# operant-mcp (npm · saagar-operant-mcp)

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

- Trust score: 69/100 (medium)
- Change this week: +16
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `operant-mcp.saagar210.workers.dev`: 64/100, [markdown](https://verifymcp.io/servers/saagpatel-operant-mcp/operant-mcp.md), [page](https://verifymcp.io/servers/saagpatel-operant-mcp/operant-mcp)
- npm · `saagar-operant-mcp`: 69/100 (this document), [markdown](https://verifymcp.io/servers/saagpatel-operant-mcp/saagar-operant-mcp.md), [page](https://verifymcp.io/servers/saagpatel-operant-mcp/saagar-operant-mcp)

## Channel facts

- Registry: `npm`
- Package: `saagar-operant-mcp`
- Version: `0.1.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 83/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known medium-severity CVE affects @hono/node-server 1.19.17, reached via @modelcontextprotocol/sdk > @hono/node-server. A fixed version is available.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 16 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 82/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 626 tokens (~89/item across 7 items; 5 tools + 2 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add saagpatel-operant-mcp -- npx -y saagar-operant-mcp
```

### Codex

```bash
codex mcp add saagpatel-operant-mcp -- npx -y saagar-operant-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "saagpatel-operant-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "saagar-operant-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add saagpatel-operant-mcp --command npx --arg -y --arg saagar-operant-mcp
```

### Hermes

```yaml
mcp_servers:
  saagpatel-operant-mcp:
    command: "npx"
    args: ["-y", "saagar-operant-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "saagpatel-operant-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "saagar-operant-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 68, +42)

- [security regression] GHSA-frvp-7c67-39w9 affects this package: medium
- [security regression] Provenance: unverified → fail
- [security regression] Known CVEs: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [functional regression] Security disclosure: fail → unverified
- [functional improvement] Schema quality: unverified → good
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Stability: unverified → 0.20
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional] Licence: MIT

### 2026-08-01 (score 26, +21)

- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Schema quality: unverified → 100

### 2026-07-31 (score 5, −30)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 35, +11)

- [security regression] Malware scan: pass → unverified
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Schema quality: unverified → 100

### 2026-07-28 (score 24, −29)

- [functional regression] Schema quality: 100 → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-07-27 (score 53)

First indexed and scored.

## MCP tools (5)

### `get_results` (~84 tokens)

Get calibration results

Return all model calibration profiles (OCS mean/stdev, orchestration mean, run_family, subject_shell), plus generated_at, included_lab_labels, and the not-a-flat-leaderboard caveat. Models are returned as-is — do not pre-sort into a naive leaderboard. Single-run models (null stdev) must not be ranked as-if reliable against multi-run models.

### `compare_models` (~112 tokens)

Compare two models

Side-by-side comparison of two models by display_name (case-insensitive substring). Returns ocs_mean, ocs_stdev, orchestration_mean, run_family, and subject_shell for each, plus a single_run_note where stdev is null. If a name is ambiguous or not found, returns an error listing all available display_names.

Input parameters:

- `model_a` (string, required): Display name (or substring) of the first model
- `model_b` (string, required): Display name (or substring) of the second model

### `get_methodology` (~85 tokens)

Get benchmark 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.

### `list_cases` (~111 tokens)

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.

Input parameters:

- `axis` (string): Axis to filter by: refusal-calibration | sanctioned-path | orchestration | escalation-reroute

### `get_case` (~122 tokens)

Get a 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.

Input parameters:

- `axis` (string, required): The axis this case belongs to
- `pair_id` (string, required): The pair_id (axes 1/2/4) or id (axis 3) to retrieve

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/saagpatel-operant-mcp/saagar-operant-mcp#diagnostics

## Score history

- 2026-08-03: 69
- 2026-08-02: 68
- 2026-08-01: 26
- 2026-07-31: 5
- 2026-07-30: 35
- 2026-07-28: 24
- 2026-07-27: 53

## Links

- npm package: https://www.npmjs.com/package/saagar-operant-mcp
- Socket report: https://socket.dev/npm/package/saagar-operant-mcp
- Repository: https://github.com/saagpatel/operant
- Changelog RSS feed: https://verifymcp.io/servers/saagpatel-operant-mcp/saagar-operant-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/saagpatel-operant-mcp/saagar-operant-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/saagpatel-operant-mcp/saagar-operant-mcp