mcp-builder

A guide to building Model Context Protocol servers. MCP is a standard connection that lets an AI system use outside tools and read outside data through a defined interface.

In plain words
What is it for?
Use it to design tools, data resources, and reusable prompts; choose local or remote connections; handle errors and secrets; and build servers with the TypeScript or Python SDK.
Why use it?
It helps make the server's available actions and data clear to the AI, while avoiding poorly defined tools, unsafe secret handling, and unsuitable connection methods.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/phuonghx/aim-cli/mcp-builder
Any agent
npx skills add phuonghx/aim-cli --skill mcp-builder
Clone the repo
git clone --depth 1 https://github.com/phuonghx/aim-cli

Made for: Claude Code, Codex.

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,202 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00080 $0.01202
Opus 5 $0.00040 $0.00601
Sonnet 5 $0.00016 $0.00240
Haiku 4.5 $0.00008 $0.00120

Measured yesterday against content hash aa72b1c24b93, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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.

aim/templates/aim-agents/skills/mcp-builder/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Building MCP Servers

The Model Context Protocol is the wiring that lets an AI system reach external tools and data through a stable contract. A well-built server makes that contract obvious; a poorly built one leaves the model guessing. The notes below are about getting the design right.

The Three Building Blocks

A server exposes some mix of three things:

Block What it gives the model
Tools Functions it can call to act
Resources Data it can read
Prompts Reusable prompt templates

Laying Out The Server

A minimal project

my-server/
├── src/
│   └── index.ts      # entry — McpServer from the TS SDK
├── package.json      # depends on @modelcontextprotocol/sdk
└── tsconfig.json

The TypeScript SDK is @modelcontextprotocol/sdk, which exports McpServer. The Python SDK is the mcp package — install it with pip install "mcp[cli]", and reach for FastMCP from mcp.server.fastmcp.

Transports

Transport Where it fits
stdio Local processes, CLI-launched servers
Streamable HTTP Remote and web-hosted servers (this superseded the old HTTP+SSE transport)

The current spec (revision 2025-06-18) standardizes exactly these two. WebSocket is not a standard transport. On any Streamable HTTP server, check the Origin header before trusting a request.

Designing Tools

What a good tool looks like

Trait What it means
Verb-first name fetch_invoice, archive_thread — the action is in the name
One job It does a single thing and does it cleanly
Typed input A schema with types and per-field descriptions
Predictable output A consistent, parseable result shape

Shaping the input schema

Piece Needed?
Top-level type Yes — object
Properties Define every parameter
Required list Name the mandatory ones
Descriptions Write them for a human reader

Read the full file on GitHub · 162 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. yesterday First seen · 162 lines · 80 tokens per session scan A aa72b1c24b93

Subscribe to this mod's changes

mcp-builder is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 1,202 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 2026-08-31.

Related

Other skills, from other repositories

hs-release

Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR. Use when asked to cut/start a release, bump the version, or publish a new Hindsight version.

vectorize-io/hindsight · 45 tokens

hindsight-local

Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).

vectorize-io/hindsight · 32 tokens

research-repository

Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.

Owl-Listener/designer-skills · 43 tokens

design-negotiation

Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).

Owl-Listener/designer-skills · 48 tokens

user-persona

Build research-grounded personas with goals, frustrations, and behavioural patterns. Use when decisions need a consistent user reference. For one session's emotional snapshot use empathy-map; for motivation framing use jobs-to-be-done.

Owl-Listener/designer-skills · 50 tokens

version-control-strategy

Define version control for design files, components, and libraries — branching, naming, and release. Use when file history is chaotic. For design system contribution rules, use design-system-governance (design-systems).

Owl-Listener/designer-skills · 50 tokens