io.github.saagpatel/operant-mcp

pkg:npm:saagar-operant-mcp

Read-only MCP server for the OPERANT AI operating-agent calibration benchmark.

transport:: remote + stdio
credential class:: open
repo:: https://github.com/saagpatel/operant

Owner verification

Not yet verified. Verifying proves you control this server and is free, permanently — it never changes a published score.

Start verification →

Tools

compare_models
Place two retained calculation profiles side by side by display_name substring. Returns ocs_mean, ocs_stdev, orchestration_mean, run_family, and subject_shell for each, plus comparison_status=NOT_DURABLE and the public claim_status. This is not evidence that either named model outperforms, equals, or differs significantly from the other. If a name is ambiguous or not found, returns an error listing all available display_names.
shallow
get_case
Return the full case for a given pair_id (axes 1/2/4) or id (axis 3): malign and benign task prompts, expected decisions, grounding rationale, and bypass patterns. Axis 3 cases are single (unmatched) and use an 'id' field instead of 'pair_id'. Use list_cases to browse available ids.
shallow
get_methodology
Return the benchmark design: the 4 axes, the OCS formula (Youden's J), the 5 decision labels (PROCEED, PROCEED_SANCTIONED, REFUSE, ESCALATE, REROUTE), scoring blocks, and a concise what-it-measures / what-it-doesn't summary. Sourced from the baked case-file metadata.
shallow
get_results
Return retained model calculation profiles plus generated_at, claim_status, claims_at_risk, and the bounded evidence_binding. These rows are not durable named-model performance claims. Do not rank them or treat stdev/significance as reliable model evidence.
shallow
list_cases
Return case metadata (no full task prompts): pair_id/id, axis, tier, grounding, and side indicators (malign/benign for axes 1/2/4; null for axis 3). Filter by axis, or omit for all cases across all axes (the result includes a count). Use get_case to fetch a full case with task prompts and expected decisions.
shallow

Embed this server’s score

Tool count and median score across every tool in this server’s corpus — honest in a way a single cherry-picked tool’s badge wouldn’t be.

[![Vouch score](https://vouch.tools/api/servers/8c068fdf-6645-446f-bbd1-010b79807593/badge.svg)](https://vouch.tools/servers/8c068fdf-6645-446f-bbd1-010b79807593)