mcp-server-skeleton

A starting template for building an MCP server with FastMCP and streamable HTTP. MCP, or Model Context Protocol, is a way for an AI agent to call tools that access data or services.

In plain words
What is it for?
Use it to scaffold a server that exposes tools such as stock lookups, define its data models, implement storage access, and provide health and readiness checks.
Why use it?
It gives new servers a consistent layout, typed input and output models, a storage layer, a Dockerfile, and health endpoints for deployment checks.

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/microsoft/aks-lab-githubcopilot/mcp-server-skeleton
Any agent
npx skills add microsoft/AKS-Lab-GitHubCopilot --skill mcp-server-skeleton
Clone the repo
git clone --depth 1 https://github.com/microsoft/AKS-Lab-GitHubCopilot

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 554 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.00554
Opus 5 $0.00000 $0.00277
Sonnet 5 $0.00000 $0.00111
Haiku 4.5 $0.00000 $0.00055

Measured 2d ago against content hash 84843e3296e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-server-skeleton scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

sleep 1 && curl -fsS http://localhost:8080/healthz
.github/skills/mcp-server-skeleton/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: MCP Server Skeleton (FastMCP, streamable-http)

Reference layout

src/mcp_servers/<name>/
├── __init__.py
├── models.py
├── store.py
├── server.py
└── Dockerfile

server.py template

from __future__ import annotations

from mcp.server.fastmcp import FastMCP
import structlog
from starlette.requests import Request
from starlette.responses import JSONResponse

from .models import StockQuery, StockReport
from .store import lookup_stock

log = structlog.get_logger("<name>-mcp")
mcp = FastMCP("<name>-mcp", host="0.0.0.0", port=8080, streamable_http_path="/mcp")


@mcp.custom_route("/healthz", methods=["GET"])
async def healthz(_request: Request) -> JSONResponse:
    """Return process health for container probes."""

    return JSONResponse({"status": "ok"})


@mcp.custom_route("/readyz", methods=["GET"])
async def readyz(_request: Request) -> JSONResponse:
    """Return readiness for ACA ingress probes."""

    return JSONResponse({"status": "ready", "name": "<name>-mcp"})


@mcp.tool()
async def check_stock(query: StockQuery) -> StockReport:
    """Return on-hand stock and reorder point for each requested location.

    Args:
        query: SKU and list of location IDs.
    Returns:
        StockReport with one LocationStock per requested location.
    """
    log.info("tool.check_stock", sku=query.sku, locations=query.locations)
    return await lookup_stock(query)


if __name__ == "__main__":
    mcp.run(transport="streamable-http")

models.py rules

  • Every request / response is a Pydantic v2 model with model_config = ConfigDict(frozen=True).
  • Field names are snake_case; alias to camelCase only if an external API requires it.

store.py rules

  • In-memory dict keyed by primary key. Leave the marker:
    # TODO: replace with Cosmos DB (see specs/storage.md)
    
  • Seed with at least: SKU ZS-1042; locations store-101, store-202, wh-east.

Acceptance

uv run python -m src.mcp_servers.<name>.server &
sleep 1 && curl -fsS http://localhost:8080/healthz
curl -fsS http://localhost:8080/readyz
kill %1

Read the full file on GitHub · 83 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. 2d ago First seen · 83 lines · 0 tokens per session scan A 84843e3296e9

Subscribe to this mod's changes

mcp-server-skeleton is a skill published in the GitHub repository microsoft/AKS-Lab-GitHubCopilot (7 stars, last pushed 27d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 554 tokens. A static security scan graded it A with 1 finding (makes network calls). 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens