CVE-2026-25904
SSRF Vulnerability in Pydantic-AI MCP Run Python Tool
Publication date: 2026-02-09
Last updated on: 2026-02-09
Assigner: JFrog
Description
Description
CVSS Scores
EPSS Scores
| Probability: | |
| Percentile: |
Meta Information
Affected Vendors & Products
| Vendor | Product | Version / Range |
|---|---|---|
| pydantic-ai | mcp-run-python | * |
Helpful Resources
Exploitability
| 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 Powered Q&A
Can you explain this vulnerability to me?
The vulnerability exists in the Pydantic-AI MCP Run Python tool, which configures the Deno sandbox with an overly permissive setup. This configuration allows the underlying Python code to access the localhost interface of the host machine. As a result, an attacker can perform Server-Side Request Forgery (SSRF) attacks by exploiting this access.
Additionally, the project "mcp-run-python" is archived and unlikely to receive a fix, meaning the vulnerability may remain unpatched.
How can this vulnerability impact me? :
This vulnerability can allow attackers to perform SSRF attacks by accessing the localhost interface through the vulnerable tool. SSRF attacks can be used to access internal services, potentially leading to unauthorized information disclosure, data manipulation, or further exploitation within the internal network.
The CVSS score of 5.8 indicates a medium severity impact, with potential consequences including limited confidentiality, integrity, and availability impacts.
How does this vulnerability affect compliance with common standards and regulations (like GDPR, HIPAA)?:
I don't know
How can this vulnerability be detected on my network or system? Can you suggest some commands?
I don't know
What immediate steps should I take to mitigate this vulnerability?
I don't know