MCP server

operant-mcp

io.github.saagpatel/operant-mcp

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

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

Source

At a glance

Type

MCP server

Publisher

Not verified

Status

Working at last check

Tools

5

Token cost

About 887 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

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

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.operant-mcp]
url = "https://operant-mcp.saagar210.workers.dev/mcp"

Gemini CLI

{"mcpServers":{"operant-mcp":{"httpUrl":"https://operant-mcp.saagar210.workers.dev/mcp"}}}

Cursor

{"mcpServers":{"operant-mcp":{"url":"https://operant-mcp.saagar210.workers.dev/mcp"}}}

VS Code

{"servers":{"operant-mcp":{"type":"http","url":"https://operant-mcp.saagar210.workers.dev/mcp"}}}

Antigravity

agy mcp add operant-mcp https://operant-mcp.saagar210.workers.dev/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"operant-mcp","server_url":"https://operant-mcp.saagar210.workers.dev/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"operant-mcp","server_url":"https://operant-mcp.saagar210.workers.dev/mcp"}

Tools

• compare_models ~242 tokens
  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, o
• get_case ~213 tokens
  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.
• get_methodology ~118 tokens
  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.
• get_results ~114 tokens
  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.
• list_cases ~200 tokens
  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 d

Browse

• GitHub tools
• GitHub and code hosting

Related MCP servers

• saagarpatel.dev Portfolio
  Agent-native MCP server over the public saagarpatel.dev corpus. Read-only, stateless.
• Stratalize Crypto & DeFi
  Retired. Use com.stratalize/stratalize.
• RentalAnalytics rent tools
  Read-only HUD rent lookup and the site's existing rental calculators.
• AgentMart Procurement
  Procure, compare, quote, budget, and execute web extraction or scraping across providers for agents
• Phasefolio
  Biotech rNPV/PoS engine for AI agents. Signed exports, evidence register, asset landscape.
• DNAAI prediction ledger
  Read-only ledger of agent forecasts: events, rules, leaderboard, calibration.
• Tresslers Intelligence MCP Server
  Sovereign intelligence dossiers, daily briefings, RAG search, knowledge graph, codon optimizer.
• The Cure Protocol
  Agent research API for 15 disease areas, plus a T1D cure lab, sourced evidence ledger and models.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.github.saagpatel/operant-mcp.svg)](https://aptlynx.net/servers/io.github.saagpatel/operant-mcp)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents