Platform Analytics

Know which MCP servers earn their keep. Without the joins.

Every question about fleet health is a manual join across telemetry tables. That's not judgment — it's plumbing. These blueprints make the join, and hand back the same snapshot on a schedule.

Book a demo Browse every blueprint

What breaks when you do this by hand

Understanding one server's real performance means joining tables by hand. Every time.
No quick, repeatable snapshot exists for what's actually driving usage.
Errors and dormant connections stay invisible until someone goes looking.

What you get instead

One fleet-wide view — usage, errors, dormant connections
Per-server performance without a single hand-written join
Reporting on a schedule. Not on request.

This is the whole thing

The opening of MCP Server Insights — the system prompt, its typed parameters, and the tools it's allowed to reach, all declared up front. No canvas, no hidden nodes. 207 lines of source you can review in a pull request.

Read all 207 lines →

mcp-server-insights.fml

Copy

system("You are an analytical assistant querying BigQuery for MCP server telemetry.")

parameter("servername", type=string, title="Server Name")

require mcp BigQuery

components {
    schema("TenantStats") {
        tenant_name: string
        tenant_id: string
        status: string
        total_tool_calls: int
        total_errors: int
        error_rate: float
        active_users: int
        distinct_tools_called: int
        active_days: int
        first_call: string
        last_call: string
        days_since_last_call: int
        connected_but_never_called: bool
    }

2 blueprints you can run today

Every one is a typed FML plan. Open it, read the source, and run it — nothing here is a mockup.

MCP Server Insights

Knowing how one server is really doing means joining telemetry tables by hand. Every time.

Platform PMs

DevOps

Engineering leaders

Read the blueprint

MCP Fleet Overview

No quick, repeatable snapshot exists. Someone has to go looking, table by table.

Platform PMs

DevOps

Leadership

Read the blueprint

What every Blueprint here guarantees

Zero prompt drift

Every Blueprint is a versioned contract. Run 1 and run 10,000 behave identically.

Scoped sessions

Each LLM call sees only the context it needs — no one giant prompt, no context rot.

Typed output

Blueprints return validated objects pinned to a schema, not text you have to parse.

Reusable like an API

Parameterise once and call it from anywhere — versioned, auditable, shareable.