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 pomerium/mcp-app-typescript-template --skill create-mcp-toolgit clone --depth 1 https://github.com/pomerium/mcp-app-typescript-templateWrote 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/pomerium/mcp-app-typescript-template/create-mcp-tool)<a href="https://agentmods.dev/skills/pomerium/mcp-app-typescript-template/create-mcp-tool"><img src="https://agentmods.dev/badge/skills/pomerium/mcp-app-typescript-template/create-mcp-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/pomerium/mcp-app-typescript-template/create-mcp-tool"><img src="https://agentmods.dev/badge/skills/pomerium/mcp-app-typescript-template/create-mcp-tool.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 14 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00080 | $0.01134 |
| Opus 5 | $0.00040 | $0.00567 |
| Sonnet 5 | $0.00016 | $0.00227 |
| Haiku 4.5 | $0.00008 | $0.00113 |
Grade A, and why
create-mcp-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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add an MCP Tool to This Template
Fetch the upstream add-app-to-server skill for core SDK patterns, then apply them using the template-specific conventions below:
https://raw.githubusercontent.com/modelcontextprotocol/ext-apps/main/plugins/mcp-apps/skills/add-app-to-server/SKILL.md
Use WebFetch to retrieve that skill now. The steps below cover what is different in this template.
How This Template Differs from the Generic SDK Examples
| Generic ext-apps approach | This template |
|---|---|
Edit server.ts directly |
Edit server/src/server.ts inside the createMcpServer() function |
| Inline Zod schemas in the tool handler | Define schemas in server/src/types.ts, import into server.ts |
vite-plugin-singlefile for UI |
Widget build system in widgets/ — see the add-widget skill if you want a UI |
| Single-file server | createMcpHandler creates a fresh McpServer for each request |
All tools must be registered inside createMcpServer() in server/src/server.ts. This function is called once per request, so each request gets its own isolated McpServer instance. Do not add session managers or rely on transport session state; state that must survive a request belongs in explicit tool arguments or an external store.
Step 1: Define the Schema and Types
Edit server/src/types.ts. Every tool input must have a Zod schema and an inferred TypeScript type:
export const MyToolInputSchema = z.object({
query: z.string().describe('The search query'),
limit: z.number().int().min(1).max(50).optional().describe('Max results'),
});
export type MyToolInput = z.infer<typeof MyToolInputSchema>;
export interface MyToolOutput {
results: string[];
count: number;
[key: string]: unknown;
}
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.
- 9d ago First seen · 150 lines · 80 tokens per session scan A 08e5856a98bd
create-mcp-tool is a skill published in the GitHub repository pomerium/mcp-app-typescript-template (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 80 tokens to every session and 1,134 once invoked, about $0.0004 per session on Opus 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
purchasing
Create approved purchase orders with the create-purchase-order tool.
chatgpt-app-builder
Build, modify, debug, migrate, review, or verify TypeScript MCP servers and MCP Apps with mcp-use. Use for tools, resources, prompts, middleware, Views, authentication, Skills over MCP, scaffolding, and advanced features.
refunds
Check refund eligibility and use the refund-order tool safely.
chatgpt-app-builder
Guide developers through creating and updating ChatGPT apps. Covers the full lifecycle: brainstorming ideas against UX guidelines, bootstrapping projects, implementing tools/views, debugging, running dev servers, deploying and connecting apps to ChatGPT. Use when a user wants to create or update a ChatGPT app / MCP…
openapi-to-mcp
Build and deploy an MCP server from an OpenAPI / Swagger spec using the mcp-use TypeScript SDK. Use this skill whenever the user wants to "turn this OpenAPI spec into an MCP server", "make this API usable from Claude/ChatGPT", "wrap this Swagger doc as MCP tools", "expose this REST API to an LLM", "generate MCP tools…
codexless-browser-repair
Diagnose and temporarily repair Codexless Browser compatibility after a Codex, Chrome Skill, or Browser runtime update when Codexless Browser stopped working. Use for current-version Codexless Browser compatibility drift, not ordinary website bugs, general Browser operation, Codexless install/update work, or long-term…