Adios

Adios MCP client catalog

Adios in your AI client.

Choose a documented connection for Adios workspaces, files, commands, previews, logs, reviews, and approval-gated deployments. Each card opens a complete setup guide.

Choose your clientExplore MCP functions
Hosted
No server deployment
OAuth
User and team scoped
Controlled
Approval-gated changes

MCP clients

Clients.

Open a client to see its requirements, exact install steps, capabilities, example workflow, and setup FAQ.

Command line

Codex CLI

Connect Codex directly to the hosted Adios endpoint for source-backed development, previews, logs, and approved deployments.

View setup

Web and desktop

ChatGPT

Install one Adios plugin with the hosted MCP connection plus guided build, deploy, operate, and debug workflows.

View setup

Web and desktop

Claude

Add Adios as a custom connector in Claude or Claude Desktop, then build, preview, debug, and deploy from a conversation.

View setup

Command line

Claude Code

Connect Claude Code to Adios from the terminal and use hosted workspace, preview, log, and deployment tools beside your repository.

View setup

Code editor

VS Code

Use VS Code's built-in MCP support for Adios tools today. The separate Adios extension adds a sidebar for workspace sync, previews, and deployments.

View setup

Apple IDE

Xcode

Use Adios from Xcode's coding assistant by adding the hosted MCP server to its Codex, Claude, or Gemini agent environment.

View setup

Code editor

Cursor

Add Adios to Cursor's MCP tools and work with hosted projects, previews, builds, logs, and approved deployments from Agent.

View setup

Command line

Grok

Connect Grok CLI to the hosted Adios endpoint for workspace source, builds, previews, logs, and approved deployments.

View setup

Agentic IDE

Google Antigravity

Add Adios to Antigravity's shared MCP configuration and use the same tools from its app, IDE, or CLI.

View setup

Command line

GitHub Copilot CLI

Add Adios to Copilot CLI and use hosted development, preview, log, and deployment tools from the terminal.

View setup

Team workspace

Slack

Use Adios from Slackbot with the official Adios app when it is approved, or connect a Slack app your workspace owns today.

View setup

Command line

OpenCode

Add Adios as an OpenCode remote server and use hosted workspaces, builds, previews, logs, and approved deployments from the TUI.

View setup

Editor companion

Sublime Text

Use the Adios Sublime Text extension for workspace actions and an MCP-capable companion for conversational Adios tools in the same project.

View setup

Compatibility bridge

stdio MCP clients

Use the public npm bridge when your MCP client can launch a local command but cannot connect to remote HTTP directly.

View setup

How it works

How it works.

Adios MCP does not hand an agent broad cloud credentials. It exposes a defined platform workflow with identity, source, runtime evidence, and approvals attached.

  1. 01

    Choose a client

    Open your client's guide and add the hosted HTTP endpoint, plugin, or local stdio bridge it uses.

  2. 02

    Authorize

    OAuth establishes the current user and team. You do not paste a long-lived platform token into a prompt or project file.

  3. 03

    Work with source

    The client can inspect and edit workspace files, run commands, build the project, open a preview, and read the resulting logs.

  4. 04

    Approve changes

    Deployment, runtime stops, and file deletion remain confirmation-sensitive. The agent must pause before it crosses those boundaries.

Available functions

Functions.

The documented MCP surface covers 34 functions across identity, source, planning, execution, review, and deployment. The live discovery endpoint remains the source of truth for tool schemas.

34
documented functions in 6 capability groups
Open live tool discovery

Discover and authenticate

Learn what the server can do and confirm the user and team behind the current OAuth session.

2 functions
adios_capabilities

Describe the available Adios capabilities and tool groups.

auth_me

Return the current principal and team context.

Plan and track

Keep the plan, progress, and important run events attached to the coding task instead of losing them between sessions.

4 functions
get_agent_state

Read the session transcript, runs, plan steps, and events.

save_agent_plan

Persist the plan for the current coding task.

update_agent_plan_step

Mark a plan step passed, failed, blocked, or skipped.

append_agent_event

Record progress, tool, test, browser, approval, or deploy events.

Manage workspaces

Create or open durable projects where the AI client can inspect source, make changes, and prepare a running preview.

4 functions
list_workspaces

List workspaces available to the current team.

get_workspace

Read one workspace and its current state.

create_workspace

Create a workspace or a source-backed project shell.

prepare_workspace_preview

Write files, generate adios.yaml when needed, build, start, and wait for a preview URL.

Edit source

Read and change project source while keeping the deployment contract explicit and destructive file operations approval-sensitive.

8 functions
list_workspace_files

List files in a workspace.

read_workspace_file

Read one workspace file.

write_workspace_file

Write or replace one workspace file.

write_workspace_files

Write multiple workspace files together.

write_workspace_adios_yaml

Create or replace the deployment manifest.

move_workspace_file

Move or rename a file.

delete_workspace_file

Delete a file after explicit approval.

check_workspace_adios_yaml

Check manifest security and risky command patterns before execution.

Run and debug

Run the same checks a developer would use, follow long-running command state, and diagnose the evidence from a failed build or preview.

12 functions
build_workspace

Build an artifact from the workspace contents.

build_workspace_dev

Queue the canonical workspace build command.

lint_workspace

Queue the canonical lint command.

start_workspace_run

Start a preview runtime.

stop_workspace_run

Stop a preview runtime after approval.

restart_workspace_run

Restart the current preview runtime.

run_workspace_command

Queue an allowed workspace command.

get_workspace_command_status

Read command state by command ID.

get_workspace_command_logs

Read logs for a queued command.

get_workspace_run_status

Read the current preview runtime state.

get_workspace_logs

Read recent build or runtime logs.

get_workspace_git_status

Inspect current Git changes and source state.

Review and deploy

Move a verified workspace into production through an explicit approval boundary, then inspect the live workload evidence.

4 functions
security_review_workspace

Collect workspace context for a focused security review.

deploy_workspace

Deploy the current workspace after explicit approval.

get_workload_logs

Read recent logs for a deployed workload.

deploy_workload

Deploy an existing build after explicit approval.

Complete workflows

Workflows.

Good MCP work is more than a successful connection. These prompts show the source, runtime evidence, and approval boundaries a complete run should cross.

EXAMPLE 01

Build and preview

“Build me a Next.js landing page and give me a working preview URL.”

Expected tool path

create_workspacelist_workspace_fileswrite_workspace_adios_yamlbuild_workspace_devstart_workspace_run
EXAMPLE 02

Fix a failed preview

“The preview is crashing after my last change. Find out why, fix it, and send me the healthy URL.”

Expected tool path

get_workspace_command_logsread_workspace_filewrite_workspace_filerestart_workspace_runget_workspace_run_status
EXAMPLE 03

Review and deploy

“Get this ready to ship. Run the checks, tell me if anything looks risky, then wait for me before deploying.”

Expected tool path

check_workspace_adios_yamllint_workspacesecurity_review_workspacedeploy_workspaceget_workload_logs

Security boundary

Security.

Authentication, tenant context, and explicit approvals remain part of every session instead of being delegated to prompt text.

01

OAuth credentials

The client completes Adios authorization in the browser. Static account credentials do not belong in MCP configuration or source code.

02

Scoped access

Tool calls run in the authorized user and team context, then narrow further to the selected workspace or workload.

03

Explicit approval

Deployments, runtime stops, workload changes, and file deletion remain sensitive operations that require confirmation.

Public connection reference

Endpoints.

The hosted service is the same platform boundary used by the Adios app. The npm command is only a compatibility bridge to this remote endpoint.

Remote HTTP
https://api.adios.dev/v1/mcp
SSE fallback
https://api.adios.dev/v1/mcp/sse
Connection metadata
https://api.adios.dev/v1/mcp/config
Tool discovery
https://api.adios.dev/v1/mcp/tools
View public packageRead security model

Client requests

Request a client.

Tell us which client and workflow you need next. We test the full connection, from OAuth through preview and deployment approval.

Request a client

Questions

FAQ.

Which MCP clients does Adios support?

Adios supports Claude, Claude Code, ChatGPT, Codex CLI, VS Code, Xcode, Cursor, Grok, Google Antigravity, GitHub Copilot CLI, Slack, OpenCode, Sublime Text, and clients that use the stdio bridge. Each has its own setup guide and FAQ.

What MCP transport does Adios use?

The preferred public transport is Streamable HTTP at https://api.adios.dev/v1/mcp. Adios also publishes an SSE fallback and an npm-based stdio bridge for clients that launch a local command.

How is an Adios MCP session authenticated?

Adios uses OAuth. The session is scoped to the authorized user and team, and clients should complete the OAuth flow rather than storing a static platform token.

Can an MCP client deploy to production?

Yes, but deployment and other sensitive operations remain approval-gated. The client should stop, show what it intends to change, and wait for explicit confirmation before calling those tools.

Is this the same as hosting my own MCP server?

No. This page explains how AI clients use the hosted Adios platform through MCP. If you are building an MCP server of your own, use the Adios MCP server deployment guide.

Ready to connect

Start building.

Start with an Adios account, choose a client, and keep source, runtime evidence, and deployment approval together.

Create an Adios accountDeploy your own MCP server