MCP serverio.github.saagpatel/operant-mcp

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

UNRATEDActivestreamable-httpoperant-mcp.saagar210.workers.dev

Overview

Score?

UNRATED 0.800

of what a free look can see, on 31 looks

Looks

last 13 hr ago

Tools

More info

URL

operant-mcp.saagar210.workers.dev/mcp

streamable-http

Says it is

operant-mcp 0.1.1

protocol 2025-06-18

In the record since

32 days ago

Among servers18,413 with a card

0median 0.606 · this server 0.800 · highest on record 0.8561

Toolsfrom sha256:aa8d334a1d…c23b6a

The tools this server lists, read out of the definition it returned
Tool	Schema
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 compar	input · no output
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	input · no output
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	input · no output
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 cla	input · no output
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	input · no output

Verify it yourselfnpx teppi-check https://operant-mcp.saagar210.workers.dev/mcpcurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M1FZ2N0175SS4EZ9XBW0Q2VB