CVE-2026-19984
Received Received - Intake

Server-Side Request Forgery in mcp-florence2

Publication date: 2026-08-17

Last updated on: 2026-08-17

Assigner: VulDB

Description
A flaw has been found in jkawamoto mcp-florence2 up to 0.3.13. Affected by this issue is the function get_images of the file src/mcp_florence2/__init__.py. This manipulation of the argument src causes server-side request forgery. The attack may be initiated remotely. The exploit has been published and may be used. It is recommended to change the configuration settings. The vendor explains: "For deployments where SSRF protection is required, I recommend routing all HTTP(S) requests through an SSRF-safe proxy server. This approach mitigates the vulnerability without requiring changes to the mcp-florence2 source code."

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-08-17
Last Modified
2026-08-17
Generated
2026-08-17
AI Q&A
2026-08-17
EPSS Evaluated
N/A
NVD
CVE-2026-19984
EUVD
EUVD-2026-60047

Affected Vendors & Products

Showing 1 associated CPE
Vendor Product Version / Range
jkawamoto mcp-florence2 to 0.3.13 (inc)

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-918 The web server receives a URL or similar request from an upstream component and retrieves the contents of this URL, but it does not sufficiently ensure that the request is being sent to the expected destination.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

This vulnerability is a Server-Side Request Forgery (SSRF) flaw in the mcp-florence2 library up to version 0.3.13. It occurs in the get_images function of src/mcp_florence2/__init__.py where the src argument is manipulated to make the server initiate arbitrary HTTP requests to internal or external hosts without proper validation. The attack can be triggered remotely and may allow access to internal network services or cloud metadata endpoints.

Detection Guidance

To detect this SSRF vulnerability in mcp-florence2, monitor outbound HTTP/HTTPS requests from the server, especially those initiated by the OCR or caption tools. Check logs for requests to internal IPs, cloud metadata endpoints, or unusual domains. Use network traffic analysis tools like tcpdump or Wireshark to capture requests originating from the mcp-florence2 process.

Impact Analysis

This vulnerability allows attackers to force the mcp-florence2 server to make unauthorized requests to internal systems or external URLs. This could lead to data leakage, unauthorized access to sensitive services, or bypassing network restrictions. The impact includes potential exposure of internal network information and increased risk of further attacks via the compromised server.

Compliance Impact

This SSRF vulnerability could lead to unauthorized access to sensitive data, violating confidentiality requirements under GDPR and HIPAA. It may cause data breaches, unauthorized disclosure of personal or health information, and failure to implement adequate security controls, potentially resulting in regulatory penalties and loss of compliance certifications.

Mitigation Strategies

Immediately restrict the src parameter in mcp-florence2 to only allow trusted domains or IPs. Configure a proxy server to route all HTTP(S) requests and enforce SSRF-safe policies. Update to the latest patched version if available. Disable the OCR and caption tools if SSRF protection is not feasible.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-19984. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart