VYPR
High severity7.3NVD Advisory· Published Apr 28, 2026· Updated Apr 29, 2026

CVE-2026-7314

CVE-2026-7314

Description

A vulnerability was detected in eiceblue spire-doc-mcp-server 1.0.0. This affects the function get_doc_path of the file src/spire_doc_mcp/api/base.py. Performing a manipulation of the argument document_name results in path traversal. The attack can be initiated remotely. The exploit is now public and may be used. The project was informed of the problem early through an issue report but has not responded yet.

AI Insight

LLM-synthesized narrative grounded in this CVE's description and references.

Path traversal in spire-doc-mcp-server's convert_document function allows remote attackers to write arbitrary files outside the configured WORD_FILES_PATH directory.

The vulnerability exists in spire-doc-mcp-server version 1.0.0, specifically in the convert_document tool located in src/spire_doc_mcp/api/conversion_tools.py. While the get_doc_path function properly validates the document_name argument to prevent path traversal, the output_path parameter is passed directly to ConversionHandler.convert_document() without canonicalization or enforcement of the intended WORD_FILES_PATH boundary [1]. This results in an external control of file name or path (CWE-73).

The attack can be performed remotely by sending crafted requests to the MCP server. An attacker can supply a output_path containing path traversal sequences (e.g., ../) to write converted documents to arbitrary locations on the filesystem. No authentication is required if the server is exposed to untrusted networks, and the exploit has been publicly disclosed [1,2].

Successful exploitation allows an attacker to create or overwrite files with the permissions of the service account, potentially leading to remote code execution, modification of server configuration, or data loss. Since the server is often integrated with AI agents (such as Cursor IDE), a compromised server could affect downstream workflows [2]. The vulnerability is documented in an issue report, and no patch has been released as of the disclosure date [1].

Mitigation is limited at this time because the vendor has not responded to the issue report. Users should restrict network access to the MCP server (e.g., via firewall or reverse proxy) and validate the output_path parameter externally. Monitoring for unexpected file creation is also recommended until a fix is provided [1,2].

AI Insight generated on May 18, 2026. Synthesized from this CVE's description and the cited reference URLs; citations are validated against the source bundle.

Affected products

2

Patches

0

No patches discovered yet.

Vulnerability mechanics

AI mechanics synthesis has not run for this CVE yet.

References

4

News mentions

0

No linked articles in our index yet.