About Argocd
Argocd is an ArgoCD MCP server for GenAI applications managing GitOps continuous delivery and Kubernetes deployments. It covers applications, projects, repositories, clusters, and multi-cluster workflows.
Key features
- 01Create, sync, roll back, and delete applications
- 02Manage projects, repositories, and Kubernetes clusters
- 03Monitor application health, sync status, and resource trees
- 04Configure RBAC, roles, and policies
- 05Support ApplicationSets and multi-cluster deployments
- 06Provide progressive delivery and disaster recovery workflows
Use cases
- 01Inspect application health and diagnose sync drift
- 02Sync Kubernetes applications from Git repositories
- 03Deploy applications across multiple clusters
- 04Roll back applications or run recovery workflows after failures
MCP support
The MCP server provides GenAI clients with ArgoCD management tools for applications, projects, repositories, clusters, sync operations, and health monitoring.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
uvx argocd-mcp-serverARGOCD_API_KEYSecretAPI Key for ARGOCDARGOCD_API_URLAPI URL for ARGOCDLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEArgoCD MCP Server
A Model Context Protocol (MCP) server for integrating ArgoCD GitOps continuous delivery tool with GenAI applications, enabling intelligent Kubernetes deployment management.
Features
-
Comprehensive ArgoCD API Coverage:
- Application Management: Create, sync, delete, rollback applications
- Project Management: Configure projects, roles, and policies
- Repository Management: Add/remove Git repositories, Helm charts
- Cluster Management: Register and manage Kubernetes clusters
- Sync Operations: Manual/auto sync, sync windows, hooks
- Health Monitoring: Application health, sync status, resource tree
- RBAC Management: Users, roles, policies, JWT tokens
- GitOps Workflows: Automated deployments from Git commits
- Multi-tenancy: Namespace isolation, project restrictions
- Application Sets: Template-based multi-cluster deployments
-
Authentication Methods:
- JWT Token authentication
- API Token authentication
- OIDC/OAuth2 integration
- LDAP authentication support
-
Enterprise Features:
- Multi-cluster support
- Disaster recovery workflows
- Progressive delivery (Canary, Blue-Green)
- Automated rollback on failures
- Audit logging and compliance
- Resource optimization
- Secret management integration
Installation
pip install argocd-mcp-server
Or install from source:
git clone https://github.com/asklokesh/argocd-mcp-server.git
cd argocd-mcp-server
pip install -e .
Configuration
Create a .env file or set environment variables:
# ArgoCD Connection
ARGOCD_SERVER=argocd.example.com
ARGOCD_AUTH_TOKEN=your_auth_token
ARGOCD_INSECURE=false
# Optional Settings
ARGOCD_GRPC_WEB=true
ARGOCD_TIMEOUT=30
ARGOCD_CLIENT_CERT=/path/to/cert.pem
ARGOCD_CLIENT_KEY=/path/to/key.pem
# Multi-Cluster Support
ARGOCD_PROD_SERVER=argocd-prod.example.com
ARGOCD_PROD_TOKEN=prod_token
ARGOCD_DEV_SERVER=argocd-dev.example.com
ARGOCD_DEV_TOKEN=dev_token
Quick Start
Basic Usage
from argocd_mcp import ArgoCDMCPServer
# Initialize the server
server = ArgoCDMCPServer()
# Start the server
server.start()
Claude Desktop Configuration
Add to your Claude Desktop config:
{
"mcpServers": {
"argocd": {
"command": "python",
"args": ["-m", "argocd_mcp.server"],
"env": {
"ARGOCD_SERVER": "argocd.example.com",
"ARGOCD_AUTH_TOKEN": "your_auth_token"
}
}
}
}
Available Tools
Application Management
List Applications
{
"tool": "argocd_list_applications",
"arguments": {
"project": "default",
"namespace": "argocd"
}
}
Create Application
{
"tool": "argocd_create_application",
"arguments": {
"name": "my-app",
"project": "default",
"source": {
"repoURL": "https://github.com/org/repo.git",
"path": "manifests",
"targetRevision": "main"
},
"destination": {
"server": "https://kubernetes.default.svc",
"namespace": "production"
},
"syncPolicy": {
"automated": {
"prune": true,
"selfHeal": true
}
}
}
}
Sync Application
{
"tool": "argocd_sync_application",
"arguments": {
"name": "my-app",
"prune": true,
"force": false,
"strategy": {
"hook": {
"force": true
}
}
}
}
Get Application Status
{
"tool": "argocd_get_application_status",
"arguments": {
"name": "my-app",
"refresh": true
}
}
Rollback Application
{
"tool": "argocd_rollback_application",
"arguments": {
"name": "my-app",
"revision": "abc123"
}
}
Project Management
Create Project
{
"tool": "argocd_create_project",
"arguments": {
"name": "production",
"description": "Production applications",
"sourceRepos": ["https://github.com/org/*"],
"destinations": [
{
"server": "https://kubernetes.default.svc",
"namespace": "prod-*"
}
],
"clusterResourceWhitelist": [
{"group": "*", "kind": "*"}
]
}
}
Repository Management
Add Repository
{
"tool": "argocd_add_repository",
"arguments": {
"url": "https://github.com/org/repo.git",
"name": "my-repo",
"type": "git",
"username": "git-user",
"password": "git-token",
"insecure": false
}
}
Add Helm Repository
{
"tool": "argocd_add_helm_repository",
"arguments": {
"url": "https://charts.example.com",
"name": "my-charts",
"type": "helm",
"username": "helm-user",
"password": "helm-password"
}
}
Cluster Management
Add Cluster
{
"tool": "argocd_add_cluster",
"arguments": {
"name": "production-cluster",
"server": "https://k8s-prod.example.com",
"config": {
"bearerToken": "cluster-token",
"tlsClientConfig": {
"insecure": false,
"caData": "base64-encoded-ca"
}
}
}
}
Application Sets
Create ApplicationSet
{
"tool": "argocd_create_applicationset",
"arguments": {
"name": "multi-cluster-app",
"generators": [
{
"clusters": {},
"selector": {
"matchLabels": {
"environment": "production"
}
}
}
],
"template": {
"metadata": {
"name": "{{cluster}}-app"
},
"spec": {
"project": "default",
"source": {
"repoURL": "https://github.com/org/repo.git",
"path": "{{cluster}}"
},
"destination": {
"server": "{{server}}",
"namespace": "default"
}
}
}
}
}
Health and Monitoring
Get Application Health
{
"tool": "argocd_get_application_health",
"arguments": {
"name": "my-app"
}
}
Get Resource Tree
{
"tool": "argocd_get_resource_tree",
"arguments": {
"name": "my-app"
}
}
Advanced Configuration
Multi-Cluster GitOps
from argocd_mcp import ArgoCDMCPServer, ClusterConfig
# Configure multiple ArgoCD instances
clusters = {
"production": ClusterConfig(
server="argocd-prod.example.com",
auth_token="prod_token",
default_namespace="argocd"
),
"staging": ClusterConfig(
server="argocd-staging.example.com",
auth_token="staging_token",
default_namespace="argocd-staging"
),
"development": ClusterConfig(
server="argocd-dev.example.com",
auth_token="dev_token",
default_namespace="argocd-dev"
)
}
server = ArgoCDMCPServer(clusters=clusters, default_cluster="production")
Progressive Delivery
# Configure progressive delivery strategies
progressive_config = {
"canary": {
"steps": [
{"setWeight": 10},
{"pause": {"duration": "5m"}},
{"setWeight": 30},
{"pause": {"duration": "5m"}},
{"setWeight": 50},
{"pause": {"duration": "5m"}},
{"setWeight": 100}
]
},
"blueGreen": {
"activeService": "app-active",
"previewService": "app-preview",
"autoPromotionEnabled": false
}
}
server = ArgoCDMCPServer(progressive_config=progressive_config)
Disaster Recovery
from argocd_mcp import ArgoCDMCPServer, DisasterRecoveryConfig
dr_config = DisasterRecoveryConfig(
backup_enabled=True,
backup_schedule="0 2 * * *", # Daily at 2 AM
backup_location="s3://backups/argocd",
restore_priority=["production", "staging", "development"]
)
server = ArgoCDMCPServer(dr_config=dr_config)
Integration Examples
See the examples/ directory for complete integration examples:
basic_gitops.py- Basic GitOps workflowsmulti_cluster_deployment.py- Multi-cluster application deploymentprogressive_delivery.py- Canary and blue-green deploymentsdisaster_recovery.py- Backup and restore workflowsgenai_gitops.py- AI-powered GitOps automationsecurity_scanning.py- Integration with security tools
Security Best Practices
- Use service accounts with minimal permissions
- Enable RBAC with proper policies
- Implement network policies for cluster isolation
- Use sealed secrets or external secret operators
- Enable audit logging for compliance
- Implement admission controllers for policy enforcement
- Regular security scanning of images and manifests
Error Handling
The server provides detailed error information:
try:
result = server.execute_tool("argocd_sync_application", {
"name": "my-app"
})
except ArgoCDError as e:
print(f"ArgoCD error: {e.error_code} - {e.message}")
if e.error_code == "OutOfSync":
print("Application is out of sync")
elif e.error_code == "ComparisonError":
print("Error comparing application state")
Performance Optimization
- Use application sets for similar apps
- Enable resource caching in ArgoCD
- Implement sync windows to control deployment times
- Use webhook notifications instead of polling
- Optimize manifest generation with Helm/Kustomize
Troubleshooting
Common Issues
-
Sync failures
- Check application logs
- Verify repository access
- Review resource quotas
-
Authentication errors
- Verify token validity
- Check RBAC policies
- Review server connectivity
-
Performance issues
- Check ArgoCD server resources
- Review application count
- Optimize manifest size
Contributing
Contributions are welcome! Please read our contributing guidelines and submit pull requests.
License
MIT License - see LICENSE file for details
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.