# `com.soxoa/automation-planning` 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/com.soxoa/automation-planning
- JSON: https://anlyon.dev/api/v1/servers/com.soxoa/automation-planning
- Version: 1.0.0 (active)
- Publisher: com.soxoa (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-10-21T18:05:29.554Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Soxoa Automation Planner
Estimate illustrative automation ROI and rank recurring workflows to automate. Read-only, no auth.
```

Scanned 2026-10-21T18:55:44.170Z over streamable-http.

**3 tools: 3 change things.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 3 | ask |
| Only reads | read | 0 | allow |

## Findings

No check matched anything in these tool definitions.


## Changes things (3)

Creates or changes something that can be changed back. Claude Code: ask.

### `build_workflow_pilot`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

Description, as the server wrote it:

```untrusted-server-text
Builds a pilot plan from supplied workflow facts: current steps, trigger, inputs, desired output, source and destination systems, review owner, risk, data sensitivity and success checks. Returns proposed steps, tools, a ready-to-use drafting prompt, review gates, acceptance checks, rollout and a Markdown plan. It does not connect accounts, start provider work, store a plan, send messages or execute the workflow.
```

### `estimate_automation_roi`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

Description, as the server wrote it:

```untrusted-server-text
Estimates reclaimable team capacity and an illustrative payback period from caller-supplied workload figures. Requires people, weekly hours per person and loaded hourly cost; when automatable share or working weeks are omitted, the server uses 60% and 48. Payback is calculated only when an implementation cost is supplied. Returns weekly and annual hours reclaimed, annual capacity value, payback months, the assumptions used and a recommended next step. Results are planning estimates, not guaranteed savings or financial advice.
```

### `prioritize_automation_workflows`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

Description, as the server wrote it:

```untrusted-server-text
Ranks 1 to 12 caller-described workflows by value, predictability, judgment, data sensitivity and integration complexity, and labels each automate, assist or discovery. Each workflow requires a name, weekly hours, predictability, judgment required, error cost, data sensitivity and system count. Returns each workflow's score, recommendation, human-review flag and rationale, plus a recommended first workflow and guardrails. It does not connect to or change any system.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `automation-planning`:

```json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__automation-planning__estimate_automation_roi",
      "mcp__automation-planning__prioritize_automation_workflows",
      "mcp__automation-planning__build_workflow_pilot"
    ],
    "deny": []
  }
}
```