Marketing
aetherya.ai
Runs AI-driven audience research simulations, estimates session costs, and produces decision briefs from planned studies.
ENDPOINT 1
https://mcp.aetherya.ai/mcp
MCP server metadata
- Name
- aetherya
- Version
- 1.0.4
Aetherya runs behavioral simulations with a synthetic audience: it predicts how real users would behave (where they hesitate, get confused, or drop off) — it does not survey real people. Every result is simulated, not real-user data; frame it that way to the user. There are two ways in. Pick by what you actually have: LANE A — you have a decision, not a study design. Call aetherya_plan_study with the objective in plain English. Aetherya designs the study, picks or builds the audience, prices it and runs it. It stops at a price and returns status 'needs_price_confirmation'; check with the user, then call aetherya_confirm_study with accept_sessions set to the quoted figure. Nothing is spent until you do. It may also return 'needs_clarification' with a question — answer it the same way. Re-call aetherya_plan_study with the autopilot_id to check progress. LANE B — you already know the method and the exact inputs: 1. ORIENT — call aetherya_list_capabilities to see which research methods are available and the exact inputs each needs, plus the plan headroom left. Do not guess method ids or enum values. 2. PRICE — call aetherya_estimate before anything expensive. It is free and runs nothing. 3. RUN — aetherya_run_study for a research study (pricing, concept, message, focus group), aetherya_test_copy to compare 2-5 copy variants, aetherya_audit_site for a page or flow, aetherya_ask_audience for a quick open-ended reaction, aetherya_simulate_post for a social post or email before it goes out. For a fast, cheap first answer on 2-5 variants, start with aetherya_read (an instant read against a market, in seconds) and test_copy the winner if it matters. 4. COLLECT — simulations usually outlive a single tool call, so a run normally returns status 'running' plus an id. That is expected. Call aetherya_get_result with the kind and id from the run's `next` hint to collect the findings. DELIVER (both lanes) — do not stop at raw metrics. aetherya_get_brief turns a finished run into a short decision brief (question, answer, reasoning, risks, what to do next) — that is what you show the user. aetherya_share_result then mints a public link they can send to someone else. Briefs are cached, so re-reading one is free. History: aetherya_list_runs finds earlier runs with the kind and id to collect them; do not re-run what already exists. aetherya_cancel stops a run started by mistake. Images: aetherya_compare_creatives compares thumbnails or banners (draft is free, it quotes the cost first). Video: aetherya_pretest_video uploads a clip, drafts it and quotes the cost before spending (speech-to-text is charged at prepare unless you pass a transcript); collect with aetherya_get_result kind video_analysis. Audiences: aetherya_list_audiences shows the synthetic audiences you can target; aetherya_create_audience generates new ones from a description. Cost: every run reports the simulation sessions it consumed. Three results are states, not failures — 'needs_price_confirmation' (re-send accepting the quoted sessions), 'needs_audience' (create an audience first) and 'needs_clarification' (answer the question asked). Each names its own next call. If a tool reports the plan's simulation limit was reached, relay that plainly and stop retrying.
Known tools 27
aetherya_list_capabilitiesList the research methods this workspace can run — with the exact stimulus fields each one requires — plus remaining plan headroom and simulation-session balance.
Inferred read-onlyaetherya_estimateQuote how many simulation sessions a run would cost, and roughly what share of your plan it would consume, before committing to it.
Inferred read-onlyaetherya_plan_studyGive Aetherya a decision you need to make, in plain English, and it designs the study, picks or builds the audience, prices it, and runs it — then writes a decision brief.
Inferred read-onlyaetherya_run_studyRun a Research Lab study — pricing sensitivity, message testing, concept testing, focus groups — against a synthetic audience and get a structured verdict with segment breakdowns, objections and representative reactions.
Potential side effectsaetherya_test_copyCompare 2-5 copy variants — headlines, value propositions, ad or email copy — against a synthetic audience, and get a ranked verdict with predicted action propensity, comprehension and trust per variant, plus the objections each raises.
Potential side effectsaetherya_audit_siteRun a behavioral simulation: a synthetic audience visits a URL and predicts where real users would hesitate, get confused, or drop off, plus messaging-clarity and UX friction findings with concrete fixes.
Potential side effectsaetherya_test_flowSimulate people who arrive from an ad (image, video or copy), land on a page, and take one of several exits (for example book a consultation, open the plan form, or leave).
Inferred read-onlyaetherya_simulate_postRun a post (X, LinkedIn, Instagram, Facebook) or email through a synthetic audience and get predicted engagement, sentiment and representative reactions before publishing.
Potential side effectsaetherya_cancelStop a study, instant read, plan, audit or post simulation that is still running.
Potential side effectsaetherya_list_runsList the workspace's recent simulations across studies, instant reads, plans, audits and post simulations, newest first, with the kind and id to pass to aetherya_get_result or aetherya_get_brief.
Potential side effectsaetherya_get_resultFetch the findings of a run started by aetherya_run_study, aetherya_test_copy, aetherya_audit_site, aetherya_plan_study, aetherya_read, aetherya_simulate_post, aetherya_compare_creatives, aetherya_pretest_video or aetherya_test_flow, using the kind and id from that tool's response.
Inferred read-onlyaetherya_get_audit_resultFetch the result of an audit started by aetherya_audit_site, using its job_id.
Inferred read-onlyaetherya_get_briefTurn a finished study, audit, read or post simulation into a short decision brief: the question, a direct answer, the reasoning with supporting simulated reactions, the risks, and what to do next.
Potential side effectsaetherya_share_resultMint a shareable URL for a completed study, audit or creative comparison so someone without an Aetherya account can read the findings.
Inferred read-onlyaetherya_pretest_reportAssemble a markdown pretest report (how we worked, one section per set, what the results mean, sealed predictions appendix) from finished simulations.
Inferred read-onlyaetherya_compare_creativesCompare 2+ image creatives (thumbnails, display banners, social images) against a synthetic audience.
Inferred read-onlyaetherya_pretest_videoPretest a short video (mp4, mov, webm; max 512 MB, 10 minutes) against a synthetic audience: hook score, attention curve, drop-off points.
Potential side effectsaetherya_seal_predictionLock a prediction (a creative comparison ranking, a video analysis, a study or a manual payload) with a SHA-256 hash and timestamp, so it can later be compared with what really happened.
Inferred read-onlyaetherya_verify_predictionRecompute the hash of a sealed prediction and report whether it still matches the stored one.
Inferred read-onlyaetherya_record_outcomeAttach what actually happened to a sealed prediction (append-only) and get the evaluation.
Inferred read-onlyaetherya_create_intake_linkCreate a secret upload link to send a client so they can drop creative files (images, video) for pretesting.
Potential side effectsaetherya_list_intake_filesList the files a client uploaded through an intake link (name, type, size, status, set label, a short-lived download url).
Inferred read-onlyaetherya_list_audiencesList the synthetic audiences (simulated personas) in this workspace: their overall shape (where they are, what they do, how much is actually filled in) plus a sample with ids.
Inferred read-onlyaetherya_create_audienceCreate synthetic-audience personas to simulate against.
Potential side effectsCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.aetherya]
url = "https://mcp.aetherya.ai/mcp"
enabled = trueClaude Code
.mcp.json
{
"mcpServers": {
"aetherya": {
"type": "http",
"url": "https://mcp.aetherya.ai/mcp"
}
}
}Claude Desktop
Settings → Connectors → Add custom connector
Name: aetherya
Remote MCP URL: https://mcp.aetherya.ai/mcpAdd this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"aetherya": {
"url": "https://mcp.aetherya.ai/mcp"
}
}
}Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"aetherya": {
"type": "http",
"url": "https://mcp.aetherya.ai/mcp"
}
}
}Generic MCP
Client-specific MCP configuration
{
"name": "aetherya",
"transport": "streamable-http",
"url": "https://mcp.aetherya.ai/mcp"
}MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.