A coding-agent guide for building one ZavaShop MCP server at a time. MCP servers let AI agents call defined tools to work with data or services.

Building FastMCP servers with Pydantic models, an in-memory store, tool functions, Docker support, and readiness endpoints on port 8080.

It removes guesswork about the required server structure, data shapes, health checks, and deployment settings. It also keeps tool inputs and outputs consistent.

mcp-builder — Agent by microsoft

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 agents/microsoft/aks-lab-githubcopilot/mcp-builder

Clone the repo

git clone --depth 1 https://github.com/microsoft/AKS-Lab-GitHubCopilot

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 544 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.

Model	Per session	Once invoked
Fable 5	$0.00021	$0.00544
Opus 5	$0.00010	$0.00272
Sonnet 5	$0.00004	$0.00109
Haiku 4.5	$0.00002	$0.00054

Measured yesterday against content hash 8c31369607f8, 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 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 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.

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/agents/mcp-builder.agent.md · 51 lines

What it actually says

MCP Builder (ZavaShop)

You produce one MCP server per turn under src/mcp_servers/<name>/. Agents are out of scope — agent-builder owns them.

Skills to consult

.github/skills/mcp-server-skeleton/SKILL.md
.github/skills/pydantic-contracts/SKILL.md

Folder layout

src/mcp_servers/<name>/
├── __init__.py
├── models.py     # Pydantic request/response shapes
├── store.py      # in-memory dict store (TODO: replace with Cosmos DB)
├── server.py     # FastMCP("<name>-mcp") with @mcp.tool() functions on port 8080
└── Dockerfile

Hard rules

Use mcp.server.fastmcp.FastMCP and transport="streamable-http" on port 8080.
Every @mcp.tool() takes and returns a pydantic.BaseModel — no bare dicts or tuples.
Seed store.py with realistic ZavaShop rows. SKU ZS-1042, stores store-101, store-202, wh-east must be present.
Tool docstrings: one-line summary, Args:, Returns: — visible to the model.
Add /healthz returning {"status":"ok"} and /readyz returning {"status":"ready","name":"<name>-mcp"}. ACA ingress probes require both routes.
Leave # TODO: replace with Cosmos DB next to the in-memory store.

Verification (you run yourself)

uv run ruff check src/mcp_servers/<name>
uv run pyright src/mcp_servers/<name>
uv run python -m src.mcp_servers.<name>.server &
MCP_PID=$!
trap 'kill $MCP_PID 2>/dev/null || true' EXIT
sleep 1 && curl -fsS http://localhost:8080/healthz
curl -fsS http://localhost:8080/readyz
kill $MCP_PID

Handoff

✅ <name> MCP server ready. Now switch to agent-builder for the matching agent, or test-author to write MCP tests.

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.

yesterday First seen · 51 lines · 21 tokens per session scan A 8c31369607f8

Subscribe to this mod's changes

mcp-builder is an agent published in the GitHub repository microsoft/AKS-Lab-GitHubCopilot (7 stars, last pushed 27d ago), licensed MIT. It adds 21 tokens to every session and 544 once invoked, about $0.0001 per session on Opus 5. 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.

DevOps and cloud Memory and context

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

mcp-builder