Skip to content

operant-mcp

by saagpatel · remote · local (npm) · no sign-in to list tools · v0.1.0 · published by GitHub user saagpatel

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

Read only
CompareRegistry entry

5 tools: 5 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http operant https://operant-mcp.saagar210.workers.dev/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

5 tools

Only reads 5Claude Code: allow
  • compare_modelsPlace two retained calculation profiles side by side by display_name substring.No findings

    Why it is in this group

    • The name "compare_models" says "compare": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_caseReturn 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.No findings

    Why it is in this group

    • The name "get_case" says "get": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_methodologyReturn 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…No findings

    Why it is in this group

    • The name "get_methodology" says "get": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_resultsReturn retained model calculation profiles plus generated_at, claim_status, claims_at_risk, and the bounded evidence_binding.No findings

    Why it is in this group

    • The name "get_results" says "get": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • list_casesReturn 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).No findings

    Why it is in this group

    • The name "list_cases" says "list": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http operant https://operant-mcp.saagar210.workers.dev/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__operant__get_results",
      "mcp__operant__compare_models",
      "mcp__operant__get_methodology",
      "mcp__operant__list_cases",
      "mcp__operant__get_case"
    ],
    "ask": [],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as operant. Review it before you use it.