mcpbeat Sign in

operant-mcp MCP Server

answering

operant-mcp is answering right now. Last checked 1 min ago. 36 installs a week from npm. It exposes 5 tools. Last commit 10 Sep 2026.

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

Installs per day peak 149 · avg 12 · -22% w/w
a month agotoday
Uptime history 47 days of history
47 days agonow
100.0%
Uptime 24h
92 of 92 checks
5
Tools
read from the server
162 ms
Response time
average over 24h
36
Installs / week
npm and PyPI

What the code does

We read the source, 19 h ago · tools taken from the live server · rules 3dff92dd89df

Evidence

Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.

        proc = subprocess.run(
Deletes files or strips permissions operant_lab/harness_ablation.py:110
    "rm -rf": (
Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Builds a file path from a variable gen_cases.py:140
    out_path = args.out if os.path.isabs(args.out) else os.path.join(HERE, args.out)

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

We found things in this code

Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch operant-mcp and you get told the day something new turns up.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 1 min ago.

run in your terminal
claude mcp add operant-mcp --transport http https://operant-mcp.saagar210.workers.dev/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "operant-mcp": {
      "url": "https://operant-mcp.saagar210.workers.dev/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.operant-mcp]
url = "https://operant-mcp.saagar210.workers.dev/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "operant-mcp": {
      "url": "https://operant-mcp.saagar210.workers.dev/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "operant-mcp": {
      "url": "https://operant-mcp.saagar210.workers.dev/mcp"
    }
  }
}

Available tools 5

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

case
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) and use an 'id' field instead of 'pair_id'. Use list_cases to browse available ids.
cases
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 axes (the result includes a count). Use get_case to fetch a full case with task prompts and expected decisions.
compare
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_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.
methodology
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 / what-it-doesn't summary. Sourced from the baked case-file metadata.
results
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 them or treat stdev/significance as reliable model evidence.

Endpoints

URLTransportStateLatencyChecked
https://operant-mcp.saagar210.workers.dev/mcp streamable-http answering 179 ms 1 min ago

Alternatives to operant-mcp

same job, measured the same way
Localgym MCP Server
by lo-nau

Read-only MCP server for UK gym search using the LocalGym Agent API.

41 installs/wk local only
TypesenseKit
by typesensekit

95 typed Typesense operations for AI agents through an MCP server that is read-only by default.

94 installs/wk local only
TypesenseKit
by akshitkrnagpal

95 typed Typesense operations for AI agents through an MCP server that is read-only by default.

local only
Calibre-Web
by ni-c

Read-only MCP server for Calibre-Web: library search, browsing and covers via the OPDS feed

78 installs/wk local only
Recraft MCP Server
by muhammetali

Recraft AI Image Generation MCP Server for AI coding agents

84 installs/wk local only
Toolroute
by grossiweb

Route AI agent tasks to the best MCP server and LLM, scored on 132+ real benchmark executions.

1 410 installs/wk local only
AgentTrust
by raditotev

MCP Server for Agent Reputation & Trust Scoring

150 installs/wk local only
Monzo MCP
by partymola

Read-only MCP server for the Monzo banking API: OAuth, local transaction cache, spending analysis.

local only

operant-mcp — questions

Answers built from our own checks of this server.

What can operant-mcp do?
It exposes 5 tools, read directly from the server on our last check. Among them: compare_models, get_case, get_methodology, get_results, list_cases. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is operant-mcp working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 162 ms. The bar chart above shows every period we have measured.
How do I connect operant-mcp?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does operant-mcp need an API key?
No. operant-mcp completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 5 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is operant-mcp?
It answers our handshake in 162 ms on average, which is faster than 74% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
How many people use operant-mcp?
The npm package saagar-operant-mcp was installed 36 times in the last week. Week over week that is -22%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is operant-mcp open source?
Yes — it is published under the MIT licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.