TrialRun MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TRIALRUN_MODE | No | monitor or enforce. Default is monitor; the policy file's mode wins. | |
| TRIALRUN_ROLE | No | student or assessor. Default is student. | |
| TRIALRUN_STATE | No | Session log path (JSON Lines). Default is <workspace>/.trialrun-session.jsonl or ./trialrun-session.jsonl. | |
| TRIALRUN_WORKSPACE | No | Real folder to serve; switches to workspace mode. Leave out to serve the built-in demo scenario. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_filesB | List the files on the Fernvale Kitchens Ltd assessment desktop that the AI is allowed to see. Files the student has blocked are hidden. |
| read_fileA | Read a file (or one section of it) from the assessment desktop. Every read is logged by the gateway. Blocked files are refused. |
| get_access_policyA | Show the student's access checklist: which files the AI may and may not open. |
| check_textA | Scan an outgoing AI answer, a draft, or text the user pasted, for restricted data (credentials, cards, personal details, sensitive terms) before it is shown or saved. Hits are logged as leaks into the AI answer. Returns labels and redacted snippets only. |
| record_momentA | For a coaching skill: log a moment for one of three habits. habit: "check" (verifying AI output), "decide" (keeping a judgement call), "protect" (keeping restricted data out). outcome: "did" (the user did it unprompted), "prompted" (after a coaching note), "missed". Restricted values in the note are redacted before storage. |
| get_reportA | A short markdown report for the user: data stewardship score, restricted data by type and channel (counts only, no values), files read, and the three habits with recent examples. |
| get_audit_logB | Timestamped gateway events, restricted-data leak summary and a preliminary Data Stewardship score (Full / Partial / Zero). Contains labels and redacted snippets only. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| briefing | Criteria, statement guidelines and data categories shown to the student. |
| report | The same report as get_report. |
| audit | Raw JSON session state (access policy + events). Redacted snippets only. |
TDQS
Scored across 7 tools
Each tool has a fairly distinct purpose: policy viewing, file listing, file reading, text scanning, moment logging, reporting, and audit. The main overlap is get_report vs get_audit_log, which both surface restricted-data information, though the descriptions differentiate user-facing scoring from raw gateway events.
All seven tools follow a consistent snake_case verb_noun pattern (get_access_policy, list_files, read_file, check_text, record_moment, get_report, get_audit_log). No camelCase mixing or vague bare verbs.
Seven tools is well within the ideal 3-15 range and each maps to a distinct step of the stewardship workflow. Nothing feels padded or missing for the stated scope.
The read-and-monitor surface is coherent: policy, list, read, check, record, report, audit covers the assessment lifecycle. The only gaps are the absence of any file-search/write operation, which appears intentional for a read-only assessment sandbox.