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.
npx skills add agentcathq/webmcp-react --skill webmcp-add-toolgit clone --depth 1 https://github.com/agentcathq/webmcp-reactWrote 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.
[](https://agentmods.dev/skills/agentcathq/webmcp-react/webmcp-add-tool)<a href="https://agentmods.dev/skills/agentcathq/webmcp-react/webmcp-add-tool"><img src="https://agentmods.dev/badge/skills/agentcathq/webmcp-react/webmcp-add-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.
<a href="https://agentmods.dev/skills/agentcathq/webmcp-react/webmcp-add-tool"><img src="https://agentmods.dev/badge/skills/agentcathq/webmcp-react/webmcp-add-tool.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00073 | $0.02213 |
| Opus 5.5 | $0.00029 | $0.00885 |
| Sonnet 5.5 | $0.00015 | $0.00443 |
| Haiku 4.5 | $0.00007 | $0.00221 |
Grade A, and why
webmcp-add-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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a WebMCP Tool
Overview
Each tool is a React component that calls useMcpTool. It registers on mount, unregisters on unmount. Tools can be headless (return null) or render UI showing execution state.
Workflow
- Determine the tool's name, description, input schema, and what the handler does
- Choose headless vs UI tool
- Scaffold using the appropriate template below
- Set annotations based on tool behavior
- Wire the component into the
<WebMCPProvider>tree
Template: Headless tool
For tools that do work without rendering anything visible:
import { useMcpTool } from "webmcp-react";
import { z } from "zod";
export function MyTool() {
useMcpTool({
name: "my_tool",
description: "One-line description of what this tool does",
input: z.object({
// Define each input field with .describe() for AI context
query: z.string().describe("The search query"),
}),
handler: async ({ query }, { signal }) => {
// signal aborts if the agent cancels — forward it to cancellable work
const result = await doSomething(query, { signal });
return {
content: [{ type: "text", text: JSON.stringify(result) }],
};
},
});
return null;
}
Template: Tool with execution state UI
For tools that show loading, results, or errors:
import { useMcpTool } from "webmcp-react";
import { z } from "zod";
export function MyTool() {
const { state, execute, reset } = useMcpTool({
name: "my_tool",
description: "One-line description of what this tool does",
input: z.object({
text: z.string().describe("Input text to process"),
}),
handler: async ({ text }) => {
const result = await process(text);
return { content: [{ type: "text", text: result }] };
},
onSuccess: (result) => {
// Optional: analytics, toast, etc.
},
onError: (error) => {
// Optional: error reporting
},
});
return (
<div>
<button onClick={() => execute({ text: "hello" })} disabled={state.isExecuting}>
{state.isExecuting ? "Processing..." : "Run"}
</button>
{state.lastResult && <p>{state.lastResult.content[0].text}</p>}
{state.error && <p className="error">{state.error.message}</p>}
<span>Executions: {state.executionCount}</span>
</div>
);
}
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.
- yesterday Changed · +32 lines 37a37e0ed28d
- 1mo ago Changed b3b0315c30ae
- 1mo ago First seen · 214 lines · 73 tokens per session scan A a3c7de658f0e
webmcp-add-tool is a skill published in the GitHub repository agentcathq/webmcp-react (90 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 2,213 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
react-expert
Expert-level React development with hooks, performance optimization, state management, and modern patterns. Use when the user mentions frontend, hooks, JSX, TypeScript, or Next.js, or when the task involves Modern React, State Management, Forms, or Performance Optimization.
react-hooks-composition
Advanced React hooks composition patterns - SWR integration, debounced search, memoized contexts, state machines, and performance optimization.
fp-react
Practical patterns for using fp-ts with React - hooks, state, forms, data fetching. Works with React 18/19, Next.js 14/15.
zustand-docs
Zustand — small, fast, scalable state management for React. Store creation, hooks, middleware, TypeScript.
react-patterns
A guide to modern React patterns, including components, hooks, server components, actions, forms, state updates, and TypeScript.
Functional Programming in React
Practical patterns for using fp-ts with React - hooks, state, forms, data fetching. Works with React 18/19, Next.js 14/15.