20 Best Kubernetes MCP Servers, Compared (November 2026)

The short answer

Which one, for your situation

Top MCP servers for Kubernetes

The ranking, with the evidence

• 1

  mcp-server-kubernetes

  Community favourite

  Flux159/mcp-server-kubernetes ↗

  Best for: Managing a running cluster from an assistant session: it exposes 17 tools covering pods, deployments, services, Helm releases, and port forwards.

  It runs locally over stdio via npx and exposes 17 tools that wrap cluster operations such as get, describe, apply, create, logs, scale, patch, rollout, context switching, Helm install and upgrade, and port forwarding. The prerequisite worth checking first is local tooling: kubectl must be on PATH with a valid kubeconfig, Helm v3 is needed for the chart tools, and cluster access comes from the machine running the server.

  Score 87.2: show every number behind it

  • Adoption96 / 100 · weight 40%
    • GitHub stars80
    • npm downloads84
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum61 / 100 · weight 14%
    • Stars gained, relative to size44
    • Stars gained, absolute53
    • npm download trend100
  • Tool quality56 / 100 · weight 13%
    • Tool description quality48
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  87.2

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  87.2

• 2

  kubernetes-mcp-server

  Community favourite

  containers/kubernetes-mcp-server ↗

  Best for: Managing Kubernetes or OpenShift resources without kubectl or helm: it provides native CRUD, pod, Helm, and Tekton operations directly against the Kubernetes API.

  It exposes MCP operations for Kubernetes and OpenShift resources, including generic CRUD, pod operations, namespace and event listing, OpenShift projects, Helm, and Tekton. It requires access to a Kubernetes cluster and reads the kubeconfig or in-cluster configuration.

  Score 86.4: show every number behind it

  • Adoption84 / 100 · weight 40%
    • GitHub stars84
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum79 / 100 · weight 14%
    • Stars gained, relative to size80
    • Stars gained, absolute79
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈68 / 100 · weight 13%
    • Tool description quality≈68
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  86.4

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  86.4

• 3

  Radar

  Community favourite

  skyhook-io/radar ↗

  Best for: Diagnosing a broken workload in a live Kubernetes cluster: tools such as diagnose, get_changes, get_events, get_topology, and get_pod_logs surface root causes and recent changes.

  Radar is an open-source Kubernetes observability and diagnostics MCP server that exposes 25 tools for cluster health, workload diagnosis, logs, events, topology, audit findings, changes, Helm and GitOps resources, RBAC permissions, and remediation actions. It assumes Kubernetes API access, using a local kubeconfig when run as a single binary on a laptop or an in-cluster Helm deployment for shared access.

  Score 74.2: show every number behind it

  • Adoption90 / 100 · weight 40%
    • GitHub stars90
    • npm downloadsnot measured
      npm publishes radar from zendesk/radar
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum100 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute100
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality93 / 100 · weight 13%
    • Tool description quality85
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  95.1

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  74.2

• 4

  Kubectl MCP Tool

  Community favourite

  rohitg00/kubectl-mcp-server ↗

  Best for: Crash-debugging a broken workload from an AI assistant: its README documents natural-language pod diagnosis plus RBAC and Secret security auditing.

  It runs as an MCP server that puts a Kubernetes cluster behind a chat interface, with the README documenting toolsets for core operations, Helm chart management, crash diagnosis, cost analysis, security auditing, and multi-cluster use, distributed via npx, pip/uvx, and Docker. Installation picks the runtime for the reader: the npx quick start assumes Node.js, while the pip and uvx routes are documented for Python 3.10 or newer, and the OAuth 2.1, read-only, and Secret-redaction options are documented as configuration rather than defaults.

  Score 73.6: show every number behind it

  • Adoption78 / 100 · weight 40%
    • GitHub stars75
    • npm downloads21
      downloads show none of the weekday rhythm human traffic has; halved
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance77 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade55
    • Commit cadence40
  • Momentum45 / 100 · weight 14%
    • Stars gained, relative to size25
    • Stars gained, absolute29
    • npm download trend100
  • Tool quality≈68 / 100 · weight 13%
    • Tool description quality≈68
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  73.6

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  73.6

• 5

  k8s-mcp-server

  Steady

  reza-gholizade/k8s-mcp-server ↗

  Best for: Kubernetes cluster operations that need both read and write access: it exposes resource discovery, listing, describe, logs, metrics, events, create/update, and delete tools.

  The server exposes Kubernetes API resource discovery, resource listing and details, kubectl-style descriptions, pod logs, node and pod metrics, event listing, and create/update/delete operations, with stdio, SSE, and streamable HTTP modes. Before choosing it, note that it requires Go 1.23 or later and access to a Kubernetes cluster with kubectl configured; HTTP modes also require a bearer token and bind to loopback by default.

  Score 69.4: show every number behind it

  • Adoption57 / 100 · weight 40%
    • GitHub stars57
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum35 / 100 · weight 14%
    • Stars gained, relative to size41
    • Stars gained, absolute26
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈68 / 100 · weight 13%
    • Tool description quality≈68
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  69.4

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  69.4

• 6

  kubeshark

  Community favourite

  kubeshark/kubeshark ↗

  Best for: Cluster-wide network root cause analysis for AI agents: it exposes an MCP interface to query traffic, investigate API calls, and use Kubernetes context.

  Kubeshark documents an MCP server, launched with kubeshark mcp, that lets AI agents query cluster-wide network traffic, investigate API calls, and perform root cause analysis with Kubernetes context. It assumes Kubeshark is installed and capturing cluster traffic, and the MCP server is started through the kubeshark CLI rather than an npm or PyPI package.

  Score 67.0: show every number behind it

  • Adoption100 / 100 · weight 40%
    • GitHub stars100
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance92 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade80
    • Commit cadence85
  • Momentum43 / 100 · weight 14%
    • Stars gained, relative to size26
    • Stars gained, absolute68
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈68 / 100 · weight 13%
    • Tool description quality≈68
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integrates100

  Weighted mean of the five

  85.9

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  67.0

• 7

  DevOps AI Toolkit

  Community favourite

  vfarcic/dot-ai ↗

  Best for: Kubernetes platform teams needing conversational operations: it provides MCP and CLI access for natural-language cluster querying, deployment recommendations, and remediation.

  It documents MCP and CLI access for natural-language cluster querying, deployment recommendations, remediation, pattern and policy management, documentation search, and shared prompt libraries. It assumes an MCP-capable assistant or the CLI, with setup documented through the complete stack or individual component installation.

  Score 58.5: show every number behind it

  • Adoption67 / 100 · weight 40%
    • GitHub stars63
    • npm downloads25
      downloads show none of the weekday rhythm human traffic has; halved
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum46 / 100 · weight 14%
    • Stars gained, relative to size31
    • Stars gained, absolute24
    • npm download trend100
  • Tool quality≈68 / 100 · weight 13%
    • Tool description quality≈68
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  75.0

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  58.5

• 8

  k8m

  Community favourite

  weibaohui/k8m ↗

  Best for: Multi-cluster Kubernetes teams needing MCP operations under each user's cluster permissions: k8m ties MCP calls to the invoking user's permissions and includes a management console.

  k8m provides a web dashboard for multi-cluster Kubernetes management and can act as an MCP server so other LLM clients can invoke its Kubernetes tools, with its README documenting logging of MCP calls. Before choosing it, note that it is deployed as a downloadable executable from GitHub releases rather than an npm or PyPI package, and it starts with default k8m/k8m credentials that should be changed.

  Score 58.4: show every number behind it

  • Adoption74 / 100 · weight 40%
    • GitHub stars74
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance97 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence85
  • Momentum31 / 100 · weight 14%
    • Stars gained, relative to size30
    • Stars gained, absolute33
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈68 / 100 · weight 13%
    • Tool description quality≈68
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  74.9

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  58.4

• 9

  ContextForge MCP Gateway

  Community favourite

  IBM/mcp-context-forge ↗

  Best for: Teams running MCP servers across multiple clusters: it federates MCP, REST and A2A backends behind one endpoint with Redis-backed federation and OpenTelemetry tracing.

  ContextForge is a gateway and registry that proxies MCP servers, A2A agents and REST or gRPC APIs into a single endpoint, with admin and web UIs plus OpenTelemetry tracing to OTLP backends such as Phoenix, Jaeger and Zipkin. It ships as a PyPI package or Docker image that the operator runs themselves, and multi-cluster Kubernetes federation assumes Redis for caching and federation, so it fronts and governs other servers rather than serving as a Kubernetes toolset itself.

  Score 55.4: show every number behind it

  • Adoption98 / 100 · weight 40%
    • GitHub stars92
    • PyPI downloads41
      PyPI downloads show no weekday rhythm; halved
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum81 / 100 · weight 14%
    • Stars gained, relative to size76
    • Stars gained, absolute90
    • PyPI download trend77
  • Tool quality≈68 / 100 · weight 13%
    • Tool description quality≈68
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integrates100

  Weighted mean of the five

  92.3

  × relevance: the keyword is tagged here

  0.60

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  55.4

• 10

  Maintenant

  Community favourite

  kOlapsis/maintenant ↗

  Best for: A self-hosted Docker or Kubernetes host the agent runs beside: 51 tools expose container, pod, node, alert and certificate state.

  Maintenant is a monitoring server deployed as a container or binary next to the workload, and its 51 MCP tools let an agent read container, Kubernetes pod, node and workload, endpoint, certificate, heartbeat, CVE and alert state, while also creating channels, triggers, escalation policies, incidents and maintenance windows. It only reaches the local instance it is installed beside, so it cannot see online deployments, and several tools (escalation policies, incidents, maintenance windows, security posture, remote agents) require the Personal or Pro edition, which get_edition reports along with quota usage.

  Score 53.9: show every number behind it

  • Adoption68 / 100 · weight 40%
    • GitHub stars68
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum≈0 / 100 · weight 14%
    • Stars gained, relative to sizenot measured
      no snapshot history yet
    • Stars gained, absolutenot measured
      no snapshot history yet
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality68 / 100 · weight 13%
    • Tool description quality60
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  69.1

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  53.9

• 11

  mcp-k8s-go

  Abandoned but popular

  strowk/mcp-k8s-go ↗

  Best for: Managing Kubernetes resources from an MCP client: it exposes tools to list, get, create, and modify Kubernetes resources.

  mcp-k8s-go is an MCP server for Kubernetes that documents tools for listing contexts and namespaces, listing, getting, creating, and modifying resources, retrieving events and pod logs, and running commands in pods. Before choosing it, note that the selected installation path requires Node.js, Golang, or Docker.

  Score 51.2: show every number behind it

  • Adoption65 / 100 · weight 40%
    • GitHub stars65
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance32 / 100 · weight 24%
    • Last commit touching this server42
    • Repository maintenance grade30
    • Commit cadence5
  • Momentum0 / 100 · weight 14%
    • Stars gained, relative to size0
    • Stars gained, absolute0
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈68 / 100 · weight 13%
    • Tool description quality≈68
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  51.2

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  51.2

• 12

  ArcadeDB Multi-Model DBMS

  Community favourite

  ArcadeData/arcadedb ↗

  Best for: Administering ArcadeDB through an MCP client: it exposes 10 tools for database listing, schema inspection, read-only queries, writes, server status, profiling, and runtime settings.

  ArcadeDB Multi-Model DBMS is exposed through 10 MCP tools for listing databases, inspecting schemas, running read-only queries and write commands, checking server status, profiling queries, and reading or updating server settings. No npm package is published and no PyPI package is attributed, so npm and PyPI are not documented install routes.

  Score 50.9: show every number behind it

  • Adoption77 / 100 · weight 40%
    • GitHub stars77
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum75 / 100 · weight 14%
    • Stars gained, relative to size79
    • Stars gained, absolute69
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality81 / 100 · weight 13%
    • Tool description quality73
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integrates100

  Weighted mean of the five

  84.8

  × relevance: the keyword is tagged here

  0.60

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  50.9

• 13

  Duckle MCP Server

  Community favourite

  slothflowlabs/duckle ↗

  Best for: Authoring and validating Duckle pipelines from an MCP client: it supports catalog and schema browsing, pipeline generation, compile-only validation, headless runs, and run logs.

  Duckle is a self-hosted open-source ETL platform whose bundled MCP server lets Claude browse component and property schemas, generate pipelines into a chosen working directory, compile-validate them, run them headlessly, and read existing pipelines and run logs. Before choosing it, note that no npm package is published and no PyPI package is attributed, so the MCP server comes with the Duckle platform rather than as a standalone package.

  Score 50.8: show every number behind it

  • Adoption80 / 100 · weight 40%
    • GitHub stars80
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum79 / 100 · weight 14%
    • Stars gained, relative to size82
    • Stars gained, absolute74
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈68 / 100 · weight 13%
    • Tool description quality≈68
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  84.7

  × relevance: the keyword is tagged here

  0.60

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  50.8

• 14

  argocd-mcp

  Community favourite

  argoproj-labs/mcp-for-argocd ↗

  Best for: Argo CD users needing an AI assistant to inspect and operate applications: it exposes 14 tools for application, resource, log, event, sync, and action management.

  argocd-mcp exposes 14 tools for listing, inspecting, creating, updating, deleting, and syncing Argo CD applications, plus retrieving resource trees, managed resources, manifests, workload logs, events, and resource actions. It assumes a reachable Argo CD instance with API access and requires ARGOCD_BASE_URL and ARGOCD_API_TOKEN to be configured.

  Score 50.0: show every number behind it

  • Adoption100 / 100 · weight 40%
    • GitHub stars70
    • npm downloads93
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance77 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade55
    • Commit cadence40
  • Momentum62 / 100 · weight 14%
    • Stars gained, relative to size72
    • Stars gained, absolute56
    • npm download trend50
  • Tool quality56 / 100 · weight 13%
    • Tool description quality48
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integrates100

  Weighted mean of the five

  83.3

  × relevance: the keyword is tagged here

  0.60

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  50.0

• 15

  ack-mcp-server

  Abandoned but popular

  aliyun/alibabacloud-ack-mcp-server ↗

  Best for: Managing Alibaba Cloud ACK clusters from an AI assistant: it documents ACK resource queries, kubectl operations, Prometheus and control-plane log queries, and diagnostics.

  The server documents tools for ACK cluster queries, kubectl-style operations, Prometheus metric queries, control-plane SLS log queries, audit log queries, resource diagnosis, and health inspection reports, and it can be deployed via Helm, Docker, or a binary. Before choosing it, note that it requires an Alibaba Cloud ACK environment and a RAM sub-account with read-only CS, log, and ARMS Prometheus permissions plus suitable Kubernetes RBAC.

  Score 47.2: show every number behind it

  • Adoption57 / 100 · weight 40%
    • GitHub stars52
    • PyPI downloads31
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance63 / 100 · weight 24%
    • Last commit touching this server88
    • Repository maintenance grade55
    • Commit cadence5
  • Momentum35 / 100 · weight 14%
    • Stars gained, relative to size42
    • Stars gained, absolute24
    • PyPI download trendnot measured
      no download history for the selected registry
  • Tool quality≈68 / 100 · weight 13%
    • Tool description quality≈68
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integrates100

  Weighted mean of the five

  60.5

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  47.2

• 16

  qzcli

  Steady

  tianyilt/qzcli_tool ↗

  Best for: Managing OpenI/启智 platform resources from Claude or Codex: it documents an MCP server, qzcli-mcp, for login, node queries, job submission, and logs.

  The project documents a kubectl/docker-style qzcli CLI and an MCP server, qzcli-mcp, which is registered with Codex or Claude Code and covers OpenI/启智 platform login, resource discovery, node availability, job submission, and logs. Before choosing it, note that it is installed locally as a Python package, requires the qzcli-mcp executable on PATH, and needs OpenI/启智 platform authentication via CAS credentials or a cookie.

  Score 46.9: show every number behind it

  • Adoption54 / 100 · weight 40%
    • GitHub stars54
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum53 / 100 · weight 14%
    • Stars gained, relative to size64
    • Stars gained, absolute37
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈68 / 100 · weight 13%
    • Tool description quality≈68
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  70.7

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  46.9

• 17

  cloud-finops-mcp

  Steady

  OptimNow/cloud-finops-skills ↗

  Best for: Splitting the cost of a shared Kubernetes cluster between teams: its reference tools return allocation and chargeback guidance rather than cluster operations.

  It exposes seven read-only tools: list, get and find over FinOps references and waste-pattern playbooks, plus one that fetches the current value of a dated figure a reference quotes. It cannot see your cloud account, so a question about your own resources comes back as a detection query the reader runs, and no npm package is published, so installation is not through a package manager.

  Score 46.9: show every number behind it

  • Adoption46 / 100 · weight 40%
    • GitHub stars46
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum46 / 100 · weight 14%
    • Stars gained, relative to size58
    • Stars gained, absolute29
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality100 / 100 · weight 13%
    • Tool description quality93
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  70.7

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  46.9

• 18

  Containarium-Cloud

  Community favourite

  FootprintAI/Containarium ↗

  Best for: When AI agents need persistent, SSH-reachable LXC sandboxes on Kubernetes or a VM, it documents an MCP admin surface and an in-box shell_exec MCP server.

  Containarium documents a CLI for creating LXC sandbox boxes, syncing SSH configuration, and exposing ports, plus an MCP admin surface and a second MCP server inside the box for shell_exec and file edits. Before choosing it, note that the documented quickstart requires a fresh Ubuntu 24.04 VM with sudo access, even though the README names Kubernetes and LXC as supported runtimes.

  Score 45.6: show every number behind it

  • Adoption63 / 100 · weight 40%
    • GitHub stars63
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum65 / 100 · weight 14%
    • Stars gained, relative to size76
    • Stars gained, absolute49
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈68 / 100 · weight 13%
    • Tool description quality≈68
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  76.0

  × relevance: the keyword is tagged here

  0.60

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  45.6

• 19

  Kubeflow MCP Server

  Steady

  kubeflow/mcp-server ↗

  Best for: Teams running Kubeflow Trainer on Kubernetes: it exposes Kubeflow Training operations as MCP tools, including preview-before-submit confirmation for mutating actions.

  The README documents a Python package, kubeflow-mcp, installed from PyPI and run with kubeflow-mcp serve (or Docker), exposing Kubeflow Training operations as MCP tools for planning, submitting, monitoring, and managing training jobs. It assumes a running Kubernetes cluster with Kubeflow Trainer installed, its CRDs and at least one ClusterTrainingRuntime, plus kubectl and a kubeconfig configured for the target cluster.

  Score 45.5: show every number behind it

  • Adoption44 / 100 · weight 40%
    • GitHub stars44
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum65 / 100 · weight 14%
    • Stars gained, relative to size82
    • Stars gained, absolute39
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈68 / 100 · weight 13%
    • Tool description quality≈68
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integrates100

  Weighted mean of the five

  68.6

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  45.5

• 20

  Pronounce / pronounce-mcp

  Steady

  anzy-renlab-ai/pronounce ↗

  Best for: Before a Kubernetes stand-up when unsure about kubectl, nginx, or JWT: it exposes pronunciation lookup, search, and list tools with IPA and respelling.

  Pronounce exposes three MCP tools for developer-term pronunciation: pronounce returns IPA, respelling, source citation, and confidence; search_pronunciations matches partial words or categories; and list_pronunciations lists entries, optionally filtered by category. It is not a Kubernetes operations server: its tools only perform pronunciation lookup, search, and listing.

  Score 44.8: show every number behind it

  • Adoption42 / 100 · weight 40%
    • GitHub stars42
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance90 / 100 · weight 24%
    • Last commit touching this server88
    • Repository maintenance grade100
    • Commit cadence85
  • Momentum62 / 100 · weight 14%
    • Stars gained, relative to size79
    • Stars gained, absolute37
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality88 / 100 · weight 13%
    • Tool description quality80
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  67.6

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  44.8

Questions people ask

Other comparisons

• Best Figma MCP servers
• Best Obsidian MCP servers
• Best YouTube MCP servers
• Best Jira MCP servers
• Best PostgreSQL MCP servers
• Best MySQL MCP servers
• Best GitHub MCP servers
• Best Notion MCP servers
• Best Linear MCP servers
• Best Discord MCP servers
• Best MongoDB MCP servers
• Best CRM MCP servers
• Best Payments MCP servers
• Best Ecommerce MCP servers
• Best Social Media MCP servers
• Best Browser Automation MCP servers
• Best Email MCP servers
• Best PDF MCP servers
• Best Docker MCP servers
• Best AWS MCP servers
• Best Spreadsheets MCP servers
• Best SEO MCP servers
• Best Web Search MCP servers
• Best Web Scraping MCP servers
• Best Vector Database MCP servers
• Best Code Execution MCP servers
• Best Calendar MCP servers
• Best Observability MCP servers
• Best Image Generation MCP servers
• Best Speech & Transcription MCP servers
• Best Maps MCP servers
• Best Travel MCP servers
• Best Stock Market MCP servers
• Best Web Analytics MCP servers
• Best Memory MCP servers
• Best Documentation MCP servers
• Best Security MCP servers