Tools Reference

The Autousers MCP server exposes 39 tools across four categories. Read-only tools carry readOnlyHint=true and are safe to call without side effects. Write tools mutate data or queue Gemini runs.

Templates (6 tools)

• templates_list — List question templates available to the caller
• templates_get — Fetch a single template by ID
• templates_create — Create a new team-scoped template
• templates_update — Patch a template (only supplied fields change)
• templates_delete — Hard-delete a template (refuses if attached to an eval)
• templates_duplicate — Deep-clone a template into a destination team

Evaluations (14 tools)

• evaluations_list — List evaluations the caller can see
• evaluations_get — Fetch a single evaluation by ID (includes config and comparisons)
• evaluations_create — Create an SSE or SxS evaluation; optionally queue autouser runs
• evaluations_update — Patch scalar and share fields on an evaluation
• evaluations_delete — Hard-delete an evaluation and its dependent rows
• evaluations_save_draft — Merge wizard fields into a draft evaluation
• evaluations_ratings_list — List human + autouser ratings for an evaluation
• evaluations_results_get — Aggregate stats and per-rater summaries
• evaluations_agreement_get — Pairwise Cohen's Kappa inter-rater agreement
• evaluations_ai_insights_get — Gemini-authored summary, key findings, and recommendations
• evaluations_export_get — Download results as JSON or CSV
• evaluations_share_create — Grant a per-user VIEWER/EDITOR/OWNER share
• evaluations_shares_list — List explicit per-user shares on an evaluation
• evaluations_transfer — Transfer ownership to another user

Autousers (15 tools)

• autousers_list — List autousers (built-in + custom); pass includeSystem:false for custom only
• autousers_get — Fetch a single autouser by ID
• autousers_create — Create a team-scoped custom autouser
• autousers_update — Patch a custom autouser
• autousers_delete — Soft-delete a custom autouser
• autousers_duplicate — Deep-clone an autouser into a team
• autousers_run — Queue autouser runs against an evaluation (incurs Gemini cost)
• autousers_run_stop — Cancel pending or running autouser runs
• autouser_status_get — Run statuses and summary counts for an evaluation
• autouser_run_get — Fetch one autouser run with autouser and evaluation summaries
• autouser_run_turns_list — Per-turn token and cost telemetry for a run
• autousers_calibration_start — Compute Cohen's Kappa vs human ratings
• autousers_calibration_status_get — Calibration status; pass includeEvals:true for eval picker
• autousers_calibration_freeze — Mark a rubric version as frozen and set it as active
• autousers_calibration_optimize — Send disagreements to Gemini for rubric suggestions

Settings (4 tools)

• teams_list — List every team the caller belongs to
• teams_get — Fetch one team's detail including the full member list
• team_members_list — List members of a team with roles and profiles
• usage_get — Team usage rollup: free-run pool remaining and Gemini token spend