MCP Server Fleet
Next: Check that busier servers really draw bigger, then commit the experiment and write the Outcome.
We needed clean, repeatable pictures of how a company's MCP servers are used and who calls them, without waiting on live data.
Three map views of a six-server fleet: the roster, servers sized by use, and who calls each one. The sizing doesn't show in the captures, and nothing is committed.
What changed
The change that matters most, in plain words. Open any one to see it.
- 1
The fleet can be drawn alone or with the agents and people who call each server.
Who calls what · came from Mark Parson
- Busier servers are meant to be drawn bigger, but in the captures all six look the same size. In words
- Selecting a server shows its version, transport, tools, skills and sessions. In words
How we got here
Each change, traced back to the conversation it came from. A solid mark means the record names the source; a dashed one was matched by the draft and waits for review.
From the record: no recorded conversation behind this one.
qmap-c27-D1 The default data set reproduces the six-row server table exactly, and every view is deterministic for a given seed. — Mark Parson
The fleet can be drawn alone or with the agents and people who call each server.
Thanks to
People outside Qpoint first. Every thank-you points at something they said or made.
Built the fleet views
Matched: the record names nobody and the experiment is uncommitted, so there is no git authorship; it sits in Mark's qmap working tree.
All images
Every picture from this cycle. Click any one to step through them all.
The pairs
Everything captured · 7
The full record 0 decisions · 0 key-change entries · 269 words · 7 captures
The record stays as written, for agents and for audit: Key Changes, every decision, the artifacts and the visual record.
Open the record for c27 →