MCP.Market

Ocm MCP server

by ocm-mcp-server·io.github.ocm-mcp-server/ocm-mcp-server·v0.6.0·16 stars

Guardrailed fleet ops for AI agents: multi-cluster Kubernetes via OCM with policy, approval, audit.

B83/100grade B
What users say
No reviews yet
Be the first
Safety scan
B83/100

full report

Adoption
Growing

16 stars51 downloads/wk

Reviews

Write one

Nobody has reviewed Ocm yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Ocm tools (36, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • apply_cluster_action

    Apply a previously proposed cluster lifecycle action. Requires a human-minted token.

  • apply_manifestwork

    Apply a previously proposed ManifestWork. Requires a human-minted approval token.

  • compute
  • get_addon_health

    Per-cluster add-on health across the fleet (ManagedClusterAddOn Available / Degraded).

  • get_audit_trail

    Return the last N entries of this server's own tool-call audit log.

  • get_cluster

    Full view of one ManagedCluster.

  • get_cluster_health

    Health summary for one cluster: hub conditions, unhealthy pods, degraded deployments.

  • get_cluster_info

    Extended inventory for one cluster from the hub: OpenShift version, nodes, console URL.

  • get_fleet_health

    Health of the WHOLE fleet in one call: hub conditions for every cluster plus concurrent pod/deployment scans of each spoke that has a read context.

  • get_hosted_cluster

    Detailed HostedCluster: version, conditions, and its NodePools.

  • get_manifestwork

    Detailed ManifestWork status: top-level conditions and per-resource status feedback.

  • get_placement_decision

    Which clusters a Placement actually selected (reads its PlacementDecisions).

  • get_pod_logs

    Tail logs from a pod on a managed cluster.

  • get_resource

    Generic get of one allow-listed OCM resource, in full.

  • list_addon_placement_scores

    List AddOnPlacementScores in a cluster's namespace (custom scores prioritizers consume).

  • list_addons_for_cluster

    Every add-on installed on one cluster, with health (ManagedClusterAddOn in its namespace).

  • list_cluster_claims

    Every cluster's ClusterClaims (id, platform, region, version) rolled up from status.

  • list_cluster_management_addons

    List fleet-level add-on definitions (ClusterManagementAddOn) and their install strategy.

  • list_cluster_set_bindings

    List ManagedClusterSetBindings (which ClusterSets a namespace's Placements may use).

  • list_cluster_sets

    List ManagedClusterSets with their selector type and member clusters.

  • list_clusters

    List all managed clusters with availability, version, labels, and capacity.

  • list_hosted_clusters

    List HyperShift HostedClusters, when the hub is the HCP hosting cluster.

  • list_manifestworkreplicasets

    List ManifestWorkReplicaSets (a template fanned across a Placement) with rollout summary.

  • list_manifestworks

    List ManifestWorks targeting a cluster (what the hub is managing there).

  • list_node_pools

    List HyperShift NodePools (worker groups), optionally filtered to one HostedCluster.

  • list_pending_csrs

    List pending cluster-join / add-on registration CSRs awaiting hub approval.

  • list_pending_proposals

    List proposals (ManifestWorks and cluster actions) waiting for human approval.

  • list_placements

    List Placements and how many clusters each currently selects.

  • list_policies

    List governance Policies and per-cluster compliance (only if the add-on is installed).

  • list_policy_violations

    Only the NonCompliant / Pending Policy-cluster pairs across the fleet - the open risks.

  • list_resources

    Generic list over an allow-list of OCM API types (identity + conditions only).

  • propose_cluster_action

    Propose an OCM cluster lifecycle action. Does NOT apply anything.

  • propose_manifestwork

    Propose a change to one cluster as an OCM ManifestWork. Does NOT apply anything.

  • propose_rollback

    Propose rolling back an applied ManifestWork. Applies nothing; needs its own approval.

  • query_events

    Recent Kubernetes events from a managed cluster, newest first.

  • rollback_manifestworkwrite action

    Delete a ManifestWork after a rollback proposal has been approved.

Public scan report

scanner v0.1.10 · 2026-10-30 · same rubric, same numbers if you re-run it

1 medium
  • Code scan57 source files scanned20/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 20 days ago15/15
  • Maintainer identityregistry namespace matches repository owner7/10

Findings (1)

  • mediumsubprocess with shell=Trueexec.shell-true
    ocm_mcp_server-0.6.0/eval/run_eval.py: … return subprocess.run( cmd, shell=True, capture_output=True, text=True, timeou…
Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Ocm compares

Against every graded Developer tools MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
83/100
higher than 65% of 1,119 Developer tools servers
Tools
36
the typical Developer tools server has 7
Tools that change things
3%
typical: 5%. Fewer write tools means less an agent can break
GitHub stars
16
more than 86% of 856 Developer tools servers
Downloads a week
51
more than 37% of 442 Developer tools servers with a package

What its tools let an agent do: 33 read · 1 change · 2 run or deploy

Install Ocm in Claude Code, Cursor or VS Code

claude mcp add ocm-mcp-server -- uvx ocm-mcp-server
Add to Cursor

What the publisher says

From the Ocm repository's README, as published. We do not edit it. Read it on GitHub

<!-- mcp-name: io.github.ocm-mcp-server/ocm-mcp-server -->

🛡️ ocm-mcp-server

📖 Read the docs site → ocm-mcp-server.github.io

Star us&nbsp;❤️&nbsp;→&nbsp;

AgentOps for Kubernetes fleets, done safely.

An MCP server that lets AI agents operate a multi-cluster Kubernetes fleet through an Open Cluster Management hub, with policy, approval, and audit between the model and your clusters.

The agent never holds a kubeconfig. Every write is policy-checked, human-approved, and traced.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Ocm: common questions

Is Ocm MCP server safe?
Mostly: it is graded B (83/100). Read the Ocm safety report
How do I install Ocm?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Ocm need an API key?
No secret keys are declared. It reads 6 settings from the environment.
Is Ocm maintained?
The last commit was 26 days ago (2026-10-10). The latest release is v0.6.0.
What can I use instead of Ocm?
Servers from other publishers that do the same job: Nora MCP server, KSail MCP server and Kubently MCP server. Compare all Ocm alternatives.
How does Ocm compare with other Developer tools MCP servers?
safety score 83/100 (higher than 65% of 1,119 Developer tools servers); tools 36 (the typical Developer tools server has 7); tools that change things 3% (typical: 5%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Ocm

Same job from other publishers: the closest match first, then the best rated.

All Ocm alternatives →
  • Nora
    Operate self-hosted OpenClaw and Hermes agent fleets on Docker or Kubernetes from MCP clients.
    B
  • KSail
    SDK for creating, managing, and operating Kubernetes clusters and workloads with ease.
    A
  • Kubently
    Troubleshoot Kubernetes agentically: natural-language cluster diagnosis via ask_kubently
    B
  • Strimzi Kafka CLI
    Manage Apache Kafka on Kubernetes via Strimzi. Clusters, topics, users, connectors, MM2.
    A
  • Kubeview
    Read-only Model Context Protocol MCP server enabling code-driven AI analysis of Kubernetes clusters.
    B