MCP Observatory
npm analyzed 3.9.1

mcp-server-kubernetes

v3.9.1
npm

MCP server for interacting with Kubernetes clusters via kubectl

maintainer
flux159
license
MIT
first seen
2026-05-22
last seen
2026-06-14
releases · 30d
8
short id
risk70/100 · heuristic grade
D high
  • vulnerabilitiesattested+34
  • capability exposureinferred+35
  • inherited (deps)attested+15
  • trust mitigatorsmixed−14

attestedinferredmixed

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 6m ago · see ecosystem CVEs →

risk trajectory2 movements
  • D · 61 → D · 70
  • D · 70 → D · 61
capability exposuregrade factor +35
Inferred surface — each links to servers holding it:
vulnerabilities5 CVEs · grade factor +34
HIGH
MCP Server Kubernetes: Tool Access Control Bypass via Presentation-Layer Filtering Without Execution… EPSS 0% CVE-2026-46519 CVSS 8.8 affects [{"type":"SEMVER","events":[{"introduced":"0"},{"fixed":"3.6.0"}]}]fixed in 3.6.0GHSANVDGHSAGHSA
HIGH
MCP Server Kubernetes has an Argument Injection in port_forward tool via space-splitting EPSS 0% CVE-2026-39884 CVSS 8.3 affects [{"type":"SEMVER","events":[{"introduced":"0"},{"fixed":"3.5.0"}]}]fixed in 3.5.0GHSANVDGHSAGHSA
HIGH
MCP Server Kubernetes vulnerable to command injection in several tools EPSS 0% CVE-2025-53355 CVSS 7.5 affects [{"type":"SEMVER","events":[{"introduced":"0"},{"fixed":"2.5.0"}]}]fixed in 2.5.0GHSANVDGHSAGHSA
MEDIUM
MCP Server Kubernetes: kubectl-generic flag injection enables Kubernetes bearer token exfiltration EPSS 0% CVE-2026-47250 CVSS 6.1 affects [{"type":"SEMVER","events":[{"introduced":"0"},{"fixed":"3.7.0"}]}]fixed in 3.7.0GHSANVDGHSAGHSA
MEDIUM
mcp-server-kubernetes has potential security issue in exec_in_pod tool EPSS 0% CVE-2025-66404 CVSS 6.4 affects [{"type":"SEMVER","events":[{"introduced":"0"},{"fixed":"2.9.8"}]}]fixed in 2.9.8GHSANVDGHSAGHSA

inherited (deps) · grade factor +15

inherited via dependencies3
HIGH
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse via @modelcontextprotocol/sdk · 1 hop CVE-2026-25536 fixed in 1.26.0
HIGH
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability via @modelcontextprotocol/sdk · 1 hop CVE-2026-0621 fixed in 1.25.2
HIGH
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default via @modelcontextprotocol/sdk · 1 hop CVE-2025-66414 fixed in 1.24.0
tool safetyall quiet

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

embed badgereadme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/npm:mcp-server-kubernetes/badge.svg)](https://mcpobservatory.com/servers/npm:mcp-server-kubernetes/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 flux159.