DevOps

ample.computer

Manages app deployments and agent credentials, including listing, inspecting, and deleting deployed apps and releases.

1 endpoint90 known toolsFirst detected October 21, 2026Last detected October 21, 2026

ENDPOINT 1

https://api.ample.computer/mcp

No auth detected

MCP server metadata

Name: ample
Version: 0.1.36

Capabilities

extensions.io.modelcontextprotocol/oauth-client-credentialsextensions.io.modelcontextprotocol/tasksresourcestools

Server instructions

Ample tools are generated from this release's CLI. If your host linked an Ample account, you already have one: never call ample_auth_signup. Otherwise start with ample_auth_signup. A new account is deleted after 48 hours unless its person claims it: ask them for their email and call ample_auth_claim, which emails them the link. Two ways to run code. Managed: put source in a workspace, then ample_plan, resolve its questions with answers, and ample_deploy (Ample detects the stack, builds in isolation, keeps releases). Hands-on: ample_server_create with a template such as node-22 or python-3.12, ample_server_exec to fetch and build (for example git clone and npm ci; long commands are fine), then ample_service_start with the directory and start command for a supervised process with a public URL; after changing its files, ample_service_restart. Deploy is synchronous and content-addressed: call once and read the result, never poll by redeploying. Exit 2 is needs_input only when the result has status needs_input; fix the manifest or answer the questions. Read ample_logs after failures. For anything on a schedule (reminders, reports, price checks), use ample_job_create on a deployed service, then ample_job_run with wait to test it; jobs run whether or not the app has traffic. A worker service wakes and sleeps with the web services that feed it (same ample.toml project, or a shared bound database). Other background work no request waits on (a render, an import) counts as idle after a minute: run it under ample-awake inside the server, or hold the server with ample_server_keep_awake. Remote calls accept workspace_id and execution_key; reuse execution_key after disconnects to retrieve the existing execution without repeating mutations.

Known tools 90

ample_app_delete

Delete an app and its releases; preserve shared servers and declared resources Apps are addressed by deployment ID, not name: a name can be shared, an ID cannot.

Potential side effects

ample_app_get

Read an app's deployment status

Inferred read-only

ample_app_list

List deployed apps, including static sites without a server

Inferred read-only

ample_auth_agent_create

Provision an agent credential with a secret shown only once

Inferred read-only

ample_auth_agent_list

List agent credentials without exposing secrets

Inferred read-only

ample_auth_agent_revoke

Revoke a credential and all its access tokens

Inferred read-only

ample_auth_claim

Keep this account: email the person a link that makes them its owner

Potential side effects

ample_auth_signup

Inferred read-only

ample_auth_token_create

Create a new scoped token

Potential side effects

ample_auth_token_list

List all tokens

Inferred read-only

ample_auth_token_revoke

Revoke a token by ID

Inferred read-only

ample_auth_whoami

Show current identity and scopes

Inferred read-only

ample_bucket_create

Create an object-storage bucket (returns S3 credentials)

Potential side effects

ample_bucket_credentials

Show the bucket's S3 credentials and endpoint

Inferred read-only

ample_bucket_delete

Delete a bucket and all objects in it

Potential side effects

ample_bucket_get

Get bucket details (including live usage and over_quota)

Inferred read-only

ample_bucket_list

List buckets

Inferred read-only

ample_bucket_publish

Serve the bucket's objects publicly (the response has public_url)

Inferred read-only

ample_bucket_rotate_key

Rotate the bucket's S3 key (old key stops working)

Inferred read-only

ample_bucket_unpublish

Stop serving the bucket publicly

Inferred read-only

ample_budget_set

Set budget limits

Inferred read-only

ample_budget_status

Show budget status

Inferred read-only

ample_database_create

Create a managed database

Potential side effects

ample_database_delete

Delete a managed database

Potential side effects

ample_database_get

Get database details

Inferred read-only

ample_database_list

List managed databases

Inferred read-only

ample_deploy

Deploy a local app/workspace and wait until it is live This command blocks until the release is live or fails, then exits: 0 = live, 1 = failed, 2 = blocked on a required preflight action.

Potential side effects

ample_docs

Read embedded CLI documentation (compatibility alias)

Inferred read-only

ample_docs_agents

Print the agent playbook (plan → answer → deploy workflow, contracts, footguns)

Inferred read-only

ample_docs_llms

Print the llms.txt-style condensed command and manifest reference

Potential side effects

ample_docs_mcp

Print the generated MCP tool catalog or registry metadata

Inferred read-only

ample_docs_remote

Print remote MCP authentication, workspace, and recovery instructions

Inferred read-only

ample_domain_add

Add a custom domain to a deployment

Inferred read-only

ample_domain_list

List domains for a deployment

Inferred read-only

ample_domain_verify

Verify DNS for a custom domain and activate it

Inferred read-only

ample_execution_cancel

Cancel remote execution; accepted cloud mutations may already have completed

Inferred read-only

ample_execution_get

Retrieve an existing remote execution and its result without replaying it

Inferred read-only

ample_init

Plan this repo and write ample.toml, with onboarding guidance Runs `ample plan --write`, lifts legacy .ample/config.toml settings into the manifest, and prints the AGENTS.md snippet + .gitignore recommendation.

Potential side effects

ample_job_create

Run a command or an HTTP request on one of your services on a schedule The job runs inside the service's server with its environment, directory and database, whether or not the app has traffic.

Potential side effects

ample_job_delete

Delete a job and its run history

Potential side effects

ample_job_get

Show a job: schedule, next run, limits and its last few runs

Inferred read-only

ample_job_list

List scheduled jobs and when each runs next

Inferred read-only

ample_job_pause

Stop a job from running on its schedule (manual runs still work)

Inferred read-only

ample_job_resume

Resume a paused job's schedule

Inferred read-only

ample_job_run

Run a job now With --wait it is synchronous: it returns when the run finishes, exits 0 if it succeeded and 1 if it failed (the result has the output and, on failure, who should act and how).

Inferred read-only

ample_job_runs

Show a job's recent runs, newest first

Inferred read-only

ample_logs

Tail build/runtime logs for a deployment

Inferred read-only

ample_operation

Read an existing operation without starting another deployment

Inferred read-only

ample_plan

Analyze the repo and plan its infrastructure before deploying Detects every deployable service (monorepos included), proposes the topology (servers, databases, volumes, links), and lists open questions with options and safe defaults.

Inferred read-only

ample_recipe_get

Inspect one published recipe contract (prerequisites, tested configuration, limitations, evidence, binding, next actions)

Inferred read-only

ample_recipe_plan

Prepare a side-effect-free deployment plan for a recipe against a workspace or server you own Requires an account token with servers:read.

Inferred read-only

ample_recipe_search

Search the published deployment recipe catalog by task, stack and explicit constraints Public and read-only.

Inferred read-only

ample_report

Report a problem with Ample to the Ample team The last failed ample command's error is attached automatically.

Potential side effects

ample_server_cp

Copy files to/from a server (scp-style) Upload: ample server cp ./local.txt my-server:/remote.txt Download: ample server cp my-server:/remote.txt ./local.txt

Potential side effects

ample_server_create

Create a new server

Potential side effects

ample_server_destroy

Destroy a server

Potential side effects

ample_server_exec

Execute a command on a server

Potential side effects

ample_server_get

Get server details

Inferred read-only

ample_server_keep_awake

Keep a running server from being treated as idle for a while, e.g.

Inferred read-only

ample_server_list

List servers

Inferred read-only

ample_server_pause

Pause a server (snapshot to disk, stop billing)

Inferred read-only

ample_server_resize

Resize a server in place (pause, cold boot with the new vCPU/memory; short restart, data kept)

Inferred read-only

ample_server_resume

Resume a paused server

Inferred read-only

ample_service_delete

Stop a service and remove it (its directory on the server is kept)

Potential side effects

ample_service_restart

Restart a service, for example after updating its files

Inferred read-only

ample_service_start

Run a command from a directory on an existing server as a supervised service Re-running with the same arguments is a no-op; after changing files in the directory, use `ample service restart`.

Potential side effects

ample_service_status

Show whether a service is running and how often it restarted

Inferred read-only

ample_up

Reconcile the whole ample.toml topology (databases, volumes, services, domains) Where `ample deploy <service>` applies one service, `ample up` applies the entire manifest in dependency order: it ensures every `[databases.*]` and `[volumes.*]` exists, deploys each `[services.*]` (a service linking to X deploys after X), then attaches each `[domains.*]`.

Inferred read-only

ample_usage_current

Show current month's usage

Inferred read-only

ample_volume_attach

Attach a detached volume before a server first boots

Inferred read-only

ample_volume_create

Create a new volume

Potential side effects

ample_volume_delete

Delete a volume (must be detached)

Potential side effects

ample_volume_detach

Detach a volume from its server

Inferred read-only

ample_volume_get

Get volume details

Inferred read-only

ample_volume_list

List volumes

Inferred read-only

ample_workspace_create

Create an empty account-owned source workspace (expires after seven inactive days)

Potential side effects

ample_workspace_delete

Delete workspace source and metadata; deployed applications are retained

Potential side effects

ample_workspace_download

Return an authenticated archive download URL, or save it to a local file

Inferred read-only

ample_workspace_get

Read workspace metadata and resolved Git commit

Inferred read-only

ample_workspace_import

Import a public HTTPS Git repository into an empty workspace

Inferred read-only

ample_workspace_list

List source workspaces

Inferred read-only

ample_workspace_read

Read a UTF-8 or binary file inside a workspace

Inferred read-only

ample_workspace_upload

Replace workspace source with a bounded tar.gz archive (preserve ample.toml and .ample when editing)

Inferred read-only

ample_workspace_write

Write a workspace file; provide either text or base64 data

Potential side effects

ample_ui_open

Show the person their Ample apps, one app (deployment_id), or the progress of a deploy started with ample_deploy or ample_up (execution_id).

Inferred read-only

ample_ui_refresh

Panel only: reread the apps, the selected app and a followed deploy.

Inferred read-only

ample_ui_identity

Panel only: the signed-in account.

Inferred read-only

ample_ui_claim

Panel only: a link that adds an email to a temporary account.

Potential side effects

ample_ui_logs

Panel only: recent build or runtime logs of an app.

Inferred read-only

ample_ui_traffic

Panel only: requests to an app over the last 24 hours.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.ample]
url = "https://api.ample.computer/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "ample": {
      "type": "http",
      "url": "https://api.ample.computer/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: ample
Remote MCP URL: https://api.ample.computer/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "ample": {
      "url": "https://api.ample.computer/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "ample": {
      "type": "http",
      "url": "https://api.ample.computer/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "ample",
  "transport": "streamable-http",
  "url": "https://api.ample.computer/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.