CVE-2026-65056: Server-Side Request Forgery (SSRF) in mzxrai mcp-webresearch
mcp-webresearch version 0.1.7 contains a server-side request forgery (SSRF) vulnerability. This flaw allows attackers to supply URLs pointing to internal network addresses, such as loopback, link-local, or cloud metadata endpoints, via the visit_page tool. The vulnerability arises because the tool only validates the URL protocol but does not filter out private or reserved IP ranges. Exploitation can lead to the server's Playwright browser accessing internal services and returning sensitive data, including credentials, into the model context.
AI Analysis
Technical Summary
CVE-2026-65056 is a server-side request forgery vulnerability in mzxrai's mcp-webresearch 0.1.7. The visit_page tool accepts a URL argument controlled by an attacker, which is only checked for protocol validity but not for private or reserved IP ranges. This allows attackers to direct the server's Playwright browser to internal network endpoints such as cloud instance metadata services. As a result, sensitive internal content, including credentials, may be exposed to the attacker via the model context. The vulnerability has a CVSS 4.0 base score of 8.3, indicating high severity. No official patch or remediation guidance is currently available, and no known exploits in the wild have been reported.
Potential Impact
An attacker can leverage this SSRF vulnerability to access internal network services that are normally inaccessible externally. This includes cloud instance metadata endpoints that may contain sensitive credentials or configuration data. The exposure of such internal information can lead to further compromise of the server or cloud environment. The vulnerability requires no privileges and no user interaction other than supplying a crafted URL, increasing its risk.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is available, restrict access to the visit_page tool or implement network-level controls to prevent the server from making requests to internal or reserved IP ranges. Validate and sanitize URL inputs to block private, loopback, link-local, and cloud metadata IP addresses. Monitor for unusual internal requests originating from the application.
CVE-2026-65056: Server-Side Request Forgery (SSRF) in mzxrai mcp-webresearch
Description
mcp-webresearch version 0.1.7 contains a server-side request forgery (SSRF) vulnerability. This flaw allows attackers to supply URLs pointing to internal network addresses, such as loopback, link-local, or cloud metadata endpoints, via the visit_page tool. The vulnerability arises because the tool only validates the URL protocol but does not filter out private or reserved IP ranges. Exploitation can lead to the server's Playwright browser accessing internal services and returning sensitive data, including credentials, into the model context.
CVSS v4.0
Score 8.3high
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-65056 is a server-side request forgery vulnerability in mzxrai's mcp-webresearch 0.1.7. The visit_page tool accepts a URL argument controlled by an attacker, which is only checked for protocol validity but not for private or reserved IP ranges. This allows attackers to direct the server's Playwright browser to internal network endpoints such as cloud instance metadata services. As a result, sensitive internal content, including credentials, may be exposed to the attacker via the model context. The vulnerability has a CVSS 4.0 base score of 8.3, indicating high severity. No official patch or remediation guidance is currently available, and no known exploits in the wild have been reported.
Potential Impact
An attacker can leverage this SSRF vulnerability to access internal network services that are normally inaccessible externally. This includes cloud instance metadata endpoints that may contain sensitive credentials or configuration data. The exposure of such internal information can lead to further compromise of the server or cloud environment. The vulnerability requires no privileges and no user interaction other than supplying a crafted URL, increasing its risk.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is available, restrict access to the visit_page tool or implement network-level controls to prevent the server from making requests to internal or reserved IP ranges. Validate and sanitize URL inputs to block private, loopback, link-local, and cloud metadata IP addresses. Monitor for unusual internal requests originating from the application.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulnCheck
- Date Reserved
- 2026-07-21T14:05:53.720Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a5fdfa89c2644c7f8c1b096
Added to database: 07/21/2026, 21:07:52 UTC
Last enriched: 07/30/2026, 07:52:34 UTC
Last updated: 09/04/2026, 10:52:10 UTC
Views: 88
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.