Index / MCP servers / operant-mcp

operant-mcp MCP server

operant-mcp is a remote MCP server that gives an AI agent 5 tools, among them compare_models, get_case, get_methodology. It answers at https://operant-mcp.saagar210.workers.dev/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 23 October 2026, succeeded.

Status
Answering
Tools
5
Reliability
6 of 6 checks
Response time
307 ms
Transport
streamable HTTP
Last checked
23 October 2026

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

Description as the publisher wrote it.

The 5 tools operant-mcp offers

ToolWhat it does
compare_modelsPlace 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
Inputs: model_a, model_b
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. Axis 3 cases are single (unmatched) and use an 'id' field instead of 'pair_i
Inputs: pair_id, axis
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 what-it-measures / what-it-doesn't summary. Sourced from th
get_resultsReturn 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 reliabl
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). Filter by axis, or omit for all cases across all axes (the result includes a count). Use ge
Inputs: axis

Add operant-mcp to your AI client

Every block below points at https://operant-mcp.saagar210.workers.dev/mcp. Pick your client and copy.

Claude Code: one command in your terminal
claude mcp add --transport http operant-mcp https://operant-mcp.saagar210.workers.dev/mcp
Claude Desktop: claude_desktop_config.json
{
  "mcpServers": {
    "operant-mcp": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://operant-mcp.saagar210.workers.dev/mcp"]
    }
  }
}
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project
{
  "mcpServers": {
    "operant-mcp": {
      "url": "https://operant-mcp.saagar210.workers.dev/mcp"
    }
  }
}
VS Code and GitHub Copilot: .vscode/mcp.json
{
  "servers": {
    "operant-mcp": {
      "type": "http",
      "url": "https://operant-mcp.saagar210.workers.dev/mcp"
    }
  }
}
Zed: Zed settings.json
{
  "context_servers": {
    "operant-mcp": {
      "url": "https://operant-mcp.saagar210.workers.dev/mcp"
    }
  }
}
Windsurf: ~/.codeium/mcp_config.json
{
  "mcpServers": {
    "operant-mcp": {
      "serverUrl": "https://operant-mcp.saagar210.workers.dev/mcp"
    }
  }
}
JetBrains AI Assistant: Settings, Tools, AI Assistant, MCP, New MCP Server, as JSON
{
  "mcpServers": {
    "operant-mcp": {
      "url": "https://operant-mcp.saagar210.workers.dev/mcp"
    }
  }
}
Continue: .continue/mcpServers/neuronto.yaml
name: operant-mcp
version: 0.0.1
schema: v1
mcpServers:
  - name: operant-mcp
    type: streamable-http
    url: https://operant-mcp.saagar210.workers.dev/mcp
Gemini CLI: ~/.gemini/settings.json
{
  "mcpServers": {
    "operant-mcp": {
      "httpUrl": "https://operant-mcp.saagar210.workers.dev/mcp"
    }
  }
}
Codex CLI: MCP server config
{
  "mcpServers": {
    "operant-mcp": {
      "type": "http",
      "url": "https://operant-mcp.saagar210.workers.dev/mcp"
    }
  }
}
Warp: MCP servers, + Add, paste JSON
{
  "mcpServers": {
    "operant-mcp": {
      "url": "https://operant-mcp.saagar210.workers.dev/mcp"
    }
  }
}
Goose: a one-click extension link
goose://extension?url=https%3A%2F%2Foperant-mcp.saagar210.workers.dev%2Fmcp&type=streamable_http&id=operant-mcp&name=operant-mcp

Is operant-mcp up right now?

It answered our last check on 23 October 2026 in 307 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.

MCP servers similar to operant-mcp

Questions about operant-mcp

How many tools does operant-mcp have?

5, as returned by the server's own tools/list on 20 September 2026: compare_models, get_case, get_methodology, get_results, list_cases.

Is operant-mcp down?

It answered our last check on 23 October 2026 in 307 ms. Over 6 checks since 11 September 2026 it answered 6.

How do I add operant-mcp to Cursor?

Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://operant-mcp.saagar210.workers.dev/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.

Does operant-mcp need an API key?

It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.

Where this comes from

Publisher: io.github.saagpatel. Endpoint host: operant-mcp.saagar210.workers.dev. ARD identifier: urn:air:io.github.saagpatel:mcp:operant-mcp. First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page is inferred from its name. Ranking in Neuronto search is never for sale.

Is this your server? Get a message the day it stops answering or its tools change: monitoring, 14 days free. Or claim the domain to manage how it is listed.