Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@workshop-mcp Guide me through building a tool that checks public weather data."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An open-source starting point for anyone to build a local MCP server with guidance from Codex or Claude Code. Describe your idea; your coding agent helps investigate it, asks the necessary questions, builds the integration, tests it, and connects it to your app.
This starter contains no ready-made tools. It provides a runnable Python server, a guided workflow, and installation helpers. No model API key is needed for the server itself; your chosen coding agent has its own access requirements.
MCP (Model Context Protocol) is a shared way for AI applications to discover and call tools. Your coding agent is the assistant; this Python server provides the tools; an external API, website, or database supplies the data or actions. The local app starts this server and communicates over stdio (standard input and output). You do not need a public URL, web server, or cloud deployment. External services may still require an internet connection and authentication.
Related MCP server: dev-mcp
Install Git, Python 3.11+ and uv using Preparation.
Clone this repository into your own working folder. Replace YOUR-REPO-URL
with this repository's GitHub URL once published:
git clone YOUR-REPO-URL my-mcp
cd my-mcpSign in to Codex or Claude Code. In Codex, add/open the cloned folder as a
project and start a task in it. In Claude Code, open a terminal in this folder
and run claude. The agent must see this repository's AGENTS.md. Send:
Read AGENTS.md and guide me through building my own MCP server. Start by checking prerequisites and cloning the required SDK reference. My idea is: …
The agent runs the preparation steps below, asks about your needs, and builds only your chosen integration. You can also run preparation yourself:
python3 scripts/bootstrap.py
uv sync --locked
uv run python scripts/smoke_test.py --expect-emptyOn Windows PowerShell, use python instead of python3 for the first command.
An empty tool list is expected until you build your integration.
Once your integration passes its tests, follow Install locally. That guide explains naming, user versus project setup, connection checks and removal.
Prepare → clone the SDK → describe your use case → verify access → agree on
tools and permissions → build and test → install → try your own example questions.
The agent saves non-secret progress in the ignored .local/ folder so you can
continue later. You do not need to answer everything at once.
Ideas include checking public weather data, reading selected records from your database, or looking up information behind an authenticated API. These are intake examples, not implemented features. Writes are disabled by design until you and the agent explicitly agree on them and implement appropriate restrictions.
AGENTS.md: step-by-step instructions for your coding agent.
src/usecase_mcp/: the empty server, settings, and places for tools/clients.
scripts/: preparation, protocol check, config output and bundle builder.
reference.json: pinned official SDK revision and example paths.
packaging/: optional Claude Desktop bundle template and launcher.
docs/: intake, security,
installation, bundles,
testing, and example scenarios.
The official SDK is installed as a locked dependency. Its separate Git clone is mandatory learning/reference material and is excluded from your repository. No external integrations, hosted services, Git repository, or GitHub remote are created automatically. Before publishing, replace the clone URL above.
uv sync --locked
uv run pytest
uv run ruff check .
uv run python scripts/smoke_test.py --expect-emptyuv run mcp-starter starts the stdio server and waits for protocol input; it does
not open a web page. Use the smoke test or a connected client to interact with it.
Press Ctrl+C to stop a manually started server.
MIT licensed. See LICENSE.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
MCP server for progressive tool usage at any scale (see https://klavis.ai)
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
Create guides as MCP servers to instruct coding agents to use your software (library, API, etc).
