Now available — v3.8.23
NEW: Data reach of agents

The AI spend plane
for the token economy.

Your agents call tools. Those tools touch data. Magertron governs both — and knows which tool touched which table, for whom, and what it cost. One gateway for model inference and tool calls across every vendor.

OSS Free up to 20 servers — no signup, no credit card.

✦ AI Orchestrator Assistant Advisory · read-only · grounded in live platform state
▋
▋
Magertron dashboard with Agent Galaxy — live map of which principals and AI agents can reach and are actively calling which MCP tools, with entitlement-vs-usage edges Magertron AI Cost Dashboard — total agent spend, committed vs pay-as-you-go, per-vendor and per-user cost breakdown with budget tracking
Install in 5 minutes
# Bare Ubuntu box — installs k3s, helm and Magertron
$ curl -fsSL https://magertron.com/bootstrap.sh | sudo bash -s -- \
      --api-public-url https://mcp.example.com

# Already have a Kubernetes cluster
$ git clone https://github.com/magertron/orchestrator.git
$ cd orchestrator
$ ./install.sh                                  # Free tier — no license needed
$ ./install.sh --license /path/to/license.json  # With a license
Enterprise Security

Rogue MCP servers are already inside your network

Developers are spinning up ungoverned MCP servers on laptops, in personal cloud accounts, and inside your perimeter — with no audit trail and no controls. AI agents talking to these servers can execute actions at scale.

Now you can find them. Magertron reads MCP client configs on every endpoint you manage, shows you every server in use — approved or not — and points them at the gateway with a single policy change. No resident agent on the laptop — a script and a timer, delivered by the MDM you already run.

Read the security guide →
THREAT VECTOR 01
External AI agents
AI agents outside your perimeter reaching ungoverned internal MCP servers. Perimeter firewalls catch these — but only if the agent actually crosses the perimeter, and only if the MCP server is registered as a public service.
Magertron fleet devices — one integration token, four endpoints across macOS, Linux and Windows reporting their MCP client configs, with delivery method and last check-in per device
Governed Surfaces

Every model and tool call. One policy plane.

Internal MCP servers

MCP servers run as pods in your cluster. Traffic stays inside your network.

LLM providers

Anthropic, OpenAI, or your own model pods — registered as governed endpoints. Every inference call is metered, charged back, and budget-capped, with provider keys held by Magertron, never the agent.

External MCP servers

SaaS or cloud-hosted MCP servers, registered in Magertron and governed by the same policies as your internal servers.

Server Management

Full lifecycle control for every server you run

Deploy MCP servers and LLM pods from any container image, monitor real-time CPU and memory metrics, and scale with a slider. Every action is audited.

  • Live metrics charts polling every 5 seconds
  • Real pod logs from Kubernetes API
  • One-click rollback from deployment history
  • Rolling restart with zero downtime
Server Detail Panel
Governance

Enforce policy before anything reaches production

Namespace-scoped governance policies evaluate every deployment at deploy time. Error-severity rules block non-compliant servers. Warnings flag for review.

  • Different policies for prod vs dev environments
  • Resource limits, transport rules, naming standards
  • Dry-run evaluator for pre-flight checks
  • Export/import policies across clusters
Governance Policies
Capabilities
The full server lifecycle —
in your Kubernetes cluster
Deploy, registry, gateway, governance, observability. One Helm chart. Apache 2.0. Most platforms cover one or two of these. Magertron covers all five.
⬡

Server Lifecycle

Deploy, scale, restart, and roll back MCP servers and LLM pods from a single console.
▦

Server & Model Registry

Central catalog of every MCP server and LLM provider in your organization. Most platforms don't have a registry — Magertron does, in your cluster.
◈

Governance Engine

Policies for resource limits, transport, naming, and security. Namespace-scoped for prod vs dev.
⛊

Multi-Tenant RBAC

Role-based access with namespace isolation. Admins, deployers, operators, viewers.

⚿

Enterprise Identity

OIDC and SAML SSO. SCIM 2.0 provisioning. Just-in-time accounts. Your IdP is the source of truth.

◷

Audit & Compliance

OCSF-aligned audit events. SIEM-ready, validated with Splunk Cloud. Built for regulated environments.
Developer Experience
A CLI that gets out
of your way
Single binary, zero dependencies. Deploy, scale, and evaluate governance from your terminal. Ships for macOS and Linux.
$ mcpctl login https://mcp.acme.internal admin
✓ Logged in as admin (system:platform-admin)

$ mcpctl deploy code-assistant mcp-prod ghcr.io/acme/code-assistant --tag v2.1 --team platform
Deploying code-assistant to mcp-prod...
✓ Server deployed (state: Running)

$ mcpctl governance evaluate spec.json --namespace mcp-prod
✓ ALLOWED
⚠ Mutating tools detected — review required before production use

$ mcpctl servers
NAME NAMESPACE STATE REPLICAS IMAGE
code-assistant mcp-prod Running 2/2 ghcr.io/acme/code-assistant:v2.1
search-tool mcp-prod Running 3/3 ghcr.io/acme/search:latest
doc-retriever mcp-staging Running 1/1 ghcr.io/acme/docs:v1.4

mcpctl is a signed Go binary — install it below. There are unrelated mcpctl packages on npm and PyPI; neither is ours.

Homebrew macOS · Linux ▸
Cleanest install if you have brew — and the only one that upgrades itself:
$ brew trust magertron/tap
$ brew install magertron/tap/mcpctl
Homebrew 6 asks you to trust any tap outside its core before it will load a formula, because a formula is code that runs on your machine. One command, once. Afterwards brew upgrade keeps mcpctl current.
curl one-liner macOS · Linux ▸
No package manager required:
$ curl -fsSL https://magertron.com/install-mcpctl.sh | sh
Debian / Ubuntu apt · amd64 · arm64 ▸
One-time setup
$ curl -fsSL https://magertron.com/apt/magertron-archive-keyring.gpg | sudo tee /etc/apt/trusted.gpg.d/magertron-archive-keyring.gpg > /dev/null
$ echo "deb [signed-by=/etc/apt/trusted.gpg.d/magertron-archive-keyring.gpg] https://magertron.com/apt stable main" | sudo tee /etc/apt/sources.list.d/magertron.list
$ sudo apt update
Install
$ sudo apt install mcpctl
RHEL / Fedora / Rocky dnf · x86_64 ▸
One-time setup
$ sudo curl -fsSL https://magertron.com/yum/magertron.repo -o /etc/yum.repos.d/magertron.repo
Install
$ sudo dnf install mcpctl
Or download a binary directly
macOS arm64 · macOS amd64 · Linux amd64 · Linux arm64
View latest release →
Apache 2.0 licensed. Source at magertron/orchestrator/mcpctl. Free to download; connecting it to an orchestrator requires a Pro or Enterprise license — mcpctl login is refused on the Free tier, and commands that reach higher-tier features return a clear license error naming the tier they need.
Pricing
Choose your plan
Start free with core server management. Pro for a single team. Business for an organization running agents in production. Enterprise for the whole estate. Servers are never metered on any tier.
Open Source
Free
Free forever · Apache 2.0 licensed runtime
Up to 20 MCP servers · No signup · No credit card
  • Deploy and manage MCP servers
  • Health monitoring & metrics
  • Live metrics charts
  • Envoy gateway with xDS
  • Helm chart deployment
  • Basic RBAC (admin + viewer)
  • Call LLM models by name through the gateway
  • Developer portal — browse tools, mint scoped tokens
  • Community support via GitHub
  • CLI tool (mcpctl)
  • Model routing policy
  • Cost metering & chargeback
  • Namespace isolation
  • SSO & SCIM provisioning
  • Governance policies
  • Webhooks & audit trail
Get started on GitHub →
Subscription
Pro
$499/mo · billed annually
Up to 50 MCP servers · For a single team running their own servers
  • Everything in Free, plus:
  • Model routing — policy decides which model a caller reaches
  • Cost metering, departments & chargeback reports
  • Agent Galaxy — live entitlement graph
  • Rug-pull protection & quarantine kill switch
  • SSO (OIDC & SAML) — Okta, Azure AD, Google
  • SCIM 2.0 user provisioning
  • Governance policy engine
  • Multi-tenant namespace isolation
  • CLI tool (mcpctl) — scripting, CI, and automation
  • Deployment history & rollback
  • Webhook notifications (Slack, email)
  • Audit trail
  • Custom RBAC roles
  • Priority email & Slack support
  • Model comparison
  • AI Data Reach — govern the data agents can touch
  • Delegated administration
Try it now →
Commercial
Business
$30,000/yr
Unlimited servers · For an organization running agents in production
  • Everything in Pro, plus:
  • Model comparison — one prompt across models, cost side by side
  • Delegated administration
  • Governance policy export
  • Endpoint fleet inventory via your MDM (Jamf, Intune, Ansible)
  • Unlimited servers
  • Priority support
  • AI Data Reach & Catalog Universe
  • Continuous SOC 2 control evidence
Talk to us →
Commercial
Enterprise
Contact us for pricing
Unlimited servers · For the enterprise agent estate
  • Everything in Business, plus:
  • AI Data Reach — govern the data agents can touch, not just the tools they reach
  • Catalog Universe — across every source you configure (Databricks Unity Catalog, Snowflake, BigQuery)
  • Blast-radius analysis and grant simulation
  • Continuous SOC 2 control evidence
  • Agent capacity sized to your estate, expandable under contract
  • Contractual SLA and named support
  • Security and procurement review support
  • Custom license and payment terms
On the roadmap
  • Multi-cluster federation
  • Governance policy import
  • Bulk approvals
  • Just-in-time provisioning
Contact sales →