# Ample Computer MCP MCP Server

> **Ample Computer MCP MCP Server** is a hosted, multitenant Model Context Protocol (MCP) server run by **MewCP** (https://mewcp.com), giving AI agents managed access to Ample Computer MCP.
>
> MewCP takes care of all MCP infrastructure for you — credential storage, OAuth flows,
> token refresh, and production-grade auto-scaling — so your AI agents can connect to
> third-party services and run freely without you managing any MCP server yourself.
>
> Server page:  https://mewcp.com/mcp/ample-computer-mcp
> MewCP docs:   https://docs.mewcp.com
> All servers:  https://mewcp.com/servers (JSON: https://mewcp.com/api/servers)
> About MewCP:  https://mewcp.com/llms.txt

---

## About

Deploy and manage web applications, APIs, and static sites directly from an MCP server. Ample Computer supports managed PostgreSQL, MySQL, Redis, and MongoDB databases, object storage, isolated builds, live HTTPS URLs, server provisioning, command execution, and build/runtime log monitoring.

---

## Details

- Server ID: `ample-computer-mcp`
- Version: 0.1.46
- Tools: 52
- Authentication: OAuth, managed by MewCP
- Transport: http

---

## Access

The gateway URL below serves your **entire MewCP toolset**, not this server on its
own. Pasting a config snippet is not enough — Ample Computer MCP has to be in the toolset
first. In order:

1. Add Ample Computer MCP to your toolset at https://mewcp.com/mcp/ample-computer-mcp
2. Connect your Ample Computer MCP account (OAuth); MewCP stores the credential and attaches it to each call
3. Add the gateway URL to your client (see Connect below). It signs in with OAuth
   the first time it connects, so there is no key to copy.

Once connected, an agent does **not** see this server's tools as top-level tools.
It sees four meta-tools and reaches everything through them:

- `search(query)` — find tools by keyword across the toolset
- `get_schema(tools)` — full description and arguments for the tools you picked
- `manage_connections(requests?)` — connection status and account aliases, plus
  links the user opens to add an app or connect an account
- `call_tool(app_maskedId, tool_name, args, alias?)` — execute

If Ample Computer MCP isn't in the toolset or connected yet, `manage_connections` with
app_maskedId `ample-computer-mcp` returns a link that adds it and connects an account.

So the list below is what `search` can return for this server, not a set of
callable tool names on their own.

---

## Tools (52)

Descriptions are truncated to 160 characters; call `get_schema`
for the full text and the argument schema. Where a tool is annotated, its type
is shown — treat `destructive` as irreversible.

- `ample_app_delete` _(destructive)_ — 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…
- `ample_app_get` _(read)_ — Read an app's deployment status
- `ample_app_list` _(read)_ — List deployed apps, including static sites without a server
- `ample_app_rename` _(destructive)_ — Rename an app: --title is what the person sees, --link gives it <link>.ample.run (its last few links keep working)
- `ample_bucket_create` _(write)_ — Create an object-storage bucket (returns S3 credentials)
- `ample_bucket_credentials` _(read)_ — Show the bucket's S3 credentials and endpoint
- `ample_bucket_delete` _(destructive)_ — Delete a bucket and all objects in it
- `ample_bucket_get` _(read)_ — Get bucket details (including live usage and over_quota)
- `ample_bucket_list` _(read)_ — List buckets
- `ample_bucket_publish` _(destructive)_ — Serve the bucket's objects publicly (the response has public_url)
- `ample_bucket_put` _(destructive)_ — Write one object: text, base64 data or a public https URL Ample downloads. For a file you or the person has, call ample_upload_create with bucket and path
- `ample_database_create` _(write)_ — Create a managed database. Bind it to an app with `ample deploy --database DATABASE_URL=<name>`, which injects its connection string. An app that needs a…
- `ample_database_delete` _(destructive)_ — Delete a managed database and its data. Refused while a deployment binds it
- `ample_database_get` _(read)_ — Get database details
- `ample_database_list` _(read)_ — List managed databases
- `ample_deploy` _(destructive)_ — 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 = needs…
- `ample_email_disable` _(destructive)_ — Disable new sends and immediately revoke the app's email credential
- `ample_email_enable` _(write)_ — Enable email and return its status. No email is sent. If can_send is false, tell the person next_action before building. Deploy --force afterward to inject…
- `ample_email_get` _(read)_ — Inspect one email's status and delivery events; bodies are available only for tests
- `ample_email_preview` _(write)_ — Capture rendered HTML/text and get a private 15-minute desktop/mobile preview link. Sends nothing. Links may contain login codes: do not share publicly
- `ample_email_send` _(destructive)_ — Send a real email only when the person requests it; use preview or --test otherwise. Templates are rendered in the app. Accepted is not proof of inbox placement
- `ample_email_status` _(read)_ — Whether the app can send now (can_send, blocked_by, next_action), credential binding and the monthly allowance
- `ample_execution_get` _(read)_ — Wait up to 45 seconds for the result of a call that answered status running; answers running again while it works. Never replays it.
- `ample_job_create` _(destructive)_ — 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,…
- `ample_job_get` _(read)_ — Show a job: schedule, next run, limits and its last few runs
- `ample_job_list` _(read)_ — List scheduled jobs and when each runs next
- `ample_job_run` _(destructive)_ — 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…
- `ample_job_runs` _(read)_ — Show a job's recent runs, newest first
- `ample_logs` _(read)_ — Tail build/runtime logs for a deployment
- `ample_operation` _(read)_ — Read an existing operation without starting another deployment
- `ample_plan` _(destructive)_ — Analyze the repo and plan its infrastructure before deploying Detects every deployable service (monorepos included), proposes the topology (servers, databases,…
- `ample_server_create` _(write)_ — Create a new server
- `ample_server_destroy` _(destructive)_ — Destroy a server
- `ample_server_exec` _(destructive)_ — Execute a command on a server
- `ample_server_keep_awake` _(destructive)_ — Keep a running server from being treated as idle for a while, e.g. during a series of commands Without --for or --release it shows what holds the server. Code…
- `ample_service_delete` _(destructive)_ — Stop a service and remove it (its directory on the server is kept)
- `ample_service_restart` _(destructive)_ — Restart a service, for example after updating its files
- `ample_service_start` _(destructive)_ — 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…
- `ample_service_status` _(read)_ — Show whether a service is running and how often it restarted
- `ample_upload_create` _(write)_ — Link taking one file (or, with --archive, a project folder's tar.gz) into a workspace or bucket. Give the person page_url to drop it there, or PUT to…
- `ample_upload_get` _(read)_ — An upload's arrival and deploy
- `ample_workspace_create` _(write)_ — Create an account-owned source workspace (expires after seven inactive days). With --from-app it holds that live app's current source, and deploying it updates…
- `ample_workspace_import` _(destructive)_ — Import a public HTTPS Git repository into an empty workspace
- `ample_workspace_upload` _(destructive)_ — Replace workspace source with a bounded tar.gz archive (preserve ample.toml and .ample when editing)
- `ample_workspace_write` _(destructive)_ — Write a workspace file from text, base64 data, or a public https URL Ample downloads (an image, a file the person shared); --deploy then deploys the workspace
- `ample_file_put` _(destructive)_ — Put one file into a live app (app: its name, URL or deployment id; it redeploys with the file), a workspace (workspace_id), or a bucket (bucket). file is the…
- `ample_ui_open` _(read)_ — Show the person their Ample apps, one app (deployment_id), an ample_deploy's progress (execution_id) or, after a plan limit, the upgrade. Read-only: never…
- `ample_ui_refresh` _(read)_ — Panel only: reread the apps, the selected app and a followed deploy.
- `ample_ui_identity` _(read)_ — Panel only: the signed-in account.
- `ample_ui_claim` _(write)_ — Panel only: a link that adds an email to a temporary account.
- `ample_ui_logs` _(read)_ — Panel only: recent build or runtime logs of an app.
- `ample_ui_traffic` _(read)_ — Panel only: requests to an app over the last 24 hours.

---

## Connect

- URL: https://gateway.mewcp.com/personal/mcp
- Transport: Streamable HTTP (remote). Nothing to install.
- Sign-in: OAuth. On first connect the client opens a browser window to sign in
  to MewCP and approve access. No API key.
- Headless clients (SDKs, servers without a browser) send an API key instead:
  `Authorization: Bearer <API_KEY>`, key from https://mewcp.com/dashboard/api-keys

Agents setting themselves up: follow https://mewcp.com/SKILL.md

Step-by-step guide per client:

- Claude Desktop: https://mewcp.com/mcp/ample-computer-mcp/connect/claude
- ChatGPT: https://mewcp.com/mcp/ample-computer-mcp/connect/chatgpt
- Grok: https://mewcp.com/mcp/ample-computer-mcp/connect/grok
- DeepSeek Harness: https://mewcp.com/mcp/ample-computer-mcp/connect/dsh
- Mistral Vibe: https://mewcp.com/mcp/ample-computer-mcp/connect/mistral-vibe
- VS Code: https://mewcp.com/mcp/ample-computer-mcp/connect/vscode
- Cursor: https://mewcp.com/mcp/ample-computer-mcp/connect/cursor
- Codex: https://mewcp.com/mcp/ample-computer-mcp/connect/codex
- Claude Code: https://mewcp.com/mcp/ample-computer-mcp/connect/claude-code
- OpenCode: https://mewcp.com/mcp/ample-computer-mcp/connect/opencode
- OpenClaw: https://mewcp.com/mcp/ample-computer-mcp/connect/openclaw
- Antigravity: https://mewcp.com/mcp/ample-computer-mcp/connect/antigravity
- Hermes: https://mewcp.com/mcp/ample-computer-mcp/connect/hermes
- Kimi Code: https://mewcp.com/mcp/ample-computer-mcp/connect/kimi-code
- Grok Build: https://mewcp.com/mcp/ample-computer-mcp/connect/grok-build
- Devin Desktop: https://mewcp.com/mcp/ample-computer-mcp/connect/devin-desktop
- Zed: https://mewcp.com/mcp/ample-computer-mcp/connect/zed
- Muse Code: https://mewcp.com/mcp/ample-computer-mcp/connect/muse-code
- Cline: https://mewcp.com/mcp/ample-computer-mcp/connect/cline
- Kilo Code: https://mewcp.com/mcp/ample-computer-mcp/connect/kilo-code
- Kiro: https://mewcp.com/mcp/ample-computer-mcp/connect/kiro
- Junie: https://mewcp.com/mcp/ample-computer-mcp/connect/junie
- Amp: https://mewcp.com/mcp/ample-computer-mcp/connect/amp
- Qwen Code: https://mewcp.com/mcp/ample-computer-mcp/connect/qwen-code
- Goose: https://mewcp.com/mcp/ample-computer-mcp/connect/goose
- Python: https://mewcp.com/mcp/ample-computer-mcp/connect/python
- TypeScript: https://mewcp.com/mcp/ample-computer-mcp/connect/typescript