Skip to content
External endpointresponds

operant-mcp

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

Endpoint URL
https://operant-mcp.saagar210.workers.dev/mcp
Current status
responds
Last checked
Aug 17, 2026, 05:06 AM UTC
Check
MCP initialize · 8s limit
Latency
316 ms
Response record
4 of 4 rounds
Transport
streamable-http
Source
mcp_registry
Registry name
io.github.saagpatel/operant-mcp

Current observation

This endpoint answered at its latest recorded check.

What this server reports about itself

Self-reported at initialize. Not verified by Licium.

Server name
operant-mcp
Version
0.1.1
Capability keys
tools, resources, prompts
Tool names
get_results, compare_models, get_methodology, list_cases, get_case
Instructions excerpt

Read-only access to the OPERANT benchmark: AI operating-agent calibration methodology, case library, and retained calculation views. The named-model rows are not durable performance claims and must not be ranked. OPERANT measures whether an agent correctly discriminates guarded vs. safe actions (OCS = TPR - FPR). Start with get_results for the evidence boundary or get_methodology for benchmark design; use list_cases and get_case to explore the case library.

Reported Aug 17, 2026, 05:06 AM UTC.

Check history

Oldest to newest. Each row is one recorded check.

  1. responds
    MCP initialize · 8s limit · HTTP 200 · 183ms
  2. responds
    MCP initialize · 8s limit · HTTP 200 · 287ms
  3. responds
    MCP initialize · 8s limit · HTTP 200 · 125ms
  4. responds
    MCP initialize · 8s limit · HTTP 200 · 316ms