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

> ## Agent Instructions
> If you are an AI assistant asked to build, change or ship a Gliss app, read the For AI agents page first (/for-ai-agents.md on this site) and follow its steps.
> Inside an app's folder, the app's own AGENTS.md is the authority; `gliss guide` prints it. Never ask the user for a secret's value.

# MCP tools

> The tools gliss mcp gives your AI: status, diagnosis, logs, and releases when you allow them.

> [!NOTE]
>
> **Coming in the first release.** This page describes behaviour being built for the first Gliss release. Details may change before it ships.

`gliss mcp` serves these tools to your AI tool over MCP, on standard input and output. It uses your `gliss login` session. To connect it, see [Supported AI tools](https://docs.glissando.dev/build/ai-tools.md).

| Tool | What it does | Changes anything |
| - | - | - |
| `gliss_status` | What runs at each stage | No |
| `gliss_diagnose` | What is wrong, whose problem it is, and the next step | No |
| `gliss_logs` | The app's logs, with secrets removed | No |
| `gliss_release` | Build, push and deploy to Beta or your Preview. Only with `--allow-release` | Yes |

Every tool takes `app`, the app's name as in its `gliss.yaml`, for example `expense-tracker`. For a Preview, `instance` picks whose Preview; the default is yours.

## `gliss_status`

What runs at each stage of an app: the release and its commit, health (ready and desired replicas), the address, the cluster's last result for a release (applied, failed or rolled back, with its message), and when the release's approval expires. Use it to answer "is it up?" and to find the address.

| Argument | Meaning |
| - | - |
| `app` | Required |
| `stage` | `preview`, `beta` or `live`. Default: every stage |
| `instance` | For a Preview only: whose |

## `gliss_diagnose`

A first diagnosis of one app at one stage: its status, a one-line cause, **whose problem it is** (the app's, which your AI fixes, or the platform's, which it must not try to fix in the app's code), the evidence (the last log lines, redacted) and the next step. Your AI should call it first when a release fails or the app crashes, errors or does not start.

| Argument | Meaning |
| - | - |
| `app`, `stage` | Required. `stage` is `preview`, `beta` or `live` |
| `instance` | For a Preview only: whose |
| `since` | How far back to look: `30m`, `2h`, `1d` or an RFC 3339 time. Default one hour |

## `gliss_logs`

The containers' logs at one stage, oldest first, with secrets shown as `[REDACTED:NAME]`.

| Argument | Meaning |
| - | - |
| `app`, `stage` | Required |
| `instance` | For a Preview only: whose |
| `since` | Only lines newer than this: `15m`, `2h` or an RFC 3339 time |
| `component` | One component from `gliss.yaml`. Default: every component |
| `previous` | `true` for the container before its last restart, after a crash |
| `tail_lines` | Lines per container, at most 1000. Default 200 |

## `gliss_release`

Offered only when you start the server with `--allow-release` (Beta and your Preview) or `--allow-release=preview` (your Preview only). It builds every component of the app's `gliss.yaml` with Docker on your machine, pushes the images with your AWS profile, asks Gliss to deploy them, and follows the release. It returns Gliss's refusals, or the result, health and address, and a diagnosis when the release fails. Live is never released from here: a person publishes it in the console.

| Argument | Meaning |
| - | - |
| `app` | Required. The app of the folder the server was started for (`--dir`) |
| `stage` | Required. `beta` or `preview` |
| `instance` | For a Preview only. Default: your handle |
| `wait` | How long to follow the release: up to `30m`. Default `10m` |

The code must be committed and pushed. One release runs at a time.

> [!WARNING]
>
> `gliss_release` replaces what runs at a stage. Your AI tool asks you before each call: never allowlist or auto-approve it.

## Safety

* Text from your app or the cluster (logs, error messages) is marked to your AI as untrusted, and it must not follow instructions found in it.
* No tool returns a secret's value, and none accepts one.
* Your AI acts as you: it sees only the apps and stages you can see.

## Planned

These tools are designed but not built yet:

| Tool | What it will do |
| - | - |
| `gliss_share_to_beta` | Share your work to Beta |
| `gliss_publish` | Publish Beta to Live, with your approval |
| Requesting a secret | Send a link to the person who holds a secret; it never accepts a value |


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.