IoMarkets.ai guide
Guide to IoMarkets.ai Federated Computing: receipt checks, runs, costs and evaluation requests.
使うべきか
品質と安全性
検出事項（1）
- LOWTool 'get_overview' description lacks action verbget_overview 内
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"iomarkets-ai": {
"url": "https://iomarkets.ai/mcp"
}
}
}リモートエンドポイント
https://iomarkets.ai/mcpstreamable-httpできること
ツール一覧
ツール（7）
🟢get_overview
What IoMarkets.ai is and what is built: Federated Computing (private computing across organisations on confidential hardware), with the main pages and what is a demonstration.
入力スキーマ
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢get_guide(task)
Step-by-step instructions, with the exact button names, for one task on iomarkets.ai. Without a task, lists the tasks.
入力スキーマ
{
"type": "object",
"properties": {
"task": {
"type": "string",
"enum": [
"look-around",
"runs",
"verify-receipt",
"audit-trail",
"request",
"review-pack",
"pilot",
"cost",
"own-assistant"
],
"description": "Which task. Leave out to list them all."
}
},
"additionalProperties": false
}🟢explain_term(term)
A plain-English meaning of a word used on the site: digital signature, invoice, Federated Computing, confidential hardware, attestation, receipt, AI agent, MCP. Without a word, lists them all.
入力スキーマ
{
"type": "object",
"properties": {
"term": {
"type": "string",
"description": "The word to explain."
}
},
"additionalProperties": false
}🟢list_runs
Every Federated Computing run done on confidential hardware, newest first: its id, what it showed and the hardware it ran on.
入力スキーマ
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢get_run(id)
One Federated Computing run in detail: what it showed, the model and data, hardware, location, result, payment, and whether its receipt verifies (checked now, with the same code as the receipt checker).
入力スキーマ
{
"type": "object",
"properties": {
"id": {
"type": "string",
"enum": [
"sealed-tdx-gpu",
"sealed-tdx",
"gpu-llm-14b",
"gpu-llm-7b",
"gpu-llm",
"join-across-banks",
"federated-round",
"pilot-rehearsal",
"gpu-compute",
"three-banks",
"governed",
"intel-tdx",
"first-run"
],
"description": "The run id, from list_runs."
}
},
"required": [
"id"
],
"additionalProperties": false
}🟢estimate_cost(kind, runs, key_services, months)
What Federated Computing runs cost in confidential cloud time, at Google Cloud list prices, for the machines and run times the real runs used, plus key services. Same numbers as the cost estimator page. An estimate, not a quote.
入力スキーマ
{
"type": "object",
"properties": {
"kind": {
"type": "string",
"enum": [
"tabular-cpu",
"tabular-tdx",
"gpu-small",
"gpu-llm-14b"
],
"description": "tabular-cpu (credit, fraud, risk models), tabular-tdx, gpu-small, or gpu-llm-14b."
},
"runs": {
"type": "number",
"description": "How many runs. Default 1."
},
"key_services": {
"type": "number",
"description": "Key services, one per data or model owner. Default 2."
},
"months": {
"type": "number",
"description": "Months the key services stay up. Default 3."
}
},
"required": [
"kind"
],
"additionalProperties": false
}🟢draft_evaluation_request(role, organisation, name, email, goal, ...)
Turn what someone wants to evaluate, in their own words, into a Federated Computing evaluation request. Returns the message and a link that opens it in their email app; nothing is sent for them, and they can also use the form. Ask for anything missing, one question at a time, before calling it.
入力スキーマ
{
"type": "object",
"properties": {
"role": {
"type": "string",
"enum": [
"Benchmark or data owner",
"Model owner",
"Model-risk or audit team",
"Cloud provider",
"Research or grant partner",
"Other"
],
"description": "Their role."
},
"organisation": {
"type": "string"
},
"name": {
"type": "string"
},
"email": {
"type": "string",
"description": "Where the reply should go."
},
"goal": {
"type": "string",
"description": "What they want to evaluate, in a sentence or two."
},
"assets": {
"type": "string",
"enum": [
"Tabular model or data",
"Text classifier",
"Large language model",
"Not sure yet"
],
"description": "The kind of model or data (optional)."
},
"constraints": {
"type": "string",
"description": "Regions, confidentiality, timing (optional)."
}
},
"required": [
"role",
"organisation",
"name",
"email",
"goal"
],
"additionalProperties": false
}コミュニティ
エビデンス