Demos

Magertron™ platform demo

The whole platform in one walkthrough: governing LLM, MCP and API traffic on Kubernetes, with metering, budgets, chargeback and audit built in.

From VS Code to governed

A developer submits an MCP server; a person decides what happens next

• A small MCP server built in VS Code and tested in the MCP Inspector.
• One command — Magertron: Submit MCP Server for Review — sends its manifest, with anything credential-shaped stripped before it leaves the laptop. Submitting is not deploying.
• The platform team sees the submission at once, attributed to who sent it and from where, and opening it is recorded as a review.
• The operator stages it, chooses the namespace, and registers it; a pre-flight test finds both tools before anything is created.
• A person approves it, and access is granted by role in Tool Explorer — governed from the first call.

Agent Galaxy

Traffic in real time

• The galaxy pulses live traffic — human to agent to tool call to data securable.
• The first prompt succeeds with two calls, and the full call chain is there as evidence.
• Then permissions change. Deterministically the next call fails, and the audit trace says so.
• From the trace the operator diagnoses and remediates. The subsequent call traces all the way to the Snowflake lakehouse and succeeds.
• Last, the admin reveals the prompt alongside the verifiable, reproducible evidence object.

Catalog Universe

Diagnosing a partial failure

• The same live graph, but this prompt only partially works — one tool call fails because a table carried no permission.
• The audit log shows why: the mcp-consumer role had no select on that precise schema.
• The admin grants traversal on the schema, and the display fills in the coverage the red bricks were marking.
• The same prompt then succeeds, and the audit trace shows the completed chain.

Chargeback and reporting

Where the money went, by whoever asks

• A set of reports on a monthly cadence, out of the box.
• Chargeback statements for the current month or across months.
• The aggregated total is the same figure across several of them — one record, several readings.
• Totals by vendor, and by department, user and service account.

Registering an LLM

Provider, contract and rate card

• Register a new LLM, choose a model, add the credentials.
• Attach a cost contract with the known details — input, output, cache read and cache write, each with its own unit cost.
• Set the spend limit here; other thresholds are editable later.
• Review, register, then view the agent integration specifics — the same details your developers see in the developer portal.
• When the review process has completed, approve the LLM for use.

Model comparison

Same prompt, every registered provider

• How many LLM providers are registered, and how do they compare on an arbitrary prompt?
• Each model returns its answer, and Magertron computes the timing, the cost, and the input and output tokens for each.