CVE-2026-81091: mcp-use · Server-Side Request Forgery (SSRF)
Affects mcp-useSource CVE Database V5
Not known to be exploited · CVSS 8.7 High.
Data as of 20 Nov 2026, 14:50 UTC
Thin evidence
One scorer or none| CNA (VulnCheck) | CVSS 4.0 | 8.7 |
|---|---|---|
| CNA (VulnCheck) | CVSS 3.1 | 8.6 |
- CISA SSVC
- Exploitation
- No evidence of active exploitation and no public proof of concept
- Automatable
- Attackers can reliably automate steps 1–4 of the kill chain
- Technical impact
- Limited control over the software or limited information exposure
CISA SSVC assessment, 2026-08-27.
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:NExploitation evidence
Disclosed: evidence found.
CVE published 27 Aug 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 19 Nov 2026.
What to do
Affected software
| Product | Affected | Fixed in |
|---|---|---|
| mcp-usemcp-use | Affected
| Fixed in– |
GitHubmcp-usepkg:github/mcp-useOther threats | Affected
| Fixed in– |
Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.
AI-suggested
Users should upgrade to mcp-use version 2.x or later, where the proxy middleware includes proper validation of target addresses to block SSRF attacks. No other mitigation or temporary fixes are indicated.
Description
CVE-2026-81091 is a Server-Side Request Forgery (SSRF) vulnerability in the proxy middleware of mcp-use versions up to 1.34.8. The proxy forwards requests to destinations specified by the caller via the X-Target-URL header or __mcp_target parameter without properly validating the target host. This allows attackers to make the server send requests to internal or private network addresses and read the responses. The issue was addressed in mcp-use 2.x by adding checks to block private, loopback, and link-local addresses and limiting redirects.