mcp-builder

mcp-builder is a skill for Codex from PracticalSwan/agent-skills. It costs 47 tokens per session (1,836 once invoked), scanned A, original, MIT.

A development guide for building MCP servers, which let coding agents use tools connected to APIs, services, or internal systems. It focuses on tool design, structured results, errors, and evaluations.

In plain words
What is it for?
Use it to create or improve MCP servers in TypeScript or Python, design tool schemas and pagination, handle failures, and test whether the tools are useful.
Why use it?
It helps make agent tools easier to discover, combine, and trust in real tasks.

Skill for Codex

Written for Codex: reads ~/.codex or $CODEX_HOME. Also seen: mentions subagents; mentions Claude Code; mentions Codex.

Good fit Use it to create or improve MCP servers in TypeScript or Python, design tool schemas and pagination, handle failures, and test whether the tools are useful.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/practicalswan/agent-skills/mcp-builder
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 PracticalSwan/agent-skills --skill mcp-builder
Clone the repo
git clone --depth 1 https://github.com/PracticalSwan/agent-skills

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.

agentmods badge for mcp-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/practicalswan/agent-skills/mcp-builder/github.svg)](https://agentmods.dev/skills/practicalswan/agent-skills/mcp-builder)
Your own site
<a href="https://agentmods.dev/skills/practicalswan/agent-skills/mcp-builder"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/mcp-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.

agentmods 80×15 button for mcp-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/practicalswan/agent-skills/mcp-builder"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/mcp-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,836 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

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 →

  • high Prompt Injection · line 205
    Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
    Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.01836
Opus 5 $0.00023 $0.00918
Sonnet 5 $0.00009 $0.00367
Haiku 4.5 $0.00005 $0.00184

Measured 3d ago against content hash 313a330fe648, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-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 3d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/connections.py, scripts/evaluation.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

mcp-builder/SKILL.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Builder

Design MCP servers that are easy for agents to discover, compose, and trust.

  • Leverage native parallel subagent dispatch and 200k+ context windows where available.

When to Use

Use symptom -> action triggers: when one matches, apply this skill and verify with the protocol below.

  • You are creating a new MCP server around an external API or internal platform.
  • An existing MCP server needs better tool naming, schemas, pagination, or error handling.
  • You need a workflow for evaluating whether an MCP server is actually useful for real agent tasks.
  • You are deciding between TypeScript and Python MCP implementations.

Glossary

  • MCP Inspector: An interactive client for browsing registered tools, schemas, inputs, and outputs while you validate a server.
  • Structured outputs: Predictable JSON or schema-backed payloads that downstream agents can parse safely instead of scraping prose.
  • Workflow tool: A higher-level tool that coordinates several lower-level API steps into one agent-friendly operation.

Core Workflow

1. Research First

Before implementation:

  1. Read the current MCP protocol documentation.
  2. Read the relevant SDK guide for your implementation language.
  3. Review the target service API and list the highest-value operations.
  4. Decide which operations should stay low-level and which deserve dedicated workflow tools.

2. Design Agent-Friendly Tools

Prefer tools that are easy to discover and compose:

  • use clear action-oriented names
  • keep schemas explicit and constrained
  • support pagination and filters where lists can grow
  • return structured content whenever the client can benefit from it
  • write error messages that tell the agent what to do next

3. Implement Shared Infrastructure

Build common pieces before individual tools:

  • authenticated API client
  • error formatter
  • response normalizer
  • pagination helpers
  • reusable schema utilities

4. Test the Server Like an Agent Would

Verify more than syntax:

Read the full file on GitHub · 236 lines

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.

  1. 3d ago Changed 313a330fe648
  2. 4d ago Changed be71c2348c64
  3. 7d ago First seen · 236 lines · 47 tokens per session scan A 962c9f24e9a3

Subscribe to this mod's changes

mcp-builder is a skill published in the GitHub repository PracticalSwan/agent-skills (14 stars, last pushed 3d ago), licensed MIT. It adds 47 tokens to every session and 1,836 once invoked, about $0.0002 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 2026-09-03.