Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/OneWave-AI/claude-skillsnpx agentmods add skills/onewave-ai/claude-skills/mcp-server-builderWrote 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/onewave-ai/claude-skills/mcp-server-builder)<a href="https://agentmods.dev/skills/onewave-ai/claude-skills/mcp-server-builder"><img src="https://agentmods.dev/badge/skills/onewave-ai/claude-skills/mcp-server-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/onewave-ai/claude-skills/mcp-server-builder"><img src="https://agentmods.dev/badge/skills/onewave-ai/claude-skills/mcp-server-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 | $0.00079 | $0.01056 |
| Opus 5.5 | $0.00032 | $0.00422 |
| Sonnet 5.5 | $0.00016 | $0.00211 |
| Haiku 4.5 | $0.00008 | $0.00106 |
Grade A, and why
mcp-server-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 27d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Server Builder
An MCP server is how Claude reaches a system it does not otherwise know about — your database, your internal API, your ops tooling. The protocol is small. Almost every real problem is a design problem: which tools to expose and what they return.
Decide the Shape First
Local (stdio) — runs on the user's machine, launched by the client, credentials from the local environment. Right for developer tooling and anything touching localhost or a local database. Only that machine gets it.
Remote (HTTP) — deployed once, reached by URL, OAuth for identity. Right when a team needs it, or when the data lives in a service rather than on a laptop. Everyone gets updates the moment you deploy.
Build remote when more than one person will use it. Retrofitting local-only to multi-user later means redoing auth from scratch.
Tool Design — the part that matters
Tools are an interface for a model, not a REST API. The common failure is exposing twenty thin endpoint wrappers and watching the model chain them badly.
- Name the job, not the endpoint.
get_pipeline_boardbeatsquery_dealsplusquery_stagesplusquery_owners. - One call should answer a real question. If using your server always takes three calls in the same order, that sequence should have been one tool.
- Descriptions are prompts. Say what the tool is for, when to reach for it, and what it does not do. This text is the only instruction the model gets.
- Return prose-shaped, compact results. Trim nulls and internal ids nobody will use. A 40KB JSON blob buries the answer and eats the window.
- Paginate and cap. Always a default limit. Say in the response when results were truncated, and how to get the rest.
- Separate reads from writes. Writes get explicit, narrow tools with clear names — never a generic
executethat takes arbitrary input. - Errors are instructions. "No company matched 'acme' — try search_companies first" gets recovered from; "500 Internal Server Error" does not.
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.
- 27d ago First seen · 80 lines · 79 tokens per session scan A 938aec998d2c
mcp-server-builder is a skill published in the GitHub repository OneWave-AI/claude-skills (349 stars, last pushed 15d ago), licensed MIT. It adds 79 tokens to every session and 1,056 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 2026-09-20.
Other skills, from other repositories
form-strategy
Design forms that convert, validate well, resist spam, and integrate cleanly with downstream systems. Use this skill when designing or auditing any form (contact, signup, checkout, multi-step, embedded), planning validation logic, fighting spam, choosing form tooling, or improving form conversion. Triggers on form…
netlify-development
Best practices for building and deploying Netlify sites, covering serverless and edge functions, Netlify Blobs storage, the Image CDN, and build configuration. Use when writing Netlify Functions or Edge Functions, configuring netlify.toml or redirects/headers, managing environment variables across deploy contexts…
nextauth-authentication
Guidelines for implementing NextAuth.js (Auth.js v5) authentication in Next.js applications with session management and security best practices.
api-security-best-practices
Implement secure API design patterns including authentication, authorization, input validation, rate limiting, and protection against common API vulnerabilities.
apollo-graphql
Guidelines for developing GraphQL APIs and React applications using Apollo Client for state management, data fetching, and caching.
beautifulsoup-parsing
Expert guidance for HTML/XML parsing using BeautifulSoup in Python with best practices for DOM navigation, data extraction, and efficient scraping workflows.