A security vulnerability has been detected in modelcontextprotocol mcp-server-fetch and mcp-server-everything up to 2026.6.4. (CVE-2026-104120)
A server-side request forgery (SSRF) vulnerability exists in the fetch_url function of the mcp_server_fetch/server.py component in modelcontextprotocol mcp-server-fetch and mcp-server-everything up to version 2026.6.4. This vulnerability allows remote attackers to manipulate URL or path arguments, potentially causing the server to make unintended requests. The vulnerability has a CVSS 3.1 score of 7.3 (medium severity). A fix has been proposed but is not yet accepted or available.
AI Analysis
Technical Summary
CVE-2026-104120 describes a server-side request forgery vulnerability in the fetch_url function of the Fetch Tool component within modelcontextprotocol mcp-server-fetch and mcp-server-everything up to version 2026.6.4. The vulnerability arises from improper validation of the url/path argument, enabling remote attackers to induce the server to perform unauthorized requests. The vulnerability is publicly disclosed, and a fix is pending acceptance of a pull request. No official patch or remediation has been released at this time.
Potential Impact
Successful exploitation could allow an attacker to cause the vulnerable server to make arbitrary requests, potentially leading to information disclosure, interaction with internal systems, or other impacts associated with SSRF vulnerabilities. The CVSS score of 7.3 reflects a medium severity with impacts on confidentiality, integrity, and availability.
Mitigation Recommendations
Currently, no official patch or fix has been released. A pull request addressing the vulnerability is awaiting acceptance. Users should monitor the vendor's repository or advisory channels for the official fix and apply it promptly once available. Until then, consider restricting network access or implementing filtering controls to limit the server's ability to make arbitrary outbound requests if feasible.
A security vulnerability has been detected in modelcontextprotocol mcp-server-fetch and mcp-server-everything up to 2026.6.4. (CVE-2026-104120)
Description
A server-side request forgery (SSRF) vulnerability exists in the fetch_url function of the mcp_server_fetch/server.py component in modelcontextprotocol mcp-server-fetch and mcp-server-everything up to version 2026.6.4. This vulnerability allows remote attackers to manipulate URL or path arguments, potentially causing the server to make unintended requests. The vulnerability has a CVSS 3.1 score of 7.3 (medium severity). A fix has been proposed but is not yet accepted or available.
CVSS v3.1
Score 7.3high
Affected software
pkg:github/modelcontextprotocol/mcp-server-fetchpkg:github/modelcontextprotocol/mcp-server-everythingRun on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-104120 describes a server-side request forgery vulnerability in the fetch_url function of the Fetch Tool component within modelcontextprotocol mcp-server-fetch and mcp-server-everything up to version 2026.6.4. The vulnerability arises from improper validation of the url/path argument, enabling remote attackers to induce the server to perform unauthorized requests. The vulnerability is publicly disclosed, and a fix is pending acceptance of a pull request. No official patch or remediation has been released at this time.
Potential Impact
Successful exploitation could allow an attacker to cause the vulnerable server to make arbitrary requests, potentially leading to information disclosure, interaction with internal systems, or other impacts associated with SSRF vulnerabilities. The CVSS score of 7.3 reflects a medium severity with impacts on confidentiality, integrity, and availability.
Mitigation Recommendations
Currently, no official patch or fix has been released. A pull request addressing the vulnerability is awaiting acceptance. Users should monitor the vendor's repository or advisory channels for the official fix and apply it promptly once available. Until then, consider restricting network access or implementing filtering controls to limit the server's ability to make arbitrary outbound requests if feasible.
Technical Details
- Gcve Source
- db.gcve.eu
- Osv Id
- GHSA-v78q-44mm-wf7q
- Osv Schema Version
- 1.4.0
- Aliases
- ["CVE-2026-104120"]
- Database Specific Severity
- MODERATE
- Cvss Version
- 3.1
- State
- PUBLISHED
Threat ID: 6abfeec2a43b0b3b89e57889
Added to database: 10/02/2026, 17:49:54 UTC
Last enriched: 10/02/2026, 18:23:52 UTC
Last updated: 10/02/2026, 18:45:56 UTC
Views: 2
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.