ToolTrust
C32/100
alexei-led

k8s-mcp-server

mcp1.4.2

@alexei-led

K8s-mcp-server is a Model Context Protocol (MCP) server that enables AI assistants like Claude to securely execute Kubernetes commands. It provides a bridge between language models and essential Kubernetes CLI tools including kubectl, helm, istioctl, and argocd, allowing AI systems to assist with cluster management, troubleshooting, and deployments

By alexei-led | 104 findings | Scanned 6/3/2026 | tooltrust-scanner/v0.3.13 | 210

8 High14 Medium7 Low75 Info

Risk Summary

Needs Approval

Dep Visibility plus Excessive Permissions raises enough risk that this tool should not be auto-trusted.

Potential impact: This finding indicates the tool should be reviewed before it is trusted.

Recommended action: Keep this tool behind manual approval and avoid unattended runs until the risky capabilities are narrowed or removed.

Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.

Security Findings (104)

  • HighAS-002

    ⚠️Excessive Permissions ×5

    tool declares exec permission

    get_effective_permissionscreate_job

    tool declares network permission

    get_cluster_infocreate_network_policylist_flux_sources

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • HighAS-003

    🔀Scope Mismatch

    get_effective_permissions:tool name "get_effective_permissions" implies read-only operation but declares exec permission

    Fix: Ensure tool names, descriptions, and permission declarations are internally consistent. Use explicit naming conventions that fully reflect actual capabilities.

  • HighAS-010

    🔑Insecure Secret Handling ×2

    input parameter "secretName" appears to accept a secret or credential

    create_secretupdate_secret

    Fix: Avoid accepting raw credentials as input parameters. Use secret managers (e.g. 1Password CLI, AWS Secrets Manager) and ensure credentials are never logged or stored in agent traces.

  • MediumAS-002

    ⚠️Excessive Permissions ×14

    tool declares fs permission

    create_jobcreate_configmapupdate_configmapcreate_secretupdate_secretcreate_deploymentdelete_deploymentcreate_namespacedelete_namespacecreate_horizontal_pod_autoscalercreate_serviceupdate_ingresscreate_network_policyremove_taint

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • LowAS-002

    ⚠️Excessive Permissions

    restart_pod:tool declares http permission

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • LowAS-011

    ℹ️Missing Rate-Limit / Timeout ×6

    tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration

    restart_podget_effective_permissionsget_cluster_infocreate_jobcreate_network_policylist_flux_sources

    Fix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.

  • InfoAS-014

    ℹ️Dependency Inventory Unavailable ×75

    Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.

    list_podsget_pod_logsdescribe_poddescribe_deploymentlist_nodeslist_statefulsetsdescribe_statefulsetlist_daemonsetsdescribe_daemonsetscale_deploymentrollout_statusrollout_undorestart_podget_configmapdescribe_namespace_quotalist_eventslist_persistent_volume_claimsget_effective_permissionsget_hpa_statuslist_warning_eventsget_node_pressurelist_clustersget_cluster_infolist_jobscreate_joblist_cronjobssuspend_cronjobresume_cronjobcreate_configmapupdate_configmapcreate_secretupdate_secretcreate_deploymentdelete_deploymentcreate_namespacedelete_namespacecreate_horizontal_pod_autoscalercreate_servicelist_ingressesget_service_endpointsupdate_ingresscreate_network_policyset_resource_limitsget_resource_recommendationsget_cluster_resource_utilisationcordon_nodeuncordon_nodedrain_nodetaint_noderemove_taintget_gitops_app_statusget_gitops_diffsync_gitops_appcompare_clusterslist_flux_kustomizationslist_flux_helm_releasesget_flux_helm_releaselist_flux_sourcessuspend_flux_resourceresume_flux_resourcelist_flux_alertslist_k8s_resourcesget_k8s_resourcelist_node_poolsget_node_pool_detailget_workload_identity_configvalidate_workload_identitylist_pod_disruption_budgetsget_pdb_statuslist_vpasget_vpa_recommendationlist_storage_classesget_storage_classget_addon_healthlist_limit_ranges

    Fix: Review and remediate the identified issue.

Scan this tool yourself

Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.

Install once, then scan any MCP server:

$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash
$ tooltrust-scanner scan --server "npx -y k8s-mcp-server"

Adjust the package name if your npm registry name differs from the tool ID. View source

Add badge to your README

Copy this Markdown to show your ToolTrust grade on GitHub.

[![ToolTrust Grade C](https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-directory/main/docs/badges/grade-c.svg)](https://github.com/AgentSafe-AI/tooltrust-directory)