sends both as Authorization: Basic base64(email:token), which is how Atlassian takes personal API tokens.
4. A service account instead of a person: an admin creates a service account and an API key with the same scopes. Atlassian takes that key as Authorization: Bearer, so after installing open the connector editor, change the auth type to Bearer token and paste the key there (the email is then not used).

Network: if your organization restricts access with an IP allow list, add the address AnythingMCP calls from (on AnythingMCP Cloud, ask support for the current egress IP). With API tokens the IP allow list is the only network check, because there is no OAuth redirect domain to validate.

Safety: every call runs with the token owner's Jira, Confluence and Bitbucket permissions, so use an account (or service account) that sees only what the AI should, and give the token only the scopes you need. Installed switched off: executeWrite and executeDestructive (Atlassian's default endpoint lists only the main tools and reaches every other operation through them, so executeWrite alone could merge a pull request or change permissions; turn it on when the AI should write beyond the main tools), the Jira delete tools, space and screen administration, sprint and version management, entity properties, Confluence permission, restriction, public-link and space-instruction changes, the Confluence Remix tools (15 to 30 Rovo credits each), Bitbucket merge, approve, commit and pipeline runs, Loom visibility changes and Jira Service Management alert actions. Turn any of them on per tool when you need it. Rovo search and the Teamwork Graph tools use up to 10 Rovo credits per call from your organization's shared pool.

Working with it: start with atlassian_getAccessibleAtlassianResources. API tokens are not bound to one site, so almost every tool needs a cloudId, and this call returns it for each site you can reach. Then use atlassian_search for questions in plain language, atlassian_searchJiraIssuesUsingJql or atlassian_searchConfluence for exact filters, and atlassian_getJiraIssue or atlassian_getConfluenceContent (with detail set to full for the body) to read one item. Not every tool works with an API token: code search, Teams and some Compass tools need OAuth 2.1, while the Jira Service Management tools work only with API tokens. A 401 means API-token authentication is off for your organization, or the email and token do not belong together; a permission or scope error on one tool means the token lacks that app's agent-interface scope, so create a new token with it and replace it here.