> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pidgeon.health/llms.txt
> Use this file to discover all available pages before exploring further.

# Public packages quickstart

> Install the Pidgeon public beta packages and run a small local healthcare-data workflow.

Pidgeon's public beta gives engineers three ways into the same local-first
workflow: the .NET engine packages, the `pidgeon` command-line tool, and a thin
Model Context Protocol adapter. Start with the CLI unless you are embedding
the engine into an application or connecting an MCP client.

<Warning>
  These are beta packages. Pin the exact versions below, review the known limits,
  and test the workflow before relying on it in a controlled environment. The
  desktop products are distributed separately from these community packages.
</Warning>

## Choose an entry point

| Need                                             | Package                      | Current beta   |
| ------------------------------------------------ | ---------------------------- | -------------- |
| Use Pidgeon from a terminal or CI job            | `Pidgeon.CLI`                | `0.1.0-beta.2` |
| Embed the engine in a .NET application           | `Pidgeon.Core`               | `0.1.0-beta.1` |
| Add the provenance-cleared offline baseline data | `Pidgeon.Data.Baseline`      | `0.1.0-beta.1` |
| Connect an MCP client to the community CLI       | `@pidgeonhealth/pidgeon-mcp` | `0.1.0-beta.1` |

## Run the CLI locally

Install the .NET tool:

```bash theme={null}
dotnet tool install --global Pidgeon.CLI --version 0.1.0-beta.2
pidgeon --version
```

Generate a deterministic synthetic HL7 v2 message, validate it, and preserve
the output for review:

```bash theme={null}
pidgeon generate hl7 "ADT^A01" --seed 42 --output sample.hl7
pidgeon validate sample.hl7
```

The seed makes the generated example repeatable. The validation result is
evidence about that input and the supported rules, not a certification or a
guarantee about a production interface.

## Embed Core and Baseline

Add both packages when an application needs the public engine and its admitted
offline resource set:

```bash theme={null}
dotnet add package Pidgeon.Core --version 0.1.0-beta.1
dotnet add package Pidgeon.Data.Baseline --version 0.1.0-beta.1
```

Register the baseline package explicitly with `AddPidgeonBaselineData()` in
your dependency-injection composition. Core does not silently reach into the
legacy data tree, and an absent required data package degrades with a typed
result rather than pretending the resource exists.

## Connect an MCP client

Use the governed adapter package:

```bash theme={null}
npx -y @pidgeonhealth/pidgeon-mcp@0.1.0-beta.1
```

<Warning>
  Do not substitute `@pidgeonhealth/mcp`. That name is a contained legacy
  package and is not part of the governed public beta release train.
</Warning>

The adapter shells out to the local CLI in CLI mode. It does not turn the MCP
client into an autonomous healthcare operator: the human remains responsible
for scope, review, and use of the resulting evidence.

## Verify before expanding

1. Pin the package versions in source control.
2. Run a synthetic example without patient data.
3. Review the generated output and validation result.
4. Record the command, version, seed, and result when repeatability matters.
5. Report a reproducible issue through the relevant
   [Pidgeon Health repository](https://github.com/PidgeonHealth).

Next, read the [test-data field guide](/guides/healthcare-interface-test-data-field-guide)
or the [human-and-agent workflow map](/guides/local-first-human-agent-workflow).