CVE-2026-77243: mcp-atlassian tool authorization bypass in tools/call

CVE-2026-77243 · Severity: high · CVSS 8.8 · Published 2026-09-22

mcp-atlassian is an open-source Model Context Protocol server that bridges AI tools to Atlassian products (Jira, Confluence). It enforces tool access controls via configuration filters (`ENABLED_TOOLS`, `TOOLSETS`) to restrict which operations are available. The bypass allows any HTTP client to invoke restricted tools—including write and delete operations on Jira issues and Confluence pages—by calling the tools directly, completely circumventing the intended access controls.

Technologies: mcp-atlassian (PyPI). Vendors: PyPI.

Quick answers

Is CVE-2026-77243 exploited in the wild?
No. Junglewise Threat Intelligence has no report of CVE-2026-77243 being exploited in the wild.
How severe is CVE-2026-77243?
High severity, with a CVSS score of 8.8, published 22 September 2026.
Which products and versions are affected?
mcp-atlassian (PyPI) < 0.22.0, ECOSYSTEM:introduced=0,fixed=0.22.0.
Is there a fix for CVE-2026-77243?
Yes. mcp-atlassian (PyPI): upgrade to 0.22.0 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.
How is CVE-2026-77243 attacked?
It is attacked over the network.
Am I affected by CVE-2026-77243?
Check whether you run mcp-atlassian (PyPI) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

How to fix

  • mcp-atlassian (PyPI): upgrade to 0.22.0 or later
    pip install "mcp-atlassian>=0.22.0"

Technical details

The vulnerability is an authorization bypass in the tool dispatch layer. The `AtlassianMCP` class overrides `_list_tools_mcp` to filter tools at list time based on `ENABLED_TOOLS` and `TOOLSETS` configuration, but does not override `_call_tool_mcp`. The default FastMCP handler resolves tool calls against the full unfiltered tool registry (73 tools), bypassing filters entirely. Any authenticated or network-reachable HTTP client can invoke any tool by name via a direct JSON-RPC `tools/call` request, as tool names are public (discoverable in source code). The attack works in multi-user HTTP deployments where tool filters are trust boundaries; single-user stdio deployments are unaffected. The developers correctly implemented dual enforcement (list + call time) for `READ_ONLY_MODE`, confirming this is an implementation oversight.

Affected products

  • Atlassian mcp-atlassian prior to fix

Identifiers

  • CVE-2026-77243
  • GHSA-3r68-hf9h-887v
  • PYSEC-2026-4081

Timeline

  • 2026-09-22: disclosed: GHSA-3r68-hf9h-887v published

This page as Markdown. Free to reuse under CC BY 4.0 with a link back.