Data as of

MCP Atlassian for Windsurf: Setup & Config

MCP Atlassian connects Windsurf to Jira and Confluence for issue tracking and team documentation.

What you can do with MCP Atlassian in Windsurf

Combine Jira delivery workflows and Confluence knowledge access in one assistant integration.

  • Create bug reports and move issues through workflow statuses.
  • Create or update team pages and add comments.

Before you start: MCP Atlassian in Windsurf

  • uvx
  • An MCP-compatible client
  • Access to Jira or Confluence with appropriate credentials
  • Confluence 6.0+ or Jira 8.14+ for self-managed deployments

This is the Cloud quickstart configuration. Server/Data Center uses PAT authentication; the README specifies JIRA_PERSONAL_TOKEN in place of the Jira username and API-token pair. Keep credentials private.

MCP Atlassian Windsurf configuration

  1. Choose Windsurf configuration scope

    For MCP Atlassian, open macOS/Linux: ~/.codeium/windsurf/mcp_config.json Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json. Merge into mcpServers; remote endpoints use serverUrl.

  2. Add MCP Atlassian to Windsurf

    Use the mcp-atlassian entry below in mcpServers. Keep MCP Atlassian's documented stdio connection fields and your other Windsurf entries.

  3. Check MCP Atlassian in Windsurf

    MCP Atlassian: Refresh MCP in Windsurf settings and inspect Cascade’s tools.

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

JSON
{
  "mcpServers": {
    "mcp-atlassian": {
      "command": "uvx",
      "args": [
        "mcp-atlassian"
      ],
      "env": {
        "JIRA_URL": "<your Jira instance URL>",
        "JIRA_USERNAME": "<your Jira account email>",
        "JIRA_API_TOKEN": "<your Jira Cloud API token>",
        "CONFLUENCE_URL": "<your Confluence instance URL>",
        "CONFLUENCE_USERNAME": "<your Confluence account email>",
        "CONFLUENCE_API_TOKEN": "<your Confluence Cloud API token>"
      }
    }
  }
}

MCP Atlassian tools available to Windsurf

MCP Atlassian's stored tool list documents 10 tools; compare it with Windsurf's connected tool list, because the stored list is not a live check.

jira_search

After refreshing MCP Atlassian in Windsurf settings, check Cascade's tool list for jira_search.

jira_get_issue

After refreshing MCP Atlassian in Windsurf settings, check Cascade's tool list for jira_get_issue.

jira_create_issue

After refreshing MCP Atlassian in Windsurf settings, check Cascade's tool list for jira_create_issue.

jira_update_issue

After refreshing MCP Atlassian in Windsurf settings, check Cascade's tool list for jira_update_issue.

Modify an existing Jira issue.

jira_transition_issue

After refreshing MCP Atlassian in Windsurf settings, check Cascade's tool list for jira_transition_issue.

Move an issue to another workflow status.

confluence_search

After refreshing MCP Atlassian in Windsurf settings, check Cascade's tool list for confluence_search.

confluence_get_page

After refreshing MCP Atlassian in Windsurf settings, check Cascade's tool list for confluence_get_page.

confluence_create_page

After refreshing MCP Atlassian in Windsurf settings, check Cascade's tool list for confluence_create_page.

Add a new Confluence page.

confluence_update_page

After refreshing MCP Atlassian in Windsurf settings, check Cascade's tool list for confluence_update_page.

Revise an existing Confluence page.

confluence_add_comment

After refreshing MCP Atlassian in Windsurf settings, check Cascade's tool list for confluence_add_comment.

Post a comment to Confluence content.

MCP Atlassian: full stored tool descriptions

Troubleshooting MCP Atlassian in Windsurf

  • Check uvx mcp-atlassian (from uv, for Python tools) on the machine running Windsurf's MCP integration for MCP Atlassian; refresh MCP and inspect Cascade's tools.
  • Check CONFLUENCE_API_TOKEN, CONFLUENCE_URL, CONFLUENCE_USERNAME, JIRA_API_TOKEN, JIRA_URL, JIRA_USERNAME for MCP Atlassian; do not bypass a Windsurf permission error with a broad administrator token.
  • MCP Atlassian uses stdio here: Windsurf must keep the configured process running; protocol output belongs on stdout and diagnostics on stderr.
  • Known limitation: Requires product URLs and appropriate authentication credentials.
  • Known limitation: Self-managed support has minimum Confluence and Jira version requirements.
  • Known limitation: Only a subset of the full tool catalog is named in the README.
  • General Windsurf troubleshooting lives in the /clients/windsurf guide.

MCP Atlassian — details. Windsurf guide

Frequently asked questions

Windsurf reads MCP Atlassian under mcpServers in ~/.codeium/windsurf/mcp_config.json on macOS/Linux; Windows uses %USERPROFILE%\.codeium\windsurf\mcp_config.json.

Windsurf's mcp-atlassian example uses stdio.

MCP Atlassian's Windsurf configuration invokes uvx mcp-atlassian (from uv, for Python tools).

Windsurf's MCP Atlassian example references CONFLUENCE_API_TOKEN, CONFLUENCE_URL, CONFLUENCE_USERNAME, JIRA_API_TOKEN, JIRA_URL, JIRA_USERNAME. Check these names if startup or authentication fails; the example alone does not distinguish required from optional values.

MCP Atlassian's stored list contains 10 tools, including jira_search, jira_get_issue, jira_create_issue. Compare those names with Windsurf's connected tool list; the stored list is not a live check.

The named search tools use JQL for Jira and CQL for Confluence.

No. The README explicitly identifies it as unofficial and lists the MIT license.