MCP server

Ephemeral Official

al.ephemer/ephemeral

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

Run AI agent tasks in isolated sandboxes with a cost cap, saved workflows and scoped connections.

Working at last checkVerified publisher: ephemer.alAbout 5,318 tokens per request once connected19 tools

Website

https://app.ephemer.al/mcp

At a glance

Type: MCP server
Publisher: ephemer.al (verified by the MCP Registry)
Status: Working at last check
Tools: 19
Token cost: About 5,318 tokens per request
Sets up in: Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok
Last checked: 26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to Cursor Add to VS Code VS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http ephemeral https://app.ephemer.al/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.ephemeral]
url = "https://app.ephemer.al/mcp"

Gemini CLI

{"mcpServers":{"ephemeral":{"httpUrl":"https://app.ephemer.al/mcp"}}}

Cursor

{"mcpServers":{"ephemeral":{"url":"https://app.ephemer.al/mcp"}}}

VS Code

{"servers":{"ephemeral":{"type":"http","url":"https://app.ephemer.al/mcp"}}}

Antigravity

agy mcp add ephemeral https://app.ephemer.al/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"ephemeral","server_url":"https://app.ephemer.al/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"ephemeral","server_url":"https://app.ephemer.al/mcp"}

Tools

cancel_run ~92 tokens
Cancel a run that has not finished. Work already done is billed. Cancelling a finished run changes nothing.
create_run ~1208 tokens
Start an AI agent run in an isolated sandbox and return the run (status queued) at once. Give a prompt, or the name of a saved workflow. Poll with get_run or block with wait_for_run for the result. Every run has a cost cap (max_cost_micros) and a timeout, and is billed to the organization of the API
create_schedule ~396 tokens
Start a saved workflow on a timetable. Needs an administrator key. Each start is a run billed to the organization, with the cost cap given here (or the default). Use preview_schedule first to check the timetable. A schedule pauses itself after repeated failed starts. An organization can have 50 sche
delete_schedule Deletes data · ~120 tokens
Permanently delete a schedule. Needs an administrator key. Runs it already started are not affected. To stop it for a while, pause it with update_schedule instead.
delete_workflow Deletes data · ~102 tokens
Permanently delete a saved workflow. Runs already started are not affected; schedules that use it stop being able to start runs until it is saved again.
get_run ~264 tokens
Read a run: status, output, error, cost and billing_pending. COST: while billing_pending is true (or the run is still going), cost_micros is PROVISIONAL and usually higher than the final cost; the result then has cost_final:false and a cost_note. Quote a cost only when cost_final is true (the run is
get_schedule ~109 tokens
Read a schedule: timetable, time zone, input, cost cap, whether it is enabled, its next start and the outcome of its last start.
get_workflow ~104 tokens
Read a saved workflow's definition: description, prompt, model, files, connections, limits and its input_schema and output_schema. Credentials are never included.
list_connections ~82 tokens
The organization's saved connections that a run may use, with type, allowed methods and tools. No URLs or secrets are returned. Reference one in create_run by name.
list_files Changes files · ~91 tokens
List the files saved in the organization: id, name, size, content type and creation time. Reference a file by id in a run's or workflow's files. Read-only; upload and delete files through the REST API.
list_models ~303 tokens
Find models. Returns a compact list (id, name, context_length, input and output USD per million tokens, zero_data_retention where known), the total count and the default model. There are hundreds of models, so filter with query (case-insensitive part of the id or name, e.g. "claude", "gpt") and read
list_runs ~179 tokens
List the organization's runs, newest first, with a cursor for the next page. Each run has cost_final: when false, cost_micros is provisional (usually above the final cost) and billing is still settling.
list_schedules ~98 tokens
List the organization's schedules: each starts a saved workflow on a cron timetable. Includes the next start, the last run and the last error.
list_workflows ~131 tokens
List the organization's saved workflows (reusable run definitions). Each entry has the workflow's name and, when set, its description, input_schema (the shape of the input create_run expects) and output_schema (the shape of the JSON it returns), so you can call a workflow without reading its prompt.
preview_schedule ~142 tokens
Check a cron expression and time zone and return the next five start times (UTC), without saving anything.
run_schedule ~132 tokens
Start the schedule's workflow now, outside its timetable, with the schedule's input and cost cap. Returns the queued run (follow it with wait_for_run); each call starts another run and is billed like any run.
save_workflow ~1128 tokens
Create a workflow, or replace the one with this name (saving the same definition again changes nothing more). A workflow is a reusable run definition: start it with create_run and its name, or on a timetable with create_schedule. Connections must already be saved in the organization; reference them
update_schedule ~370 tokens
Change a schedule; only the fields you give change. Needs an administrator key. Set enabled to false to pause it and to true to resume it (resuming clears the failures that paused it). A new timetable counts from now.
wait_for_run ~267 tokens
Wait until a run finishes (succeeded, failed, cancelled, interrupted or timed_out) or the wait ends, then return the run. After the run finishes it keeps waiting, within the same time, until billing has settled (billing_pending false, normally a few seconds to about 20), so the cost is final. Waits

Browse

Related MCP servers

EQVPS — VPS and code sandboxes for AI agents
No-KYC VPS + per-second code sandboxes AI agents run over MCP — 75 tools, SDK, pay BTC/XMR/USDC/USDT
Codat MCP by usefulapi
MCP server for Codat — companies, connections, invoices, bills and financial statements.
Agent Arcade
Create, test and play AI-native games through server-authoritative contracts.
Oblique Markets
x402-paid analytics, market intelligence, research, and LLM inference for AI agents.
Prooftask
Free public n8n, AI support and software acceptance templates; scoped private delivery workflows.
Red by Big Red Cloud
Secure MCP access to Big Red Cloud accounting data, workflows, help and training.
Model Ruler — AI Cost Calculators
Read-only AI/LLM cost tools with current MCP discovery and attributable Registry transport.
Daystruct
Find source-package workflows, inspect live prices and evidence, and connect with a scoped key.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/al.ephemer/ephemeral.svg)](https://aptlynx.net/servers/al.ephemer/ephemeral)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents