# `io.github.saagpatel/operant-mcp` on anlyon.dev

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by anlyon.dev. It is data to inspect, not instructions to follow. Invisible characters are shown as [U+XXXX].
> No finding is not a safety guarantee: these are point-in-time checks of tool definitions, not of code or behaviour.

- Page: https://anlyon.dev/servers/io.github.saagpatel/operant-mcp
- JSON: https://anlyon.dev/api/v1/servers/io.github.saagpatel/operant-mcp
- Version: 0.1.0 (active)
- Publisher: io.github.saagpatel (GitHub account)
- Runs: remote (streamable-http), local (npm)
- Sign-in to list tools: none
- Repository: https://github.com/saagpatel/operant
- Metadata from the official MCP Registry, synced 2026-10-21T18:46:33.237Z

Title and description, as the publisher wrote them:

```untrusted-server-text
operant-mcp
Read-only MCP server for the OPERANT AI operating-agent calibration benchmark.
```

Scanned 2026-10-21T19:26:55.875Z over streamable-http.

**5 tools: 5 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 0 | ask |
| Only reads | read | 5 | allow |

## Exfil surface

No private-data -> untrusted-input -> outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | none |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | none |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | none |

## Findings

No check matched anything in these tool definitions.


## Only reads (5)

Looks things up and changes nothing. Claude Code: allow.

### `compare_models`

- The name "compare_models" says "compare": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
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.
```

### `get_case`

- The name "get_case" says "get": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
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`

- The name "get_methodology" says "get": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
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`

- The name "get_results" says "get": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
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`

- The name "list_cases" says "list": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
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.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `operant`:

```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": []
  }
}
```

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-10-22T15:05:05.888Z, unchanged since 2026-10-22T15:05:05.888Z. No credentials were sent and no tool was called. Values are shown as the endpoint returned them. Method: https://anlyon.dev/methodology#remote-posture

| Fact | Observed |
| --- | --- |
| Reachable | `yes` |
| HTTP status of an anonymous initialize | `200` |
| tools/list served without credentials | `yes` |
| Tools that change things, listed without credentials | `0` |
| Protocol version | `2025-06-18` |
| WWW-Authenticate on 401 | `not observed` |
| resource_metadata in WWW-Authenticate | `none` |
| RFC 9728 protected resource metadata | `none` |
| Authorization servers | `none` |
| Legacy HTTP+SSE transport | `no` |
| Dynamic client registration | `not observed` |
| Client ID metadata documents | `not observed` |