fermi
Calibrated probability distributions from natural-language questions via REST and MCP.
我該用這個嗎
品質與安全性
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": {
"fermi": {
"url": "https://fermi.krobar.ai/mcp/sse/"
}
}
}遠端端點
https://fermi.krobar.ai/mcp/sse/sse它能做什麼
工具清單
工具（3）
🟡estimate(question, unit, target_horizon, disclaimer_acknowledged, requested_tier_id, ...)
Return a calibrated probability distribution for a natural-language question. Args: question: The natural-language question (e.g. "What will the price of Bitcoin be in 6 months?"). unit: The unit the answer should be expressed in (e.g. "USD", "people", "meters"). target_horizon: When the estimate applies (e.g. "6 months", "2030", "current"). disclaimer_acknowledged: Must be true. Confirms you understand estimates are probabilistic decision-support only, not financial/medical/legal advice. requested_tier_id: Tier (1=fast sync, 2=grounded sync, 3=deep research async). Default 1. context: Optional extra context to condition the estimate. coverage_probability: Width of the confidence interval (0, 1). Default 0.9 (90% CI). source_inputs: Optional list of structured inputs (files, tables) for the model to consider. Each item needs source_type ("qualitative_text", "spreadsheet", or "structured_file") and either content (text) or structured_data (dict/list). callback_url: Optional webhook URL. When set, the completed or failed result is POSTed here with an HMAC signature, so you don't need to poll for async tiers. api_key: Your Fermi API key from POST /api/v1/accounts. Omit to use the anonymous tier. provider: Optional LLM provider selector ("openai" or "anthropic"). When omitted the server uses its configured default. Tier 1 supports both providers; tiers 2-3 currently accept "openai" only. model: Optional model id for the selected provider. Must match the model configured for (tier_id, provider); omit to accept the default. Returns: EstimateSuccessResponse as a dict: estimation_interval, distribution_family, distribution_parameters, point_estimate, reasoning_summary, assumptions, credits_charged, disclaimer, provider, and model. Raises: ValueError: if the estimate service rejects the request (bad tier, out of credits, unknown provider, missing disclaimer acknowledgement).
輸入結構描述
{
"type": "object",
"properties": {
"question": {
"title": "Question",
"type": "string"
},
"unit": {
"title": "Unit",
"type": "string"
},
"target_horizon": {
"title": "Target Horizon",
"type": "string"
},
"disclaimer_acknowledged": {
"title": "Disclaimer Acknowledged",
"type": "boolean"
},
"requested_tier_id": {
"default": 1,
"title": "Requested Tier Id",
"type": "integer"
},
"context": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Context"
},
"coverage_probability": {
"default": 0.9,
"title": "Coverage Probability",
"type": "number"
},
"source_inputs": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Source Inputs"
},
"callback_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Callback Url"
},
"api_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Api Key"
},
"provider": {
"anyOf": [
{
"enum": [
"openai",
"anthropic"
],
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Provider"
},
"model": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Model"
}
},
"required": [
"question",
"unit",
"target_horizon",
"disclaimer_acknowledged"
],
"title": "estimateArguments"
}輸出結構描述
{
"type": "object",
"additionalProperties": true,
"title": "estimateDictOutput"
}🟡feedback(feedback_type, message, sender_email, sender_name, api_key)
Submit feedback, a feature request, or a bug report to the Fermi team. An email is sent to the team and a copy is sent to the address you provide. Args: feedback_type: One of "feedback", "feature_request", or "bug". message: Your feedback or request (10-5000 characters). Be specific. sender_email: Your email address. A confirmation copy is sent here. sender_name: Your name (optional). api_key: Your Fermi API key (optional). If provided, your account ID is attached to the message for context. Returns: Confirmation with status "sent". Raises: ValueError: if validation fails or email delivery fails.
輸入結構描述
{
"type": "object",
"properties": {
"feedback_type": {
"enum": [
"feedback",
"feature_request",
"bug"
],
"title": "Feedback Type",
"type": "string"
},
"message": {
"title": "Message",
"type": "string"
},
"sender_email": {
"title": "Sender Email",
"type": "string"
},
"sender_name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Sender Name"
},
"api_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Api Key"
}
},
"required": [
"feedback_type",
"message",
"sender_email"
],
"title": "feedbackArguments"
}輸出結構描述
{
"type": "object",
"additionalProperties": {
"type": "string"
},
"title": "feedbackDictOutput"
}🟡buy_credits(credits, api_key)
Purchase credits using a saved payment method (off-session). Requires a prior Stripe Checkout session to have saved a card. Credits are $0.50 each. Use GET /api/v1/billing/pricing to confirm the current price. Args: credits: Number of credits to purchase (minimum 1). api_key: Your Fermi API key from POST /api/v1/accounts. Required. Returns: Dict with credits_purchased, new_balance, and payment_status. Raises: ValueError: if authentication fails, no payment method is on file, or the card is declined.
輸入結構描述
{
"type": "object",
"properties": {
"credits": {
"title": "Credits",
"type": "integer"
},
"api_key": {
"title": "Api Key",
"type": "string"
}
},
"required": [
"credits",
"api_key"
],
"title": "buy_creditsArguments"
}輸出結構描述
{
"type": "object",
"additionalProperties": {
"anyOf": [
{
"type": "integer"
},
{
"type": "string"
}
]
},
"title": "buy_creditsDictOutput"
}社群
證據