Metadata-Version: 2.4
Name: nxtlinq-mcp-proxy
Version: 0.1.0
Summary: Configure and deploy an isolated HTTP MCP behind nxtlinq authorization
Requires-Python: >=3.11
Description-Content-Type: text/markdown
Requires-Dist: httpx<1,>=0.27
Requires-Dist: python-dotenv<2,>=1
Provides-Extra: desktop
Requires-Dist: nxtid-sdk[desktop]==0.3.6; extra == "desktop"
Provides-Extra: dev
Requires-Dist: pytest>=8; extra == "dev"
Requires-Dist: pytest-asyncio>=0.23; extra == "dev"
Requires-Dist: build>=1.2; extra == "dev"
Provides-Extra: docs
Requires-Dist: mkdocs<2,>=1.6; extra == "docs"
Requires-Dist: mkdocs-material<10,>=9; extra == "docs"
Provides-Extra: release
Requires-Dist: build<2,>=1.2; extra == "release"
Requires-Dist: twine<7,>=6; extra == "release"

# nxtlinq MCP Proxy

Package an existing MCP server, deploy it on a private Docker network, and
check nxtlinq tool permissions before forwarding calls. The original MCP
implements the tools. Desktop Setup manages identity and tool permissions.

## Requirements

- uv on macOS or Linux; the guide uses uv to provide Python 3.11.
- Docker with Compose and Buildx, running on the deployment host.
- A dedicated nxtlinq thirdParty service API Key and Secret.
- An Agent supporting Streamable HTTP MCP with an Authorization header.
  Automatic Codex configuration is an optional integration.

## Install

Confirm `uv --version` works and that `docker info`,
`docker compose version`, and `docker buildx version` succeed. The source
distribution includes step-by-step environment installation guides at
`docs/en/environment.md` and `docs/zh-TW/environment.md`; skip components
that already pass these checks.

In a new working directory, create a Python virtual environment with uv, then
install the Proxy and its dependencies. uv downloads Python 3.11 if needed. For an
existing installation, activate its environment and skip environment creation.

```sh
mkdir nxtlinq-tools
cd nxtlinq-tools
uv venv --python 3.11 .venv
source .venv/bin/activate
```

Install from PyPI:

```sh
uv pip install 'nxtlinq-mcp-proxy[desktop]==0.1.0'
```

uv downloads the Proxy and its dependencies from PyPI. `[desktop]` includes Setup dependencies.

Download: [Proxy 0.1.0](https://pypi.org/project/nxtlinq-mcp-proxy/0.1.0/#files).

## Deploy

```sh
nxtlinq-mcp pack my-mcp-bundle
nxtlinq-mcp init my-tools --bundle my-mcp-bundle
cd my-tools
nxtlinq-mcp setup
```

Choose the packaging method for your MCP. During initialization, select `other`
for manual MCP configuration or `codex` for the optional automatic integration.
Enter the service environment and credentials when prompted, review the discovered
tools, and confirm registration. Complete Setup and enable the tools you need,
then connect your Agent using the chosen connection option.

Use a pinned npm/Python package, a custom Dockerfile, or an existing HTTP image.
Optional recipes demonstrate Filesystem, Memory, and GitHub PAT/OAuth.
Each deployment supports up to 16 MCP servers and one user's Setup session. Configure host folders and permitted API destinations for each MCP.
The proxy governs calls through its MCP endpoint; independently accessible
files, APIs, or application endpoints require their own access controls.

English and Traditional Chinese guides are included in the source distribution
under `docs/en` and `docs/zh-TW`.
