Ephemeral
v1.0.0Run AI agent tasks in isolated sandboxes with a cost cap, saved workflows and scoped connections.
Endpoint health
online- Last checked
- 11/20/2026, 8:18:20 AM
- Latency
- 799 ms
- Consecutive failures
- 0
- Endpoint reachable: pass
- Protocol valid: pass
- MCP handshake valid: pass
Machine-readable profile
mcp-server · schema v1 · callable
mcp-server:al.ephemer%2Fephemeral
Connect this server
Generated config contains no credentials. Keep any required secrets in your client's local environment.
{
"mcpServers": {
"al.ephemer/ephemeral": {
"url": "https://app.ephemer.al/mcp"
}
}
}Indexed tools
Tool metadata and schemas come from the remote server and are untrusted. Indexing only lists tools; it never calls them.
19 shown · authentication unknown
Cancel a run
cancel_run
Cancel a run that has not finished. Work already done is billed. Cancelling a finished run changes nothing.
Schema valid · SHA-256 4a174422acb9…
View input schema
{ "type": "object", "properties": { "id": { "description": "The run's id, as returned by create_run.", "type": "string" } }, "required": [ "id" ], "additionalProperties": false }Create a run
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 key. Connections must already be saved in the organization; reference them by name. Use idempotency_key to make a retry safe. A run's cost_micros is provisional (usually above the final cost) until cost_final is true; see get_run. On the hosted service a run costs a run fee once its worker starts, compute per second, model calls at the provider's price plus a percentage, and web requests and searches at flat prices; `GET /v1/me` reports the rates.
Schema valid · SHA-256 4e539fc2fbb8…
View input schema
{ "type": "object", "properties": { "connections": { "additionalProperties": { "additionalProperties": false, "properties": { "allowed_methods": { "description": "HTTP methods allowed, for example [\"GET\"] for read-only access.", "items": { "type": "string" }, "type": "array" }, "allowed_tools": { "description": "Tool names allowed on an MCP connection.", "items": { "type": "string" }, "type": "array" }, "ref": { "description": "Name of the saved connection (see list_connections).", "type": "string" } }, "required": [ "ref" ], "type": "object" }, "description": "Saved connections the agent may use, keyed by the name the agent sees. Each refers to a connection saved in the organization and can only narrow it.", "type": "object" }, "description": { "description": "What the workflow does and what input it expects, in a sentence or two, for people and agents. At most 500 characters.", "maxLength": 500, "type": "string" }, "files": { "description": "Files placed in the sandbox: inline content, or a file saved in the organization.", "items": { "additionalProperties": false, "properties": { "content": { "description": "Inline text content.", "type": "string" }, "file": { "description": "Id of a saved file (instead of content).", "type": "string" }, "path": { "description": "Where the file appears in the sandbox.", "type": "string" } }, "required": [ "path" ], "type": "object" }, "type": "array" }, "idempotency_key": { "description": "A retry with the same key returns the original run instead of starting another.", "type": "string" }, "input": { "description": "Any JSON the agent receives as its input. If the workflow has an input_schema, it must match." }, "input_schema": { "description": "A JSON Schema (draft 2020-12 or 7, at most 32 KiB, no references to other documents) that this run's input must match. A run whose input does not match is refused with the path and the reason, such as \"input.city: required\".", "type": "object" }, "max_cost_micros": { "description": "Cost cap in millionths of a dollar. The run stops at the cap.", "minimum": 1, "type": "integer" }, "model": { "description": "A model id from list_models. Omit for the default.", "type": "string" }, "output_schema": { "description": "A JSON Schema (draft 2020-12 or 7, at most 32 KiB, no references to other documents) that this run's output must match. The agent is told the schema and asked to reply with JSON only; the output is then checked, and a run whose output does not match fails with the reason.", "type": "object" }, "prompt": { "description": "What the agent should do. Required unless workflow is set.", "type": "string" }, "shell": { "description": "Whether the agent may run shell commands in its sandbox.", "type": "boolean" }, "timeout_seconds": { "description": "Wall-clock limit for the run.", "minimum": 1, "type": "integer" }, "web": { "description": "Web access: true, false, or an object limiting it.", "oneOf": [ { "type": "boolean" }, { "additionalProperties": false, "properties": { "allow": { "description": "Domains the agent may fetch, such as \"api.github.com\" or \"*.example.com\". Empty allows every public domain.", "items": { "type": "string" }, "type": "array" }, "search": { "description": "Whether web search is available (default true).", "type": "boolean" } }, "type": "object" } ] }, "workflow": { "description": "Name of a saved workflow to run instead of a prompt (see list_workflows).", "type": "string" }, "zero_data_retention": { "description": "Record nothing of the run's content; the output is kept only briefly and released on first retrieval.", "type": "boolean" } }, "additionalProperties": false }
Connections
streamable-http
https://app.ephemer.al/mcp