Server providing Argo CD integration for MCP clients.
Nothing to run from here
Cloud DevOps is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
94/100
trust score
20
downloads a day
local
runs on your machine
3k
downloads in 30d
What it does
Cloud DevOps analysis plus opt-in Git, Terraform, Kubernetes and multi-cloud inventory.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user cloud-devops-mcp '--' npx -y cloud-devops-mcp-server
# 2 — ask your agent for something these tools do
# assess_terraform_change, assess_cloud_change_bundle, build_incident_runbook and 54 more
Cloud DevOps costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
PublisherVerified · since 2026
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Cloud DevOps as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user cloud-devops-mcp '--' npx -y cloud-devops-mcp-serverReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
57 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Evaluate Terraform/IaC release risk using plan evidence plus change-governance facts such as rollback, peer review and stateful impact. Use this for overall change/release decisions; for security-only inspection of a raw Terraform plan, use review_terraform_security. It analyzes supplied evidence…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| changedResources | array | no | Infrastructure resource classes changed by the pull request or deployment. |
| terraformPlanJson | string | no | Optional raw Terraform plan JSON. When supplied, the server derives resource classes and evidence. |
| includesIamChanges | boolean | no | Whether the change adds, removes or modifies IAM permissions, roles or policies. |
| includesPublicIngress | boolean | no | Whether the change introduces or modifies internet-accessible ingress or public network exposure. |
| modifiesStatefulResources | boolean | no | Whether databases, persistent volumes or other stateful resources are changed or replaced. |
| hasRollbackPlan | boolean | no | Whether a documented rollback or recovery path exists for this change. |
| hasPeerReview | boolean | no | Whether another qualified reviewer has reviewed the proposed change. |
| hasTerraformPlan | boolean | no | Whether a Terraform plan artifact was generated and reviewed for this change. |
Correlate evidence from at least two domains (Terraform, IAM, Kubernetes, GitHub Actions) into one deployment-risk assessment and identify cross-domain change paths. Use domain-specific review tools when only one evidence domain is available. It analyzes caller-supplied artifacts only and does not…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| changeName | string | yes | Name or identifier for the cloud change bundle being assessed. |
| environment | string | yes | Target deployment environment; production increases the consequence of correlated risk. |
| terraform | object | no | Optional Terraform evidence domain. Supply this plus at least one other domain for cross-domain assessment. |
| iamPolicies | array | no | Optional IAM evidence domain with up to 10 policies; combine with at least one other domain. |
| kubernetesWorkloads | array | no | Optional Kubernetes evidence domain with up to 10 workloads; combine with at least one other domain. |
| githubWorkflows | array | no | Optional GitHub Actions evidence domain with up to 10 workflows; combine with at least one other domain. |
Generate a practical incident-response runbook from a known service symptom, severity, environment and optional signals. Use this to structure response actions and evidence collection; do not use it to fetch or diagnose from live telemetry. It does not execute remediation or make changes to the…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| service | string | yes | Service or application name affected by the incident. |
| environment | string | yes | Environment where the symptom is occurring. |
| severity | string | yes | Incident severity used to scale response urgency and communications. |
| symptom | string | yes | Observed user-facing or operational symptom to build the runbook around. |
| signals | array | no | Optional known alerts, metrics, logs or traces that should guide triage. |
Evaluate generic CI/CD production-readiness controls from structured pipeline facts, separating missing evidence from failed controls. Use this for platform-agnostic delivery process review; for raw GitHub Actions YAML, use review_github_actions_workflow. It is analysis-only and does not trigger…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pipelineName | string | yes | Human-readable name of the CI/CD pipeline being reviewed. |
| deploymentStrategy | string | yes | Primary deployment strategy used to release changes. |
| environments | array | yes | Deployment environments handled by the pipeline, for example dev, staging and production. |
| hasAutomatedTests | boolean | no | Whether automated tests run as a release gate. |
| hasSecurityScan | boolean | no | Whether the pipeline performs automated security scanning before deployment. |
| hasRollback | boolean | no | Whether the pipeline has a defined rollback or recovery mechanism. |
| hasArtifactVersioning | boolean | no | Whether build artifacts are immutable and versioned for traceability. |
| hasManualApprovalForProduction | boolean | no | Whether production deployment requires an explicit human approval gate. |
Calculate remaining SLO downtime budget and, when request counts are supplied, remaining failed-request budget for a fixed period. Use this as a deterministic budget calculator; do not use it to fetch monitoring data or forecast reliability. It performs no external calls and changes no service…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sloTargetPercent | number | yes | Target service availability percentage for the measurement period, such as 99.9. |
| periodDays | integer | yes | Length of the SLO measurement period in calendar days. |
| observedDowntimeMinutes | number | yes | Downtime already observed during the measurement period, in minutes. |
| requestVolume | integer | no | Optional total request count for calculating a request-failure error budget. |
| failedRequests | integer | no | Optional failed request count; provide together with requestVolume. |
Evaluate AWS IAM policy risk from structured facts or raw policy JSON, including wildcard scope, privilege-escalation actions and conditions. Use this for AWS IAM operational risk; for provider-specific AWS/Azure/GCP policy-pack checks, use review_cloud_identity_policy. It analyzes supplied policy…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| policyName | string | yes | Name of the AWS IAM policy being assessed. |
| actions | array | no | Explicit allowed IAM actions when raw policy JSON is not supplied. |
| resources | array | no | Explicit IAM resource ARNs or patterns when raw policy JSON is not supplied. |
| policyJson | string | no | Raw AWS IAM policy JSON. When supplied, the server derives actions, resources, wildcard scope and privilege-escalation evidence. |
| hasWildcardActions | boolean | no | Whether the policy permits wildcard actions such as * or service:* patterns. |
| hasWildcardResources | boolean | no | Whether the policy grants permissions against wildcard resources. |
| allowsPrivilegeEscalationActions | boolean | no | Whether the policy contains actions that can enable privilege escalation. |
| hasConditionBlocks | boolean | no | Whether policy statements include Condition constraints that narrow access. |
| usedByProduction | boolean | no | Whether the policy is attached to or used by production identities or workloads. |
Evaluate Kubernetes workload production readiness and reliability from structured facts or multi-document YAML, including probes, resources, replicas, disruption protection and exposure. Use this for deployability/readiness; for workload security hardening, use review_kubernetes_security. It…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workloadName | string | no | Workload name when raw manifest YAML is not the only source of identity. |
| namespace | string | no | Kubernetes namespace containing the workload. |
| replicas | integer | no | Configured replica count used to assess availability and redundancy. |
| manifestYaml | string | no | Deployment, StatefulSet or DaemonSet YAML, optionally with Service, Ingress and PodDisruptionBudget documents. |
| hasReadinessProbe | boolean | no | Whether workload containers define readiness probes. |
| hasLivenessProbe | boolean | no | Whether workload containers define liveness probes. |
| hasResourceRequests | boolean | no | Whether workload containers define CPU or memory requests. |
| hasResourceLimits | boolean | no | Whether workload containers define CPU or memory limits. |
| hasPodDisruptionBudget | boolean | no | Whether a PodDisruptionBudget protects workload availability during voluntary disruption. |
| usesLatestTag | boolean | no | Whether any container image uses the mutable latest tag. |
| runsAsRoot | boolean | no | Whether the workload is configured to run containers as root. |
| exposesPublicService | boolean | no | Whether the workload is exposed through a public Service or ingress path. |
Evaluate GitHub Actions workflow security and deployment readiness from structured facts or raw workflow YAML, including triggers, action pinning, token permissions, caching, environment protection and concurrency. Use review_cicd_pipeline for generic non-GitHub delivery-process review. It…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workflowName | string | yes | Human-readable name of the GitHub Actions workflow being reviewed. |
| workflowYaml | string | no | Raw GitHub Actions workflow YAML. The server derives triggers, action pinning, token permissions, caching and concurrency. |
| triggers | array | no | Workflow trigger events when raw YAML is not supplied, such as push, pull_request or workflow_dispatch. |
| deploysToProduction | boolean | no | Whether the workflow can deploy directly or indirectly to production. |
| usesPinnedActions | boolean | no | Whether third-party actions are pinned to immutable commit SHAs. |
| hasLeastPrivilegePermissions | boolean | no | Whether GITHUB_TOKEN permissions are explicitly restricted to least privilege. |
| hasSecretScanning | boolean | no | Whether the workflow or surrounding delivery process performs automated secret scanning. |
| hasDependencyCaching | boolean | no | Whether dependency caching is configured for repeatable and efficient builds. |
| hasEnvironmentProtection | boolean | no | Whether protected GitHub environments or equivalent approval controls guard production deployments. |
| hasConcurrencyControl | boolean | no | Whether concurrency settings prevent overlapping or conflicting workflow runs. |
Apply deterministic provider-specific identity policy packs to raw AWS IAM, Azure RBAC or GCP IAM policy documents. Use this for cross-cloud identity security analysis; use review_iam_policy when assessing AWS IAM from mixed structured facts or policy JSON. It analyzes supplied policy JSON only…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | yes | Cloud provider whose identity policy syntax and policy pack should be applied. |
| policyName | string | yes | Name or identifier of the identity policy being reviewed. |
| policyJson | string | yes | Raw provider policy document in JSON form; AWS IAM, Azure role definition/assignment data, or GCP IAM policy. |
| environment | string | no | Optional deployment environment used to contextualize policy risk; defaults are handled by the policy pack. |
Inspect raw Terraform plan JSON for security-relevant changes such as destructive actions, public exposure, encryption gaps, deletion protection and IAM wildcard risk. Use this for Terraform security posture; use assess_terraform_change for broader release/change risk and governance. It parses the…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| terraformPlanJson | string | yes | Raw Terraform plan JSON, typically produced by terraform show -json, to inspect for security-relevant resource changes. |
| environment | string | no | Optional target environment used to contextualize the severity of findings. |
Apply Kubernetes workload security rules to manifest YAML for privileged mode, host access, Linux capabilities, service accounts, seccomp, filesystem settings and network policy. Use this for security hardening; use review_kubernetes_deployment for reliability and production-readiness checks. It…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| manifestYaml | string | yes | Raw multi-document Kubernetes YAML containing workloads and related policy objects to evaluate for security hardening. |
| environment | string | no | Optional target environment used to contextualize security findings. |
Correlate CycloneDX/SPDX SBOM quality with CI action pinning, Kubernetes image immutability, artifact signing and build provenance to assess software-supply-chain risk. Use this when an SBOM is available and supply-chain evidence needs to be evaluated together. It analyzes supplied artifacts only…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sbomJson | string | yes | CycloneDX or SPDX SBOM JSON used as the primary software-supply-chain evidence. |
| workflowYaml | string | no | Optional GitHub Actions workflow YAML used to inspect action pinning and build controls. |
| kubernetesManifestYaml | string | no | Optional Kubernetes manifest YAML used to inspect runtime image immutability. |
| artifactSigned | boolean | no | Whether released artifacts or images are cryptographically signed. |
| hasProvenance | boolean | no | Whether verifiable build provenance or attestation is produced for released artifacts. |
| environment | string | no | Optional target environment used to contextualize supply-chain risk. |
Inspect an allowlisted local repository without modifying it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repositoryPath | string | yes | — |
Fetch remote refs for an allowlisted repository using an allowlisted remote.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repositoryPath | string | yes | — |
| remote | string | no | — |
| prune | boolean | no | — |
Pull the currently checked-out branch with --ff-only. Dirty working trees are rejected.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repositoryPath | string | yes | — |
| remote | string | no | — |
| branch | string | no | — |
Create and switch to an allowlisted non-protected branch from an approved local repository.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repositoryPath | string | yes | — |
| branch | string | yes | — |
| startPoint | string | no | — |
Stage only explicitly named repository paths and commit them on a non-protected branch. Supports dry-run preview.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repositoryPath | string | yes | — |
| files | array | yes | — |
| message | string | yes | — |
| dryRun | boolean | no | — |
Push only the current non-protected branch to an allowlisted remote. Force-push is never used. Supports dry-run.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repositoryPath | string | yes | — |
| remote | string | no | — |
| dryRun | boolean | no | — |
Create a pull request from the current non-protected branch in an explicitly allowlisted GitHub repository.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repositoryPath | string | yes | — |
| title | string | yes | — |
| body | string | no | — |
| base | string | no | — |
| draft | boolean | no | — |
Inspect pull request mergeability and GitHub Actions check runs for an allowlisted repository.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repositoryPath | string | yes | — |
| pullRequestNumber | integer | yes | — |
Merge an open PR only after CI checks pass and confirm is exactly MERGE. Direct protected-branch pushes remain blocked.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repositoryPath | string | yes | — |
| pullRequestNumber | integer | yes | — |
| confirm | string | yes | — |
| method | string | no | — |
Dispatch only an explicitly allowlisted GitHub Actions workflow. confirm must be exactly TRIGGER.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repositoryPath | string | yes | — |
| workflow | string | yes | — |
| ref | string | yes | — |
| inputs | object | no | — |
| confirm | string | yes | — |
Run terraform fmt in check-only mode inside an allowlisted repository. It never rewrites Terraform files.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repositoryPath | string | yes | — |
| workingDirectory | string | no | — |
Run terraform validate -json inside an allowlisted repository and return bounded diagnostics. It does not initialize providers, plan or apply infrastructure.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repositoryPath | string | yes | — |
| workingDirectory | string | no | — |
Run a non-apply Terraform plan with refresh disabled and return only a change summary. The tool never exposes full plan JSON and never runs terraform apply.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repositoryPath | string | yes | — |
| workingDirectory | string | no | — |
| varFiles | array | no | — |
Read the current kubectl context and require it to match the configured context allowlist before returning it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repositoryPath | string | yes | — |
Read bounded metadata and status summaries for allowlisted Kubernetes resource types, contexts and namespaces. Secrets and arbitrary resource types are not exposed.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repositoryPath | string | yes | — |
| context | string | yes | — |
| resource | string | yes | — |
| namespace | string | no | — |
| name | string | no | — |
| labelSelector | string | no | — |
Read rollout readiness for an allowlisted Deployment, StatefulSet or DaemonSet without watching indefinitely or mutating the cluster.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repositoryPath | string | yes | — |
| context | string | yes | — |
| namespace | string | yes | — |
| kind | string | yes | — |
| name | string | yes | — |
Verify the active allowlisted AWS, Azure or GCP identity/scope before live reads. No credentials or tokens are returned.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | yes | — |
| region | string | no | — |
| profile | string | no | — |
| subscriptionId | string | no | — |
| projectId | string | no | — |
Read a bounded live resource inventory from an explicitly allowlisted AWS account/region, Azure subscription or GCP project.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | yes | — |
| region | string | no | — |
| profile | string | no | — |
| subscriptionId | string | no | — |
| projectId | string | no | — |
List EKS, AKS or GKE clusters from an explicitly allowlisted cloud scope without changing cluster or cloud state.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | yes | — |
| region | string | no | — |
| profile | string | no | — |
| subscriptionId | string | no | — |
| projectId | string | no | — |
Read bounded observability configuration signals: CloudWatch alarms, Azure metric alerts or GCP logging sinks.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | yes | — |
| region | string | no | — |
| profile | string | no | — |
| subscriptionId | string | no | — |
| projectId | string | no | — |
Identify bounded, read-only cost-waste signals such as unattached disks/volumes and unassociated static public IPs in an allowlisted cloud scope.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | yes | — |
| region | string | no | — |
| profile | string | no | — |
| subscriptionId | string | no | — |
| projectId | string | no | — |
Compare expected resource identifiers with the bounded live inventory of an allowlisted cloud scope. It reports drift only and never reconciles resources.
No parameter schema on file.
Run a bounded, read-only PromQL instant or range query against an explicitly allowlisted Prometheus-compatible endpoint and return normalized series summaries.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| baseUrl | string | yes | Allowlisted Prometheus base URL. |
| query | string | yes | PromQL query to execute. |
| startTime | number | no | Optional range start as Unix seconds; provide with endTime. |
| endTime | number | no | Optional range end as Unix seconds; provide with startTime. |
| stepSeconds | number | no | Range-query step in seconds. |
Read a bounded summary of Grafana managed alert rules and active alerts from an explicitly allowlisted Grafana endpoint without changing alert configuration.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| baseUrl | string | yes | Allowlisted Grafana base URL. |
Run a bounded AWS CloudWatch Logs Insights query against an explicitly allowlisted account, region and log group. It only reads query results and never changes logging resources.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| region | string | yes | Allowlisted AWS region. |
| profile | string | no | Optional allowlisted AWS CLI profile. |
| logGroup | string | yes | Allowlisted CloudWatch Logs log group. |
| queryString | string | yes | CloudWatch Logs Insights query string. |
| startTime | integer | yes | Query start as Unix seconds. |
| endTime | integer | yes | Query end as Unix seconds. |
| limit | integer | no | Maximum rows to return, up to 100. |
Read bounded pod health for an explicitly allowlisted Kubernetes context and namespace, including readiness, restart and unhealthy-state summaries without cluster mutation.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| context | string | yes | Allowlisted kubectl context. |
| namespace | string | yes | Allowlisted Kubernetes namespace. |
| labelSelector | string | no | Optional bounded Kubernetes label selector. |
Inspect failed jobs and bounded job logs for one GitHub Actions run in an explicitly allowlisted repository and classify likely failure categories without rerunning or changing the workflow.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repository | string | yes | Allowlisted GitHub repository in owner/name form. |
| runId | integer | yes | GitHub Actions workflow run ID. |
Correlate supplied metrics, logs, alerts, Kubernetes health and CI/CD evidence into deterministic incident relationships and identify missing evidence needed for triage.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| service | string | yes | Service or workload being investigated. |
| metrics | array | no | Optional metric signals. |
| logs | array | no | Optional log signals. |
| alerts | array | no | Optional alert signals. |
| kubernetes | array | no | Optional Kubernetes signals. |
| cicd | array | no | Optional CI/CD signals. |
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Cloud DevOps or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 94 / 100
Release 0.14.0 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score94
Findings3 threat · 1 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digest294ff05082829fc7ac8016e5ce1f931a4ce62f3d025b178fdf3a6cc67729fe8e
Score vectorthreat 100 → client 94
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (57 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
10 of the 57 recovered tools are registered only when process.env.CLOUD_DEVOPS_MCP_EXECUTION_ENABLED === "true" holds (dist/index.js:481) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 29.
6 of the 57 recovered tools are registered only when process.env.CLOUD_DEVOPS_MCP_INFRASTRUCTURE_OPERATIONS_ENABLED === "true" holds (dist/index.js:683) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 29.
6 of the 57 recovered tools are registered only when process.env.CLOUD_DEVOPS_MCP_CLOUD_INVENTORY_ENABLED === "true" holds (dist/index.js:817) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 29.
6 of the 57 recovered tools are registered only when process.env.CLOUD_DEVOPS_MCP_OBSERVABILITY_ENABLED === "true" holds (dist/index.js:927) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 29.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
29 tools are registered unconditionally · (1) 10 more only when process.env.CLOUD_DEVOPS_MCP_EXECUTION_ENABLED === "true" holds (dist/index.js:481) · (2) 6 more only when process.env.CLOUD_DEVOPS_MCP_INFRASTRUCTURE_OPERATIONS_ENABLED === "true" holds (dist/index.js:683) · (3) 6 more only when process.env.CLOUD_DEVOPS_MCP_CLOUD_INVENTORY_ENABLED === "true" holds (dist/index.js:817) · (4) 6 more only when process.env.CLOUD_DEVOPS_MCP_OBSERVABILITY_ENABLED === "true" holds (dist/index.js:927) — typically when a key or option is configured. All 57 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| assess_terraform_change | no tags | |
| assess_cloud_change_bundle | no tags | |
| build_incident_runbook | no tags | |
| review_cicd_pipeline | no tags | |
| estimate_slo_error_budget | no tags | |
| review_iam_policy | no tags | |
| review_kubernetes_deployment | no tags | |
| review_github_actions_workflow | no tags | |
| review_cloud_identity_policy | no tags | |
| review_terraform_security | no tags | |
| review_kubernetes_security | no tags | |
| review_software_supply_chain | no tags | |
| git_status conditional (1) | no tags | |
| git_fetch conditional (1) | untrusted-inputexternal-sink | untrusted-input: keyword "fetch"; external-sink: declares readOnlyHint: false, openWorldHint: true |
| git_pull_ff_only conditional (1) | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| git_create_branch conditional (1) | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| git_commit conditional (1) | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| git_push conditional (1) | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| github_create_pull_request conditional (1) | external-sink | external-sink: keyword "create_pull_request", declares readOnlyHint: false, openWorldHint: true |
| github_check_pull_request conditional (1) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| github_merge_pull_request conditional (1) | external-sink | external-sink: keyword "open_pr", declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| github_trigger_workflow conditional (1) | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| terraform_fmt_check conditional (2) | no tags | |
| terraform_validate conditional (2) | no tags | |
| terraform_plan_summary conditional (2) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| kubectl_current_context conditional (2) | no tags | |
| kubectl_get_resources conditional (2) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| kubectl_rollout_status conditional (2) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cloud_whoami conditional (3) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cloud_inventory_summary conditional (3) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cloud_kubernetes_clusters conditional (3) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cloud_observability_summary conditional (3) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cloud_finops_signals conditional (3) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cloud_drift_compare conditional (3) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| prometheus_query conditional (4) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| grafana_alert_summary conditional (4) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cloudwatch_logs_query conditional (4) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| kubernetes_health_summary conditional (4) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| github_actions_failure_diagnosis conditional (4) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| correlate_incident_signals conditional (4) | no tags | |
| assess_cloud_health | no tags | |
| correlate_deployment_incident | no tags | |
| assess_observability_coverage | no tags | |
| analyze_finops_waste | no tags | |
| detect_configuration_drift | no tags | |
| generate_operations_brief | no tags | |
| analyze_change_blast_radius | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| analyze_advanced_finops | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| assess_governance_policy | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| assess_cloud_security_posture | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| diagnose_root_cause | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| trace_search | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| trace_summary | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| trace_dependency_map | no tags | |
| assess_tracing_coverage | no tags | |
| analyze_slo_burn_rate | no tags | |
| correlate_trace_slo_incident | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest294ff05082829fc7
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.14.0. Pin a release below and the command asks for exactly that one.
0.14.0
2 Oct 2026
latestNo release note was published with this version.
0.12.0
2 Oct 2026
No release note was published with this version.
0.7.0
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Cloud DevOps can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.