Skip to content
Back to search
100
MCP live MCP 2025-11-25 streamable-http

operant-mcp

io.github.saagpatel/operant-mcp

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

Uptime
100.0%
1 direct probes · 30d
Response
169ms
last probe
Tools
5
callable
Resources
2
readable
Prompts
1
available

Tools · 5

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 the…

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_DURA…

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 / …

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 ax…

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) …

Resources · 2

results

Historical/local calculation profiles with the public integrity boundary (JSON)

operant://results
methodology

OPERANT benchmark design, axes, decision labels, and OCS formula (JSON)

operant://methodology

Prompts · 1

score_my_agent

A ready prompt explaining how to run OPERANT against your own Claude Code agent and how to read the OCS score.

How to use

Add to your Claude Desktop / Cursor / Cline MCP config:

{
  "mcpServers": {
    "operant-mcp": {
      "url": "https://operant-mcp.saagar210.workers.dev/mcp",
      "transport": "streamable-http"
    }
  }
}