# Ephemeral

- Registry name: `al.ephemer/ephemeral` · version 1.0.0
- Categories (automatic, keyword rules): Payments & accounting, Finance & markets
- Authentication at last check: No auth
- Declared risk: Has destructive tools (destructiveHint)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=al.ephemer%2Fephemeral
- Server page: https://mcpstation.net/s/al.ephemer--ephemeral.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

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

## Tools (as reported by the server, not verified)

- `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 \(max\_cost\_micros\) and a timeout, and is billed to the organization of the API
- `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\_note. Quote a cost only when cost\_final is true \(the run is
- `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 \(billing\_pending false, normally a few seconds to about 20\), so the cost is final. Waits
- `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 \(the shape of the JSON it returns\), so you can call a workflow without reading its prompt.
- `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 \(case-insensitive part of the id or name, e.g. "claude", "gpt"\) and read
- `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. Connections must already be saved in the organization; reference them
- `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.
- `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 after repeated failed starts. An organization can have 50 sche
- `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.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html