migrate-tools

migrate-tools is a command for Claude Code from umbraco/Umbraco-CMS-MCP-Dev. It costs 0 tokens per session (3,123 once invoked), scanned A, original, MIT.

A command that converts MCP tools from direct API calls to the project's standard helper-based pattern.

In plain words
What is it for?
It is for migrating a specified tool group to helpers such as standardized GET, void-operation, and result-creation functions.
Why use it?
It reduces differences between older and newer tools and standardizes how API results and errors are handled.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/umbraco/umbraco-cms-mcp-dev/migrate-tools
Clone the repo
git clone --depth 1 https://github.com/umbraco/Umbraco-CMS-MCP-Dev

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for migrate-tools

README.md
[![agentmods](https://agentmods.dev/badge/commands/umbraco/umbraco-cms-mcp-dev/migrate-tools.svg)](https://agentmods.dev/commands/umbraco/umbraco-cms-mcp-dev/migrate-tools)
Your own site
<a href="https://agentmods.dev/commands/umbraco/umbraco-cms-mcp-dev/migrate-tools"><img src="https://agentmods.dev/badge/commands/umbraco/umbraco-cms-mcp-dev/migrate-tools.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,123 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.03123
Opus 5 $0.00000 $0.01562
Sonnet 5 $0.00000 $0.00625
Haiku 4.5 $0.00000 $0.00312

Measured 4d ago against content hash 7afd638847a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

migrate-tools scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/migrate-tools.md · 396 lines

How it starts

The opening of the file, as written. The whole thing — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/migrate-tools

Migrates MCP tools from the old pattern to the new standardized pattern using helper functions.

Usage

/migrate-tools <tool-group-path>

Example:

/migrate-tools src/umbraco-api/tools/document-type

Description

This command helps migrate MCP tools from the old manual pattern (direct client calls with JSON.stringify) to the new standardized pattern using helper functions like executeGetApiCall, executeVoidApiCall, and createToolResult.

Old vs New Patterns

DELETE Operations (Void)

Old Pattern:

import { UmbracoManagementClient } from "@umb-management-client";
import { CreateUmbracoTool } from "@/helpers/create-umbraco-tool.js";

const DeleteTool = CreateUmbracoTool(
  "delete-item",
  "Deletes an item",
  schema.shape,
  async ({ id }) => {
    const client = UmbracoManagementClient.getClient();
    await client.deleteById(id);
    return {
      content: [{ type: "text" as const, text: JSON.stringify({ success: true }) }],
    };
  }
);

New Pattern:

import { ToolDefinition } from "types/tool-definition.js";
import { withStandardDecorators, executeVoidApiCall, CAPTURE_RAW_HTTP_RESPONSE } from "@/helpers/mcp/tool-decorators.js";

const DeleteTool = {
  name: "delete-item",
  description: "Deletes an item",
  inputSchema: schema.shape,
  annotations: {
    destructiveHint: true,
  },
  slices: ['delete'],
  handler: (async ({ id }: { id: string }) => {
    return executeVoidApiCall((client) =>
      client.deleteById(id, CAPTURE_RAW_HTTP_RESPONSE)
    );
  }),
} satisfies ToolDefinition<typeof schema.shape>;

export default withStandardDecorators(DeleteTool);

GET Operations (Returns Data)

Old Pattern:

const GetTool = CreateUmbracoTool(
  "get-item",
  "Gets an item",
  schema.shape,
  async ({ id }) => {
    const client = UmbracoManagementClient.getClient();
    const response = await client.getById(id);
    return {
      content: [{ type: "text" as const, text: JSON.stringify(response) }],
    };
  }
);

Read the full file on GitHub · 396 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 396 lines · 0 tokens per session scan A 7afd638847a2

Subscribe to this mod's changes

migrate-tools is a command published in the GitHub repository umbraco/Umbraco-CMS-MCP-Dev (39 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,123 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.