MCP Observatory
github analyzed d9728a8 unconfirmed MCP

modelcontextprotocol/go-sdk

github

The official Go SDK for Model Context Protocol servers and clients. Maintained in collaboration with Google.

maintainer
modelcontextprotocol
license
NOASSERTION
first seen
2026-06-01
last seen
2026-06-17
releases · 30d
1
short id
risk 42/100 · heuristic grade
C elevated
  • vulnerabilitiesattested+50
  • trust mitigatorsmixed−8

attestedmixed

The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.

graded 14m ago · see ecosystem CVEs →

risk trajectory 2 movements
  • C · 57 → C · 42
  • C · 42 → C · 57
vulnerabilities 4 CVEs · grade factor +50
HIGH
DNS Rebinding Protection Disabled by Default in Model Context Protocol Go SDK for Servers Running on… EPSS 0% CVE-2026-34742 affects ["< 1.4.0"]
HIGH
Improper handling of null Unicode character when parsing JSON in github.com/modelcontextprotocol/go-… affects ["<= 1.4.0"]
HIGH
Cross-Site Tool Execution for HTTP Servers without Authorization in github.com/modelcontextprotocol/… EPSS 0% CVE-2026-33252 affects ["<= 1.4.0"]
HIGH
Improper Handling of Case Sensitivity in github.com/modelcontextprotocol/go-sdk EPSS 0% CVE-2026-27896 affects ["< v1.3.1"]
tool safety all quiet

No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.

skills & danger signals github-tarball
prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed commit d9728a8 · analyzer v18 · 2h ago

skills & prompt files 1

embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:modelcontextprotocol/go-sdk/badge.svg)](https://mcpobservatory.com/servers/github:modelcontextprotocol/go-sdk/security)

Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of modelcontextprotocol.