Ephemeral MCP server

• Registry nameal.ephemer/ephemeralverified in the MCP registry

The registry name sits under ephemer.al. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-27
• Tools19
• Server calls itselfephemeral
• Server version2026.10.27.1-5ab06dd
• Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 530 ms.

• Whether its tools do the product's job has not been judged yet.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP score78 of 100answers 100 · definitions 96 · context 88 · connects 100 · lowered by the warning signs below
• Answered100% of days7 of 7 daily checks
• Median first answer490 ms
• Space in an agent's context≈ 4,649 tokensthe definitions of all its tools (19), which an agent carries on every turn
• Tool definitionsA · 96 of 100
• Typed results0 of 19 toolsdeclared outputSchema: results come typed, read once

• Parameters without a type: in 3 of 19
• Parameters without a description: in 1 of 19

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• 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…

• 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…

• 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…

• 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…

• 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…

• 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…

• 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…

• 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.