What is mcp-server-builder?

A guide for building MCP servers that expose tools, data, or instructions to AI clients. It covers local and remote connections, authentication, deployment, and optional payment systems.

Use it to design tool, resource, and prompt schemas; build servers in TypeScript or Python; add OAuth authentication; wrap REST APIs; and deploy local or remote MCP services.

It helps developers turn an API or other service into a structured interface that AI clients can use, while addressing access control and deployment concerns.

mcp-server-builder — Skill for Codex by san-npm/skills-ws

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.

Any agent

npx skills add san-npm/skills-ws --skill mcp-server-builder

Clone the repo

git clone --depth 1 https://github.com/san-npm/skills-ws

Made for: Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/san-npm/skills-ws/mcp-server-builder/github.svg)](https://agentmods.dev/skills/san-npm/skills-ws/mcp-server-builder)

Your own site

<a href="https://agentmods.dev/skills/san-npm/skills-ws/mcp-server-builder"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/san-npm/skills-ws/mcp-server-builder"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/mcp-server-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,071 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.

Model	Per session	Once invoked
Fable 5.1	$0.00095	$0.01071
Opus 5.5	$0.00038	$0.00428
Sonnet 5.5	$0.00019	$0.00214
Haiku 4.5	$0.00010	$0.00107

Measured 2mo ago against content hash ed710729889b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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.

skills/mcp-server-builder/SKILL.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Server Builder — Production Skill

Pick the transport first. stdio for local-process servers (Claude Desktop, CLI). Streamable HTTP for everything remote/shared/monetized — StreamableHTTPServerTransport in TS (@modelcontextprotocol/sdk v1.x), FastMCP in Python. The two standard transports are stdio and Streamable HTTP. The old HTTP+SSE transport (/sse + /messages) is legacy/deprecated (replaced in spec 2025-03-26, current spec 2025-11-25); ship it only as a backward-compat appendix for old clients (see §2c).

Build production-grade Model Context Protocol servers that wrap any REST API into AI-callable tools, with three-tier auth, monetization, and battle-tested deployment.

Related skills: for the consuming side (connecting to / calling MCP servers) see mcp-client; for general agent architecture see ai-agent-building; for REST contract/versioning design see api-design; for the Stripe billing details behind §7 see stripe-billing; for the SSRF/secret-handling depth in §9 see security-hardening.

Reference guide

Read only the references needed for the current request:

When to Use: references/when-to-use.md
1. MCP Architecture Overview: references/1-mcp-architecture-overview.md
2. Server Setup — TypeScript (@modelcontextprotocol/sdk): references/2-server-setup-typescript-modelcontextprotocol-sdk.md
3. Server Setup — Python (FastMCP, the mcp package): references/3-server-setup-python-fastmcp-the-mcp-package.md
4. Tool Schema Design (JSON Schema): references/4-tool-schema-design-json-schema.md
5. REST API to MCP Pattern: references/5-rest-api-to-mcp-pattern.md
6. Three-Tier Authentication: references/6-three-tier-authentication.md
7. Monetization Strategy: references/7-monetization-strategy.md
8. Express.js Architecture: references/8-express-js-architecture.md
9. Security: references/9-security.md
10. Monitoring & Logging: references/10-monitoring-logging.md
11. Deployment: references/11-deployment.md
12. Testing with Claude Desktop & Claude Code: references/12-testing-with-claude-desktop-claude-code.md
13. Listing on mcpservers.org: references/13-listing-on-mcpservers-org.md
Tools: references/tools.md
Quick Start: references/quick-start.md
14. Environment Variables Reference: references/14-environment-variables-reference.md
15. Common Patterns & Gotchas: references/15-common-patterns-gotchas.md
16. Complete Production Checklist: references/16-complete-production-checklist.md
Appendix A: Graceful Shutdown: references/appendix-a-graceful-shutdown.md
Appendix B: Redis Rate Limiter (Production): references/appendix-b-redis-rate-limiter-production.md
Appendix C: Tool Registration Helper: references/appendix-c-tool-registration-helper.md

Read the full file on GitHub · 39 lines

Files

What ships with it

23 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.

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.

2mo ago First seen · 39 lines · 95 tokens per session scan A ed710729889b

Subscribe to this mod's changes

mcp-server-builder is a skill published in the GitHub repository san-npm/skills-ws (4 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 1,071 once invoked, about $0.0004 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 2026-08-31.

Backend and APIs Building agents

mcp-server-builder next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-server-buildersan-npm/skills-ws	Skill	4	1mo ago	MIT	A	95	Codex
mem0-oss-to-platformmem0ai/mem0	Skill	68k	2d ago	Apache-2.0	A	217	Claude Code, Codex
azure-mgmt-botservice-dotnetmicrosoft/skills	Skill	3.2k	yesterday	MIT	A	78	Claude Code
fastapi-router-pymicrosoft/skills	Skill	3.2k	yesterday	MIT	A	46	Claude Code
dev-runtimelangwatch/langwatch	Skill	5.0k	yesterday	Apache-2.0	A	172	Claude Code
api-designericrisco/rsc-harness	Skill	503	2d ago	MIT	A	105	Claude Code, Codex
migrate-segw-to-raparc-mcp/arc-1	Skill	252	yesterday	MIT	A	106	Claude Code