create-tool

create-tool is a command for Claude Code from Matt-Dionis/claude-code-configs. It costs 10 tokens per session (466 once invoked), scanned A, original, MIT.

A command for creating a FastMCP tool protected by a blockchain token requirement. FastMCP is a framework for exposing tools that MCP-compatible applications can call.

In plain words
What is it for?
Use it to generate a protected tool with named inputs, optional settings, token requirements, error handling, and an MCP-formatted response.
Why use it?
It provides the server structure and protection logic needed to require a specific token before a tool runs.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to generate a protected tool with named inputs, optional settings, token requirements, error handling, and an MCP-formatted response.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/matt-dionis/claude-code-configs/create-tool
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.

Clone the repo
git clone --depth 1 https://github.com/Matt-Dionis/claude-code-configs

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 create-tool

README.md
[![agentmods](https://agentmods.dev/badge/commands/matt-dionis/claude-code-configs/create-tool/github.svg)](https://agentmods.dev/commands/matt-dionis/claude-code-configs/create-tool)
Your own site
<a href="https://agentmods.dev/commands/matt-dionis/claude-code-configs/create-tool"><img src="https://agentmods.dev/badge/commands/matt-dionis/claude-code-configs/create-tool/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for create-tool

Your own site · 80×15
<a href="https://agentmods.dev/commands/matt-dionis/claude-code-configs/create-tool"><img src="https://agentmods.dev/badge/commands/matt-dionis/claude-code-configs/create-tool.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 466 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00010 $0.00466
Opus 5.5 $0.00004 $0.00186
Sonnet 5.5 $0.00002 $0.00093
Haiku 4.5 $0.00001 $0.00047

Measured 1mo ago against content hash aa5309253c62, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

create-tool 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 1mo 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.

configurations/mcp-servers/token-gated-mcp-server/.claude/commands/create-tool.md · 80 lines

What it actually says

Create Token-Gated Tool

Create a new FastMCP tool with token protection using the Radius MCP SDK.

Parameters: $ARGUMENTS

Tool Creation Steps

  1. Parse Arguments

    • Extract tool name, token ID, and optional tier
    • Validate token ID format
    • Determine appropriate access pattern
  2. Generate Tool Implementation

server.addTool({
  name: '{tool_name}',
  description: '{description} (requires token {token_id})',
  parameters: z.object({
    // Define your parameters here
    input: z.string().describe('Input data'),
    options: z.object({
      format: z.enum(['json', 'text']).optional(),
      verbose: z.boolean().optional()
    }).optional(),
    __evmauth: z.any().optional().describe('Authentication proof')
  }),
  handler: radius.protect({token_id}, async (args) => {
    // Tool implementation
    try {
      // Process the input
      const result = await process{ToolName}(args.input, args.options);
      
      // Return MCP-formatted response
      return {
        content: [{
          type: 'text',
          text: JSON.stringify(result, null, 2)
        }]
      };
    } catch (error) {
      throw new Error(`{tool_name} failed: ${error.message}`);
    }
  })
});
  1. Add to Appropriate Tier

    • Map to correct token tier
    • Update TOOL_REQUIREMENTS mapping
    • Document access requirements
  2. Create Test Case

    • Unit test for the tool
    • Auth flow test
    • Error handling test
  3. Update Documentation

    • Add to tool registry
    • Document parameters
    • Include usage examples

Generate Complete Tool

Based on the arguments provided, create:

  1. Tool implementation file
  2. Test file
  3. Documentation update
  4. Integration with existing server

The tool should follow FastMCP best practices and properly integrate with the Radius MCP SDK for token protection.

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. 1mo ago First seen · 80 lines · 10 tokens per session scan A aa5309253c62

Subscribe to this mod's changes

create-tool is a command published in the GitHub repository Matt-Dionis/claude-code-configs (619 stars, last pushed 1y ago), licensed MIT. It adds 10 tokens to every session and 466 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-09-03.