{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"npm-argocd-mcp","slug":"argocd-mcp","name":"argocd-mcp","type":"mcp","url":"https://github.com/argoproj-labs/mcp-for-argocd#readme","page_url":"https://unfragile.ai/argocd-mcp","categories":["mcp-servers"],"tags":["mcp","argocd","argocd-mcp","argocd-mcp-server","argo-cd","argo-cd-mcp","argo-cd-mcp-server","cicd","cicd-mcp","cicd-mcp-server","gitops","gitops-mcp","gitops-mcp-server","kubernetes","kubernetes-mcp","kubernetes-mcp-server"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"npm-argocd-mcp__cap_0","uri":"capability://tool.use.integration.argo.cd.application.state.querying.via.mcp.protocol","name":"argo cd application state querying via mcp protocol","description":"Exposes Argo CD application resources (status, sync state, health, revision) through the Model Context Protocol, allowing LLM clients to query live cluster state without direct kubectl access. Implements MCP resource endpoints that translate Argo CD API calls into structured JSON responses, enabling stateless queries of application metadata and deployment status across multiple clusters managed by a single Argo CD instance.","intents":["Query the current sync status and health of a deployed application without leaving the LLM context","Retrieve application revision history and compare deployed vs desired state","Check if an application is healthy and ready before triggering downstream actions","List all applications in an Argo CD instance to understand cluster state"],"best_for":["DevOps engineers building LLM-powered deployment assistants","Platform teams integrating Argo CD observability into AI agents","Teams automating GitOps workflows with LLM decision-making"],"limitations":["Read-only by default — querying only, no mutation of application state through this capability","Requires network connectivity to Argo CD API server from MCP server process","No built-in caching — each query hits the Argo CD API, adding latency for high-frequency polling","Limited to applications visible to the Argo CD service account credentials provided"],"requires":["Argo CD 2.0+ instance with accessible API endpoint","Valid Argo CD API token or kubeconfig with cluster access","MCP client implementation (e.g., Claude Desktop, custom LLM agent)","Network route from MCP server to Argo CD API server"],"input_types":["application name (string)","namespace filter (string)","cluster selector (string)"],"output_types":["JSON application manifest with status fields","structured application health/sync state object","revision and git commit metadata"],"categories":["tool-use-integration","kubernetes"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm-argocd-mcp__cap_1","uri":"capability://tool.use.integration.argo.cd.application.synchronization.triggering.via.mcp.tools","name":"argo cd application synchronization triggering via mcp tools","description":"Implements MCP tool endpoints that trigger application sync operations (full sync, partial sync, refresh) against Argo CD, translating LLM tool calls into Argo CD API sync requests. Handles sync strategy configuration (auto-prune, self-heal, force), waits for sync completion, and returns operation status back to the LLM, enabling autonomous deployment workflows driven by LLM reasoning.","intents":["Trigger a deployment sync when an LLM detects a configuration drift or pending changes","Perform a controlled rollback by syncing to a previous git commit","Force-sync an application to recover from a stuck or degraded state","Initiate a partial sync of specific resources within an application"],"best_for":["Platform engineers building self-healing deployment agents","Teams implementing LLM-driven GitOps automation","DevOps teams reducing manual sync operations through AI orchestration"],"limitations":["Requires write permissions on Argo CD API — service account must have sync/update RBAC roles","Sync operations are asynchronous; MCP tool must poll or wait for completion status","No built-in rollback safety — LLM can trigger destructive syncs if not properly constrained","Sync strategy options (auto-prune, force) are global per application, not per-resource"],"requires":["Argo CD 2.0+ with API token having 'applications/sync' permission","MCP server running with credentials to call Argo CD sync endpoints","Application must exist in Argo CD and be in a syncable state","Git repository must be accessible to Argo CD for fetching desired state"],"input_types":["application name (string)","sync strategy flags (auto-prune: boolean, force: boolean, self-heal: boolean)","target revision (string, optional)"],"output_types":["sync operation ID (string)","operation status (pending/running/succeeded/failed)","sync result with resource counts (synced/failed/pruned)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm-argocd-mcp__cap_10","uri":"capability://tool.use.integration.argo.cd.application.diff.and.change.preview.via.mcp","name":"argo cd application diff and change preview via mcp","description":"Provides MCP tools to generate diffs between desired (Git) and actual (cluster) application state, showing resource changes, manifest differences, and impact analysis. Implements handlers that call Argo CD's diff API, parse manifests, and format diffs for readability. Supports filtering by resource type and namespace.","intents":["Preview what changes will be applied before syncing an application","Identify drift between Git source and cluster state without manual manifest comparison","Analyze the impact of pending changes on specific resources or namespaces"],"best_for":["DevOps engineers reviewing changes before deployment","Platform teams building change approval workflows with AI-assisted analysis","Teams automating drift detection and change impact analysis"],"limitations":["Diff output can be large for complex applications; may exceed MCP message size limits","Diff formatting is basic; complex manifests may be difficult to parse visually","No semantic diff (e.g., YAML ordering differences); shows all changes including whitespace","Impact analysis is limited to resource-level changes; does not predict runtime behavior"],"requires":["Argo CD 2.0+ with diff API access","Service account with application read permissions","MCP client with tool-calling support"],"input_types":["application name (string)","resource type filter (optional enum: Deployment, Service, ConfigMap, etc.)","namespace filter (optional string)"],"output_types":["diff summary (object with added, modified, deleted counts)","detailed resource diffs (array of diff objects)","impact analysis (resource-level changes)"],"categories":["tool-use-integration","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm-argocd-mcp__cap_11","uri":"capability://tool.use.integration.argo.cd.event.log.and.audit.trail.querying.via.mcp","name":"argo cd event log and audit trail querying via mcp","description":"Provides MCP tools to query Argo CD event logs and audit trails for applications, including sync operations, configuration changes, and user actions. Implements handlers that call Argo CD's event API, filter by timestamp/user/operation type, and format results for readability. Supports pagination and time-range filtering.","intents":["Retrieve the history of sync operations and configuration changes for an application","Audit who made changes to an application and when","Investigate deployment failures by reviewing event logs and error messages"],"best_for":["DevOps engineers troubleshooting deployment issues via event history","Compliance and security teams auditing Argo CD changes","Platform teams building incident investigation and root-cause analysis workflows"],"limitations":["Event retention is limited by Argo CD's storage policy; old events may be unavailable","Event log does not include cluster-side events (pod crashes, node failures); requires separate monitoring","Audit trail is basic; no integration with external audit systems (Falco, Auditbeat)","Pagination may be required for large event sets; no built-in streaming"],"requires":["Argo CD 2.0+ with event API access","Service account with application read permissions","MCP client with tool-calling support"],"input_types":["application name (string)","event type filter (optional enum: sync, config-change, error)","time range (optional object with start/end timestamps)","user filter (optional string)"],"output_types":["event list (array of event objects)","event summary (counts by type)","error messages and stack traces (if applicable)"],"categories":["tool-use-integration","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm-argocd-mcp__cap_2","uri":"capability://search.retrieval.argo.cd.application.health.and.sync.status.monitoring","name":"argo cd application health and sync status monitoring","description":"Provides MCP resources that expose real-time application health metrics (healthy/degraded/progressing), sync status (synced/out-of-sync/unknown), and resource-level health from Argo CD. Polls the Argo CD API to aggregate health conditions and surfaces them as queryable MCP resources, enabling LLMs to make decisions based on current cluster state without manual kubectl inspection.","intents":["Check if an application is healthy before triggering dependent deployments","Detect when an application has drifted from desired state and needs remediation","Monitor deployment progress during a sync operation","Alert an LLM agent when an application enters a degraded state"],"best_for":["Teams building LLM-driven deployment pipelines with health gates","Platform teams implementing intelligent rollback logic based on health signals","DevOps engineers automating incident response for degraded applications"],"limitations":["Health status is eventually consistent — reflects Argo CD's last refresh, not real-time cluster state","No built-in alerting or webhooks — LLM must poll for status changes","Health conditions are aggregated at application level; fine-grained resource health requires additional queries","Depends on Argo CD's health assessment logic, which may not catch all failure modes"],"requires":["Argo CD 2.0+ with API endpoint accessible to MCP server","Valid API token with read permissions on applications","Application must have health assessment enabled in Argo CD"],"input_types":["application name (string)","namespace (string, optional)"],"output_types":["health status enum (Healthy/Progressing/Degraded/Unknown)","sync status enum (Synced/OutOfSync/Unknown)","resource health array with per-resource status","condition messages with timestamps"],"categories":["search-retrieval","monitoring"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm-argocd-mcp__cap_3","uri":"capability://search.retrieval.git.repository.and.revision.querying.for.deployed.applications","name":"git repository and revision querying for deployed applications","description":"Exposes MCP resources that query the git repository metadata associated with Argo CD applications, including current deployed revision, commit history, branch information, and git URL. Allows LLMs to inspect what code is currently deployed and retrieve commit details without direct git repository access, enabling context-aware deployment decisions and rollback reasoning.","intents":["Determine what git commit is currently deployed in an application","Retrieve commit message and author info to understand what changes are live","List available branches or tags to propose a rollback target","Compare deployed revision against main branch to assess staleness"],"best_for":["Teams implementing LLM-driven rollback logic based on commit history","DevOps engineers building deployment audit trails with AI reasoning","Platform teams automating deployment decisions based on code changes"],"limitations":["Requires git repository to be accessible to Argo CD; private repos need credentials","Commit history is limited to what Argo CD has fetched; may not include very recent commits if refresh is stale","No direct git clone or file access — only metadata available through Argo CD","Branch/tag information depends on Argo CD's git fetch configuration"],"requires":["Argo CD 2.0+ with git repository configured for the application","Git repository must be accessible (public or with credentials configured in Argo CD)","API token with read permissions on applications"],"input_types":["application name (string)","revision type (branch/tag/commit, optional)"],"output_types":["git repository URL (string)","current deployed revision (commit hash or branch)","commit metadata (author, message, timestamp)","available branches/tags array"],"categories":["search-retrieval","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm-argocd-mcp__cap_4","uri":"capability://search.retrieval.multi.cluster.application.discovery.and.filtering","name":"multi-cluster application discovery and filtering","description":"Implements MCP resources that enumerate all applications across multiple Argo CD-managed clusters, with filtering by namespace, label selectors, and sync/health status. Aggregates application metadata from a single Argo CD instance managing multiple clusters, allowing LLMs to discover and reason about the entire deployment landscape without manual cluster enumeration.","intents":["List all applications in a specific namespace across all clusters","Find applications with a specific label to target bulk operations","Discover out-of-sync applications that need remediation","Enumerate all applications in a degraded state for incident response"],"best_for":["Platform teams managing multi-cluster deployments with LLM orchestration","DevOps engineers building cluster-wide automation and compliance checks","Teams implementing intelligent resource discovery for deployment agents"],"limitations":["Discovery is limited to applications visible to the Argo CD service account","Filtering is performed server-side by Argo CD API; complex queries may require multiple requests","No real-time updates — results reflect Argo CD's last refresh cycle","Large deployments (1000+ applications) may have pagination/performance implications"],"requires":["Argo CD 2.0+ configured with multiple cluster secrets","API token with read permissions on applications across all clusters","Clusters must be registered in Argo CD"],"input_types":["namespace filter (string, optional)","label selector (string, optional)","sync status filter (synced/out-of-sync, optional)","health status filter (healthy/degraded, optional)"],"output_types":["application list with metadata (name, namespace, cluster, status)","application count by status","cluster distribution summary"],"categories":["search-retrieval","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm-argocd-mcp__cap_5","uri":"capability://data.processing.analysis.application.configuration.and.manifest.inspection","name":"application configuration and manifest inspection","description":"Exposes MCP resources that retrieve the current application manifest, desired state from git, and actual state from the cluster, allowing LLMs to inspect what is deployed and compare against desired configuration. Provides structured access to Helm values, Kustomize overlays, and raw YAML without requiring LLMs to parse git repositories or kubectl output directly.","intents":["Inspect the current Helm values deployed in an application","Compare desired vs actual state to understand drift","Retrieve the raw Kubernetes manifests for an application","Inspect Kustomize overlays to understand configuration layers"],"best_for":["Platform engineers debugging configuration drift issues with AI assistance","Teams implementing LLM-driven configuration validation and compliance checks","DevOps engineers automating configuration audits and change analysis"],"limitations":["Large manifests (>1MB) may exceed MCP message size limits or LLM context windows","Manifest retrieval requires git repository access through Argo CD; private repos need credentials","No manifest diffing built-in — LLM must compare desired vs actual strings","Helm/Kustomize rendering depends on Argo CD's configuration; custom plugins may not be supported"],"requires":["Argo CD 2.0+ with application configured","Git repository accessible to Argo CD for desired state","API token with read permissions on applications","Sufficient MCP message size limits for manifest content"],"input_types":["application name (string)","manifest type (desired/actual/diff, optional)"],"output_types":["YAML manifest (string)","structured Helm values (JSON)","Kustomize overlay information","manifest diff (if comparing desired vs actual)"],"categories":["data-processing-analysis","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm-argocd-mcp__cap_6","uri":"capability://search.retrieval.application.resource.event.and.log.streaming","name":"application resource event and log streaming","description":"Implements MCP resources that retrieve event logs and pod logs for resources within an Argo CD application, providing visibility into deployment progress, errors, and runtime behavior. Aggregates Kubernetes events and container logs through Argo CD's API, allowing LLMs to diagnose deployment failures and understand application behavior without direct cluster access.","intents":["Retrieve pod logs to diagnose why an application is in a degraded state","Inspect Kubernetes events to understand deployment failures","Monitor startup logs during a sync operation to detect issues early","Collect error messages for incident analysis and root cause determination"],"best_for":["DevOps engineers building LLM-powered troubleshooting agents","Platform teams implementing intelligent incident response automation","Teams automating log analysis and error detection with AI"],"limitations":["Log retrieval is limited to what Argo CD can access; requires cluster API permissions","Large log volumes may exceed MCP message limits; streaming or pagination required","Logs are historical; real-time streaming not supported through MCP","Pod logs require pods to exist; logs are lost when pods are deleted"],"requires":["Argo CD 2.0+ with cluster API access","Service account with permissions to read pods and logs","API token with read permissions on applications","Pods/resources must exist in the cluster"],"input_types":["application name (string)","resource type (pod/deployment/statefulset, optional)","container name (string, optional)","log tail lines (integer, optional)"],"output_types":["pod logs (string)","Kubernetes events (structured array)","event timestamps and messages","error summaries"],"categories":["search-retrieval","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm-argocd-mcp__cap_7","uri":"capability://safety.moderation.argo.cd.project.and.rbac.policy.querying","name":"argo cd project and rbac policy querying","description":"Exposes MCP resources that query Argo CD projects, RBAC policies, and access control rules, allowing LLMs to understand deployment permissions and constraints. Provides visibility into which applications a user/service account can access, what actions are permitted, and what repositories/clusters are allowed by policy.","intents":["Determine if an LLM agent has permission to sync a specific application","Understand what repositories and clusters are accessible to a service account","Retrieve RBAC policies to validate deployment decisions against access control","Check if a proposed action violates Argo CD security policies"],"best_for":["Platform teams implementing policy-aware LLM deployment agents","Security teams automating compliance checks for deployment automation","Teams building multi-tenant deployment systems with LLM orchestration"],"limitations":["RBAC policy evaluation is static; doesn't account for dynamic conditions or time-based rules","Project policies are Argo CD-specific; don't reflect Kubernetes RBAC or cloud IAM","No built-in policy simulation — LLM must manually evaluate if an action is allowed","Policy changes require Argo CD API refresh; cached policies may be stale"],"requires":["Argo CD 2.0+ with RBAC configured","API token with read permissions on projects and RBAC policies","Argo CD admin access to query full policy set"],"input_types":["project name (string)","service account or user (string, optional)"],"output_types":["project metadata (name, description, repositories, clusters)","RBAC roles and permissions array","repository and cluster access rules","policy enforcement status"],"categories":["safety-moderation","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm-argocd-mcp__cap_8","uri":"capability://tool.use.integration.notification.and.webhook.integration.for.deployment.events","name":"notification and webhook integration for deployment events","description":"Provides MCP tool endpoints that configure Argo CD notifications and webhooks, allowing LLM agents to register callbacks for deployment events (sync complete, health changed, error occurred). Enables event-driven automation where Argo CD notifies the LLM agent of state changes, triggering downstream actions without continuous polling.","intents":["Register a webhook to notify the LLM agent when an application sync completes","Trigger downstream actions (e.g., run tests, update dashboards) when deployment health changes","Implement event-driven incident response when applications enter degraded state","Coordinate multi-step deployment workflows triggered by Argo CD events"],"best_for":["Teams building event-driven deployment automation with LLM orchestration","Platform engineers implementing reactive deployment pipelines","DevOps teams reducing polling overhead through webhook-based notifications"],"limitations":["Webhook delivery is asynchronous and not guaranteed; events may be lost or delayed","Requires MCP server to expose a public endpoint for receiving webhooks","Webhook payload size is limited; large manifests cannot be included in notifications","No built-in retry logic or dead-letter handling for failed webhook deliveries"],"requires":["Argo CD 2.0+ with notification service enabled","MCP server with public endpoint accessible from Argo CD","API token with write permissions to configure notifications","Network connectivity from Argo CD to MCP server"],"input_types":["application name (string)","event types (sync/health/error, array)","webhook URL (string)","filter conditions (optional)"],"output_types":["webhook registration confirmation","event payload (JSON with application state and change details)","delivery status (success/failed)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm-argocd-mcp__cap_9","uri":"capability://tool.use.integration.argo.cd.rollback.and.revision.management.via.mcp","name":"argo cd rollback and revision management via mcp","description":"Enables LLM clients to rollback applications to previous revisions or specific Git commits through MCP tools. Implements handlers that query application revision history, validate rollback targets, and trigger rollback operations via Argo CD API. Supports dry-run mode to preview rollback changes before execution.","intents":["Rollback a failed deployment to the previous stable revision via LLM instruction","Revert an application to a specific Git commit without manual Git operations","Preview rollback changes before executing to ensure correctness"],"best_for":["DevOps engineers automating incident response and deployment rollbacks","Platform teams building AI-driven deployment recovery workflows","Teams managing rapid deployment cycles with frequent rollback requirements"],"limitations":["Rollback only reverts Git source; does not rollback data or state changes in the cluster","Revision history is limited to Argo CD's retention policy; old revisions may be unavailable","Dry-run mode shows Git changes, not actual cluster impact; requires separate validation","No automatic rollback triggers; requires explicit LLM instruction or external orchestration"],"requires":["Argo CD 2.0+ with rollback API access","Service account with sync permissions on target applications","Git repository with accessible commit history"],"input_types":["application name (string)","target revision (string: commit hash, branch, or tag)","dry-run flag (boolean)","prune flag (boolean)"],"output_types":["rollback operation ID (string)","operation status (enum: Pending, Running, Succeeded, Failed)","changed resources summary","dry-run preview (if requested)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":41,"verified":false,"data_access_risk":"high","permissions":["Argo CD 2.0+ instance with accessible API endpoint","Valid Argo CD API token or kubeconfig with cluster access","MCP client implementation (e.g., Claude Desktop, custom LLM agent)","Network route from MCP server to Argo CD API server","Argo CD 2.0+ with API token having 'applications/sync' permission","MCP server running with credentials to call Argo CD sync endpoints","Application must exist in Argo CD and be in a syncable state","Git repository must be accessible to Argo CD for fetching desired state","Argo CD 2.0+ with diff API access","Service account with application read permissions"],"failure_modes":["Read-only by default — querying only, no mutation of application state through this capability","Requires network connectivity to Argo CD API server from MCP server process","No built-in caching — each query hits the Argo CD API, adding latency for high-frequency polling","Limited to applications visible to the Argo CD service account credentials provided","Requires write permissions on Argo CD API — service account must have sync/update RBAC roles","Sync operations are asynchronous; MCP tool must poll or wait for completion status","No built-in rollback safety — LLM can trigger destructive syncs if not properly constrained","Sync strategy options (auto-prune, force) are global per application, not per-resource","Diff output can be large for complex applications; may exceed MCP message size limits","Diff formatting is basic; complex manifests may be difficult to parse visually","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.45945578204662263,"quality":0.34,"ecosystem":0.6000000000000001,"match_graph":0.25,"freshness":0.52,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.15,"match_graph":0.23,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:23.328Z","last_scraped_at":"2026-05-03T14:04:47.472Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":9914,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=argocd-mcp","compare_url":"https://unfragile.ai/compare?artifact=argocd-mcp"}},"signature":"oWjA6N/VIuexo8vZPIThoEUFhZ8C/4qZc3pNQnjfCM09oepMPMCkHTf7bcffFqlPV3Mcc21SScLVzLKUk9B3Cg==","signedAt":"2026-06-23T07:19:06.584Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/argocd-mcp","artifact":"https://unfragile.ai/argocd-mcp","verify":"https://unfragile.ai/api/v1/verify?slug=argocd-mcp","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}