Ephemeral
OnlineNewRun AI agent tasks in isolated sandboxes with a cost cap, saved workflows and scoped connections.
What it can do: 19 tools
create_runStart 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 cget_runread-onlyRead 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_fiwait_for_runread-onlyWait 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_list_runsread-onlyList 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_runCancel a run that has not finished. Work already done is billed. Cancelling a finished run changes nothing.list_workflowsread-onlyList 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 shapeget_workflowread-onlyRead a saved workflow's definition: description, prompt, model, files, connections, limits and its input_schema and output_schema. Credentials are never included.list_modelsread-onlyFind 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 witlist_connectionsread-onlyThe 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_workflowCreate 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_delete_workflowPermanently 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_schedulesread-onlyList 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_scheduleread-onlyRead a schedule: timetable, time zone, input, cost cap, whether it is enabled, its next start and the outcome of its last start.create_scheduleStart 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 schedupdate_scheduleChange 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_schedulePermanently 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_scheduleread-onlyCheck a cron expression and time zone and return the next five start times (UTC), without saving anything.run_scheduleStart 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_filesread-onlyList 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.
Connect it
claude mcp add --transport http ephemeral https://app.ephemer.al/mcpSettings → Connectors → Add custom connector
URL: https://app.ephemer.al/mcp{
"mcpServers": {
"ephemeral": {
"url": "https://app.ephemer.al/mcp"
}
}
}{
"servers": {
"ephemeral": {
"type": "http",
"url": "https://app.ephemer.al/mcp"
}
}
}Questions
What does Ephemeral do?
Run AI agent tasks in isolated sandboxes with a cost cap, saved workflows and scoped connections. It exposes 19 tools to AI assistants.
What tools does Ephemeral provide?
19 tools, including create_run, get_run, wait_for_run, list_runs, cancel_run, list_workflows, get_workflow, list_models, list_connections, save_workflow, delete_workflow, list_schedules….
How do I connect Ephemeral to Claude, ChatGPT or Cursor?
Add the remote MCP endpoint https://app.ephemer.al/mcp as a custom connector or MCP server. Copy-paste setup is on this page.
Does Ephemeral require an account or API key?
No sign-in was needed to list its tools. Individual tools may still need an account or API key.
Is Ephemeral online?
As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.
Who publishes Ephemeral?
ephemer.al. The official MCP Registry verified that the publisher controls this domain before accepting the listing.
Similar in Agents & Orchestration
-
Upwork MCPOnline · sign-in requiredOfficialPopular
The official Upwork MCP server, letting AI agents connect to Upwork and act on your behalf.
-
Postman MCP ServerOnline · sign-in requiredOfficialPopular
Give your AI agents trusted access to the full Postman platform.
-
OpenWeather for agentsOnlineOfficialPopular
OpenWeather data for AI agents: list feeds, sign up, check balance, get a top-up link, fetch data.
-
Creator MCPOnline · sign-in requiredOfficialNew
Hosted motion engine for agents. Builds layers and keyframes, exports MP4, WebM or Lottie.
-
Agent economy data (counts from the Official MCP Registry)OnlineNew
MCP server counts from the official registry, new servers per day, and MCP/A2A spec changes. As is.
-
Rota NacionalOnlineOfficialNew
AI API compatible with OpenAI and Anthropic, with personal data handled before the model.