Ephemeral

MCP server · hosted · v1.0.0 · al.ephemer/ephemeral

Online · tested 58m agoNEW · 1h agoSeen in the registry 49m ago

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

What it does

Ephemeral is an MCP server, a connector that lets an AI assistant use it as a tool. It is hosted: an assistant connects to it over the internet, nothing to install.

No capability identified yet from its description.

Facts come from the Official MCP Registry, as declared by the publisher. Capabilities are matched automatically (low confidence). None of this is a test of the tool.

At a glance

Hosted (remote)YES

Local installNO

Live checkOnline · 19 tools

Version1.0.0

PriceNot in the registry

First seen26 Oct 2026

Last checked49m ago

How to connect

As declared in the Official MCP Registry · hosted endpoint tested by Electra Index 58m ago (live check)

Hosted endpoint

https://app.ephemer.al/mcp streamable-http

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

MCP settings (Claude Desktop, Cursor and other MCP clients)

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

Live check

Electra Index connected to the hosted endpoint 58m ago

ONLINE Ephemeral answered an MCP connection on 26 Oct 2026 and introduced itself as ephemeral 2026.10.26.65-13cda13 (MCP protocol 2025-06-18).

19 tools offered to AI assistants

create_run · 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)
get_run · 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
wait_for_run · 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, norma
list_runs · 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.
cancel_run · Cancel a run that has not finished. Work already done is billed. Cancelling a finished run changes nothing.
list_workflows · 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 retu
get_workflow · Read a saved workflow's definition: description, prompt, model, files, connections, limits and its input_schema and output_schema. Credentials are never included.
list_models · 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-insens
list_connections · 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.
save_workflow · 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. Connection
delete_workflow · 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.
list_schedules · 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.

Show 7 more

get_schedule · Read a schedule: timetable, time zone, input, cost cap, whether it is enabled, its next start and the outcome of its last start.
create_schedule · 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 af
update_schedule · 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.
delete_schedule · 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.
preview_schedule · Check a cron expression and time zone and return the next five start times (UTC), without saving anything.
run_schedule · 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.
list_files · 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.

What "online" means: the server answered an MCP connection at the time of the check. It is not a guarantee of security, quality or continuous uptime. How we test: we open an MCP session and ask for the tool list, as an AI assistant would. We never run a tool and never send a key. Checked every few days. Method

Is this your server? Monitoring Pro: a check every 30 minutes and an email within the hour when it stops answering. Launch offer: $39.99 once, for life.

Facts & evidence

Each fact shows where it was seen and when.

Fact	Value	Evidence	Source	Last confirmed
Hosted endpoint	https://app.ephemer.al/mcp	DECLARED	SRC-001 Official MCP Registry	49m ago
Local install (package)	no	DECLARED	SRC-001 Official MCP Registry	49m ago
Remote access (hosted)	yes	DECLARED	SRC-001 Official MCP Registry	49m ago
Website	https://ephemer.al/	DECLARED	SRC-001 Official MCP Registry	49m ago
Registry status	active	DECLARED	SRC-001 Official MCP Registry	49m ago
Version	1.0.0	DECLARED	SRC-001 Official MCP Registry	49m ago
MCP server	yes	DECLARED	SRC-001 Official MCP Registry	49m ago

Change history

NEW26 Oct 2026
first seen in the index

Is this page accurate?

Flag it and our robot re-checks the official source. Reports never change a score.

Is Ephemeral still online?

Free alerts · no account

Questions about Ephemeral

How do I connect Ephemeral?

Use the hosted endpoint https://app.ephemer.al/mcp in your assistant's MCP settings. The exact settings are in "How to connect" above, as declared in the Official MCP Registry.

What tools does Ephemeral offer?

When Electra Index connected on 26 Oct 2026, it listed 19 tools: create_run, get_run, wait_for_run, list_runs, cancel_run, list_workflows, get_workflow, list_models and more. The full list is in "Live check" above.

Is Ephemeral online?

Yes. Its hosted endpoint answered an MCP connection from Electra Index 58m ago.