The MCP server is for building and inspecting. It can create a configuration, run a preview, and read every score and piece of feedback — but it cannot accept content or ship it. Those decisions stay with people, in the Speedtrain UI.
What it is good at
Authoring configurations
Create and push versions from a document, using the platform’s own authoring guide as reference.
Inspecting results
Query review items, read per-rule scores and feedback, and find which rule is doing the rejecting.
Running test sessions
Preview a draft version over a selection of documents before anyone publishes it.
Managing destinations
List, create, and set the status of destinations.
What it deliberately cannot do
That boundary is the point. An agent can do the laborious part — drafting rules, reading hundreds of rejections, spotting which check is noisy — while the decisions that carry consequences remain with a person.Getting oriented
Two things are worth knowing before an agent calls anything:1
Nothing is inferred from your credential
Every call takes a tenant and an environment. The first two calls in any session get them.
2
The authoring guide is a tool, not a document
The server serves its own complete configuration reference and a fill-in template. An agent should read them before authoring or before interpreting classifier feedback, rather than guessing at the document shape.
Connect to the MCP server
Add the server to Claude, Claude Code, or a script.
Management MCP tools
Every tool the server exposes, and what it takes.