IoMarkets.ai guide
Guide to IoMarkets.ai Federated Computing: receipt checks, runs, costs and evaluation requests.
我該用這個嗎
品質與安全性
發現項目（1）
- LOWTool 'get_overview' description lacks action verb在 get_overview 中
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"iomarkets-ai": {
"url": "https://iomarkets.ai/mcp"
}
}
}遠端端點
https://iomarkets.ai/mcpstreamable-http它能做什麼
工具清單
工具（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.
輸入結構描述
{
"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.
輸入結構描述
{
"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.
輸入結構描述
{
"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.
輸入結構描述
{
"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).
輸入結構描述
{
"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.
輸入結構描述
{
"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.
輸入結構描述
{
"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
}社群
證據