CVE-2026-49986
HighCVSS 7.1Exploitation Probability (EPSS)
Low risk2th percentile - higher than 2% of all known CVEs
Summary
The Cortex MCP server (neuro-cortex-memory) before version 3.17.1 treats the CLAUDE_PROJECT_DIR environment variable as a trusted Cortex source. An attacker can place marker files in a malicious repository, leading to arbitrary code execution via the open_visualization tool.
Risk Assessment
A user may be tricked into executing malicious code with their process privileges, potentially leading to system compromise.
Recommendation
It is recommended to upgrade to version 3.17.1, which fixes this vulnerability.
Original NVD description (English source)
The Cortex MCP server (`neuro-cortex-memory`), a cross-platform persistent memory MCP, prior to version 3.17.1 treats the `CLAUDE_PROJECT_DIR` environment variable — automatically set by Claude Code to the currently open project directory — as a trusted Cortex developer checkout. When the `open_visualization` tool is invoked, `_find_dev_source()` resolves the user's active project directory as a candidate Cortex source root. The only validation performed by `_is_cortex_root()` is a check for the presence of an `mcp_server/` subdirectory and a `ui/unified-viz.html` file. An attacker who places these two marker files in a malicious repository can cause Cortex to execute an arbitrary `mcp_server/server/visualize_bootstrap.py` from that directory via `subprocess.run([sys.executable, ...])`, achieving code execution with the privileges of the victim's local user process. Version 3.17.1 fixes the issue.