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 tough-tongue/toughtongue-skills --skill mcp-apps-buildergit clone --depth 1 https://github.com/tough-tongue/toughtongue-skillsWrote 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/tough-tongue/toughtongue-skills/mcp-apps-builder)<a href="https://agentmods.dev/skills/tough-tongue/toughtongue-skills/mcp-apps-builder"><img src="https://agentmods.dev/badge/skills/tough-tongue/toughtongue-skills/mcp-apps-builder/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/tough-tongue/toughtongue-skills/mcp-apps-builder"><img src="https://agentmods.dev/badge/skills/tough-tongue/toughtongue-skills/mcp-apps-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00068 | $0.00965 |
| Opus 5 | $0.00034 | $0.00483 |
| Sonnet 5 | $0.00014 | $0.00193 |
| Haiku 4.5 | $0.00007 | $0.00097 |
Grade A, and why
mcp-apps-builder 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 12d 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.
This is a copy
94% identical to mcp-apps-builder — 91 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build MCP Apps with mcp-use v2
Treat the installed mcp-use package, its generated types, and the project's existing exports as the source of truth. Check the installed version before changing code; do not assume APIs from mcp-use v1.
Workflow
- Inspect
package.json, the server entry, exported tool refs,views/, and the installedmcp-useversion. - Scaffold a new project with
npx create-mcp-use-app@latest; do not hand-build framework boilerplate. - Read only the references needed for the task:
- Server primitives for tools, resources, prompts, middleware, and result envelopes.
- Views for interactive MCP Apps and React hooks.
- Authentication for OAuth providers and authenticated tool handlers.
- Migration when converting v1 code or reviewing package boundaries.
- Verification before reporting completion.
- Implement against the package types. Export every statically declared tool ref that a View calls.
- Validate through the real lifecycle: build/typecheck, run the server, connect a client, call the tool, and render the View when one exists.
Native v2 invariants
- Import server APIs from
mcp-use; provider adapters come frommcp-use/oauth/*; React APIs come frommcp-use/react. - Define tools with
inputSchema; addoutputSchemawhen returning structured data or binding a View. - Return MCP result envelopes with
content,structuredContent, and optionally_metaorisError. - Put each View at
views/<name>/view.tsxand bind it withview: { name: "<name>" }. - Read the rendering call with
useToolContext; use focused hooks such asuseCallTool,useViewState,useHostContext, anduseDisplayModefor additional behavior. - Export the server as the default export. Let
mcp-use dev,build, andstartown framework lifecycle and View compilation. - Keep request state in the request context or an external store. Do not rely on module globals for cross-request identity or elicitation continuity.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 83 lines · 68 tokens per session scan A f03374ed4ad8
mcp-apps-builder is a skill published in the GitHub repository tough-tongue/toughtongue-skills (7 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 965 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to mcp-apps-builder, differing in 91 lines, and is treated as a copy.
Other skills, from other repositories
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
cqrs-implementation
Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.
workflow-orchestration-patterns
Design durable workflows with Temporal for distributed systems. Covers workflow vs activity separation, saga patterns, state management, and determinism constraints. Use when building long-running processes, distributed transactions, or microservice orchestration.
microservices-patterns
Design microservices architectures with service boundaries, event-driven communication, and resilience patterns. Use when building distributed systems, decomposing monoliths, or implementing microservices.
diagnose-backend-bug
Diagnose a bounded backend or multi-service failure from GitHub Issues, Jira, Aone, user-provided exports, logs, traces, responses, stack traces, or job records. Use when a service, API, RPC, worker, queue, CLI, or scheduled job bug needs correlation through the project's existing observability route before repair; do…
durable-objects
Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.