
A Model Context Protocol (MCP) server that interfaces with the Nife.io GraphQL API
A Model Context Protocol (MCP) server that interfaces with the Nife.io GraphQL API
·
A Model Context Protocol (MCP) server that interfaces with the Nife.io GraphQL API
Nife MCP Server provides a standardized interface to interact with Nife.io's GraphQL API through the Model Context Protocol, enabling seamless integration with Claude Desktop and other MCP-compatible applications.
pip install nife-mcp-servernpx @nifelabs/mcp-server@latestgit clone https://github.com/nifetency/nife-mcp-server
cd nife-mcp-server
pip install -r requirements.txtnifectl auth login
nifectl auth tokenYou can use the Nife MCP Server in three ways depending on your setup.
This is the easiest way to get started.
{
"mcpServers": {
"nife": {
"command": "npx",
"args": ["--yes", "@nifelabs/mcp-server@latest"],
"env": {
"NIFE_ACCESS_TOKEN": "your_token_here",
"PYTHON": "PYTHON_PATH"
}
}
}
}If you installed the package via pip:
pip install nife-mcp-serverUse this configuration:
{
"mcpServers": {
"nife": {
"command": "python",
"args": ["-m", "nife_mcp_server"],
"env": {
"NIFE_ACCESS_TOKEN": "your_token_here"
}
}
}
}If you're running from source:
{
"mcpServers": {
"nife": {
"command": "python",
"args": ["-m", "nife_mcp_server.intelligent_main"],
"env": {
"PYTHONPATH": "C:\\path\\to\\nife-mcp-server\\src",
"NIFE_ACCESS_TOKEN": "your_token_here"
}
}
}
}Replace the PYTHONPATH with your local project path.
Variable Description
NIFE_ACCESS_TOKEN Your API access token from Nife
Your Nife.io integration is now active! 🎉
The hosted connector (nife-mcp-http) adds curated tools on top of the site, app and custom-domain tools. The stdio server (intelligent_main.py) loads the same tools next to its schema-generated ones when the optional dependencies are installed (pip install "nife-mcp-server[http]", or pip install -r requirements.txt). It uses NIFE_ACCESS_TOKEN as the caller's token. Without those packages it runs with only the schema-generated tools and logs a hint on stderr. Every call is made with the caller's own token. Organization-keyed tools check membership first, and alert, billing cycle and recommendation ids are checked against the caller's own lists before use.
Reliability (NERO)
| Tool | What it does |
|---|---|
get_health_insights | Overall health, open incidents, anomalies, predictions and actions. Start here |
list_incidents, get_incident | Incidents and their post-mortems |
get_root_cause_analysis | AI root cause analysis (slow; refresh=true runs a new one) |
list_alerts | Alerts with status and who handled them |
acknowledge_alert, resolve_alert | Change alert state (confirm with the user first) |
list_anomalies, predict_failures | Detected anomalies and predicted failures |
get_slo_status, get_health_report | SLO and error budget; deep per-service health |
search_knowledge_base | Past incidents and fixes by error text |
Cost (FinOps)
| Tool | What it does |
|---|---|
get_spending_overview, get_usage_stats | Spend against limits; resource usage and cost |
list_billing_cycles, get_billing_items, list_invoices, get_cloud_billing_summary | Billing detail |
list_cost_recommendations | Ranked savings opportunities with totals |
get_cost_forecast, get_cost_anomalies, get_cost_usage_patterns | Outlook, unusual cost, and what the recommendations rest on |
get_cost_breakdown | Cost explorer: total grouped by provider, service or region |
search_finops_resources, get_finops_resource_stats | Multi-cloud inventory with monthly cost |
apply_cost_recommendation | Carries out one recommendation. Previews unless confirm=true |
Platform, delivery and compliance (read-only)
| Tool | What it does |
|---|---|
get_org_dora_metrics | Deployment frequency, lead time, change failure rate and time to restore |
get_deployment_history, get_incident_history | Deployment and incident events of one app |
get_usage_summary, get_app_cost, get_app_usage_metrics | Running cost per account and app; CPU, memory and network usage |
estimate_deployment_cost, get_credits | Price a deployment before making it; prepaid balance and transactions |
get_volume_overview, get_app_failover | Volumes, health and snapshots; failover targets and which one serves |
list_clusters, get_cluster_capacity | Regions and clusters; free CPU, memory, storage and pods |
list_cloud_hosts, list_workloads | Connected servers and VMs; workload environments |
list_backup_policies, get_restore_history | Backup schedules and restore results |
get_capacity_thresholds, get_usage_report_subscription | Capacity alert thresholds; emailed usage report schedule |
get_audit_log_summary, get_regulatory_reporting, get_incident_regulatory_reports | Audit trail size; on-time reporting to CERT-In, DPB, RBI, SEBI or IRDAI |
These tools only read. Cloud credentials and kubeconfig locations are never requested.
Infrastructure and governance (read-only)
| Tool | What it does |
|---|---|
list_connected_cloud_accounts | Every cloud account connected to an organization (AWS, GCP, Azure, OpenStack), without credentials. The site tool list_cloud_accounts lists only the AWS accounts a site can be hosted in |
list_managed_clusters, list_vm_node_pools | Provisioned Kubernetes clusters (no kubeconfig) and VM pools |
list_business_units, list_roles, get_plan_limits | Business units; role permissions; what the plan allows |
list_agents, get_agent_metrics | Nife agents in customer clusters; cluster, node and app usage |
get_agent_security_findings, get_agent_health_checks | Findings with remediation; health checks per cluster |
get_resource_forecast | Nia CPU and memory forecast for an organization or app (no charts) |
The forecast service address can be changed with NIFE_LSTM_URL.
Virtual machines and cloud accounts (changes)
| Tool | What it does |
|---|---|
vm_power_action | Start, stop or restart a server or VM. Previews unless confirm=true |
validate_cloud_account | Re-check a cloud account's credentials and update its status |
Cron jobs
| Tool | What it does |
|---|---|
list_cron_job_runs, get_cron_job_run_logs | Run history with failure reasons; the tail of one run's log |
trigger_cron_job_run | Start a run now. Previews unless confirm=true |
# If installed via pip
nife-mcp-server
# If running from source
python -m nife_mcp_server.intelligent_mainThe server speaks MCP over stdin/stdout, so it is normally launched by your MCP client (e.g. Claude Desktop) rather than run by hand. It does not listen on a network port.
To run the hosted HTTP connector instead, install the http extra (pip install "nife-mcp-server[http]") and run nife-mcp-http. It listens on PORT (default 8000); see HOSTED.md.
NIFE_ACCESS_TOKEN - Your Nife.io access tokenThe GraphQL endpoint is fixed to https://api.nife.io/graphql. The hosted connector has its own settings, listed in HOSTED.md.
Once configured, you can ask Claude:
"List all my applications in Nife.io"
"Show me the status of my deployments"
"Create a new application called 'my-app'"┌─────────────────┐
│ Claude Desktop │
└────────┬────────┘
│ MCP Protocol
┌────────▼────────┐
│ Nife MCP Server│
└────────┬────────┘
│ GraphQL
┌────────▼────────┐
│ Nife.io API │
└─────────────────┘| Endpoint | Method | Description |
|---|---|---|
/api/mcp/context | GET | Retrieve model context |
/api/mcp/context | POST | Update model context |
/api/mcp/schema | GET | Get GraphQL schema |
/api/mcp/query | POST | Execute custom queries |
/api/mcp/health | GET | Health check |
The server provides full access to Nife.io's GraphQL API:
# Clone the repository
git clone https://github.com/nifetency/nife-mcp-server
cd nife-mcp-server
# Create virtual environment
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
# Install dependencies
pip install -r requirements.txt
pip install -e . # Install in editable mode
# Run the server
cd src
python -m nife_mcp_server.intelligent_mainnife-mcp-server/
├── src/
│ └── nife_mcp_server/
│ ├── intelligent_main.py # Main server logic
│ ├── schema_manager.py # GraphQL schema handling
│ ├── http_app.py # Hosted (Streamable HTTP) connector
│ ├── http_auth.py # Auth for the hosted connector
│ ├── oauth.py # OAuth support
│ ├── nife_api.py # Async client (GraphQL, express-backend, FinOps)
│ ├── tool_utils.py # Shared tool helpers and ownership checks
│ ├── site_tools.py # Site deploy, manage and inspect tools
│ ├── app_tools.py # Container app tools
│ ├── domain_tools.py # Custom-domain tools
│ ├── ops_tools.py # NERO and FinOps tools
│ ├── platform_tools.py # Delivery, compliance, usage and capacity tools
│ ├── infra_tools.py # Cloud accounts, clusters, agents, governance
│ ├── vm_tools.py # VM power actions and cloud account checks
│ ├── cron_tools.py # Cron job runs
│ └── routes/
│ └── mcp.py # MCP route handlers
├── tests/ # Test suite
├── Dockerfile # Container image for the hosted server
└── bin/ # Executable scriptspytest
pytest --cov=nife_mcp_server # With coverageWe love contributions! Please see our Contributing Guide for details.
This project is licensed under the MIT License - see the LICENSE file for details.
If you find this project useful, please consider giving it a star!
Made by the Nife.io team
Pick your client and paste the snippet. Each one is the same server, written the way that client expects it.
claude mcp add nife -- npx --yes @nifelabs/mcp-server@latest{
"mcpServers": {
"nife": {
"env": {
"PYTHON": "",
"NIFE_ACCESS_TOKEN": ""
},
"args": [
"--yes",
"@nifelabs/mcp-server@latest"
],
"command": "npx"
}
}
}code --add-mcp '{"name":"nife","env":{"PYTHON":"","NIFE_ACCESS_TOKEN":""},"args":["--yes","@nifelabs/mcp-server@latest"],"command":"npx"}'[mcp_servers.nife]
command = "npx"
args = ["--yes", "@nifelabs/mcp-server@latest"]Runs locally on your device. Your client starts the server itself, so nothing has to be hosted.
Paste this prompt into your agent. It reads this page and does the setup for you.
Read https://aiagentslisting.com/mcp/nife-io-mcp-server to learn what the "Nife.io MCP Server" MCP server does and how to install it. Add it to my coding agent's MCP configuration as documented on that page, then confirm the server connects and list the tools it exposes.Agents can also browse this directory over MCP at https://aiagentslisting.com/api/mcp
npx @nifelabs/mcp-server@latestpip install nife-mcp-serverThis server runs locally, so we can't read its tool list over the web yet.
We could not run this server: its npm package has not answered in our offline sandbox, which usually means it needs an API key or other configuration to start. The four checks that need a live server are left out, and the grade tops out at B until we can read its tools.
Maintain this server? Claiming proves you own the listing and earns the last 4 points.
Claim this listingPaste this line near the top of your repository's README. The badge always renders the current score.
[](https://aiagentslisting.com/mcp/nife-io-mcp-server)Nothing comparable is listed yet.
No tagged releases on record.
Connect to the AI Agents Listing MCP server at https://aiagentslisting.com/api/mcp using the HTTP transport and complete the sign-in when it asks. Then call the submit_review tool for the listing "nife-io-mcp-server" with a rating from 1 to 5 and a short note on what worked and what did not.No reviews yet
Be the first to share your experience with this tool.
One email a week. New agents, MCP servers and skills, and what is actually getting traction.