CVE-2026-80347 json
mcp-fetch through 1.6.3 Server-Side Request Forgery via Unstripped IPv6 Literal Brackets
published 2026-08-26 2 mo ago modified 2026-09-24 45 d ago also EUVD-2026-66386
- cvss
- 7.5
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.4%
- EPSS 0.4% chance of exploitation in 30 days, percentile 28%
- public exploits
- 0
- none known
Summary
mcp-fetch checks a fetch target against its SSRF guard without removing the brackets that surround an IPv6 literal. isSafeUrl reads the hostname from the parsed URL, which for a literal such as http://[::1]/ yields the bracketed string, and then tests it with net.isIP. That call returns zero for a bracketed value, so the branch holding the private-address checks is skipped entirely. The guard falls back to resolving the hostname, the bracketed string is not a resolvable name, no addresses are returned, and the target is reported safe. The HTTP client then strips the brackets and connects. Because the address may be given in IPv4-mapped form, the same path reaches any IPv4 target the loopback and private checks were meant to exclude, including link-local metadata endpoints. isPrivateIPv6 also has no case for the ::ffff: prefix, so the mapped form would still pass even if the brackets were removed. The fetch target is supplied as a tool argument, so an attacker who can influence what the model requests can read internal responses back into the model context.
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- yes
- Technical impact
- partial
- Assessed
- 2 mo ago
Exploit prediction
0.35% chance of exploitation in the next 30 days, higher than 28% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- github.com https://github.com/kazuph/mcp-fetch/issues/16 referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 4.0 | 8.7 | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N |
| CNA | 3.1 | 7.5 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N |
| CNA | 4.0 | 8.7 | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X |
Affected products
- kazuph mcp-fetch
Classification
- Weakness
-
- CWE-918 Server-Side Request Forgery
References
-
github.com
/kazuph/mcp-fetch/issues/16
issue-tracking, exploit
-
github.com
/kazuph/mcp-fetch
product
-
npmjs.com
/package/@kazuph/mcp-fetch
product
-
vulncheck.com
/advisories/mcp-fetch-through-1.6.3-server-side-request-forgery-via-unstripped-ipv6-literal-brackets
third-party-advisory
Sources
- CVE List CVE-2026-80347
- NVD CVE-2026-80347
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.