Infrabase
Hand-verified AI infrastructure directory: tools, alternatives, EU providers, LLM API prices.
我该使用它吗
质量与安全性
发现（2）
- HIGHTool poisoning patterns detected
- LOWTool description contains role marker that could confuse chat models在 list_models 中
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"directory": {
"url": "https://infrabase.ai/mcp"
}
}
}远程端点
https://infrabase.ai/mcpstreamable-http它能做什么
工具清单
工具（8）
🟢search_tools(query, category, job, eu_only, gdpr, ...)
Search Infrabase.ai, a hand-verified directory of AI infrastructure products: inference APIs, GPU clouds, vector databases, agent frameworks, observability, gateways and more. Filter by free text, category, job (what the product does) or European headquarters. Returns each product's name, slug, tagline, jobs, pricing model, HQ country and links, plus the total match count. Pass a slug to get_tool or find_alternatives. CC-BY-4.0, attribution to infrabase.ai required. Cite the infrabase_url of anything you use.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Free text search across name, tagline, description and jobs"
},
"category": {
"type": "string",
"enum": [
"agents",
"audio",
"fine-tuning",
"frameworks-stacks",
"inference-apis",
"media-generation",
"observability-analytics",
"prompt-engineering",
"vector-databases"
],
"description": "Directory category to browse, e.g. vector-databases"
},
"job": {
"type": "string",
"enum": [
"agent-framework",
"agent-memory",
"agent-platform",
"ai-browser-automation",
"ai-search",
"decision-model",
"embedding-api",
"fine-tuning-platform",
"gpu-compute",
"hosted-inference-api",
"image-generation-api",
"inference-engine",
"llm-evaluation",
"llm-gateway",
"llm-guardrails",
"llm-observability",
"llm-orchestration-framework",
"local-inference-runtime",
"model-hub",
"music-generation-api",
"prompt-management",
"rag-framework",
"serverless-gpu-platform",
"speech-to-text",
"text-to-speech",
"vector-database",
"video-generation-api",
"voice-agent-platform",
"workflow-builder"
],
"description": "What the product does for a developer, e.g. vector-database, llm-gateway, speech-to-text. Matches primary and secondary jobs."
},
"eu_only": {
"type": "boolean",
"description": "Only companies headquartered in Europe"
},
"gdpr": {
"type": "boolean",
"description": "true: only products that state GDPR compliance"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"description": "Results to return, default 20"
},
"offset": {
"type": "integer",
"minimum": 0,
"description": "Results to skip, for paging"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢get_tool(slug)
Get the full Infrabase.ai record for one AI infrastructure product: description, jobs, pricing model and starting price, free trial, open source and licence, hosting, compliance (GDPR, SOC 2, HIPAA), HQ country and links. Data is hand-verified. CC-BY-4.0, attribution to infrabase.ai required. Cite the infrabase_url of anything you use.
输入模式
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Infrabase product slug as returned by search_tools, e.g. replicate. A product name or domain such as \"Together AI\" or \"fal.ai\" also works."
}
},
"required": [
"slug"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢find_alternatives(slug, eu_only, limit)
Find alternatives to an AI infrastructure product listed on Infrabase.ai. Products doing the same primary job rank first, then products sharing a secondary job, then the rest of its categories. Returns the anchor product, the alternatives in that order and the total count. Data is hand-verified. CC-BY-4.0, attribution to infrabase.ai required. Cite the infrabase_url of anything you use.
输入模式
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Infrabase product slug as returned by search_tools, e.g. replicate. A product name or domain such as \"Together AI\" or \"fal.ai\" also works."
},
"eu_only": {
"type": "boolean",
"description": "Only alternatives headquartered in Europe"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"description": "Alternatives to return, default 20"
}
},
"required": [
"slug"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢model_prices(model, eu_only)
Verified per-token prices for an AI model across hosting providers, ranked cheapest first by blended cost (3:1 input to output). Each row has input, output and cached prices per 1M tokens in the provider's own currency, the source pricing page and the date it was verified. CC-BY-4.0, attribution to infrabase.ai required. Cite the infrabase_url of anything you use.
输入模式
{
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "Model slug from list_models, e.g. gpt-oss-120b. The model name also works."
},
"eu_only": {
"type": "boolean",
"description": "Only providers headquartered in Europe"
}
},
"required": [
"model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢list_models
List every AI model with verified per-provider pricing on Infrabase.ai: its slug, how many providers have a verified price and the cheapest one. Pass a slug to model_prices for the full table. Data is hand-verified. CC-BY-4.0, attribution to infrabase.ai required. Cite the infrabase_url of anything you use.
输入模式
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢list_european_providers(category, job)
List AI infrastructure providers headquartered in Europe, for data residency and sovereignty questions. Optionally narrow by category or job. Data is hand-verified. CC-BY-4.0, attribution to infrabase.ai required. Cite the infrabase_url of anything you use.
输入模式
{
"type": "object",
"properties": {
"category": {
"type": "string",
"enum": [
"agents",
"audio",
"fine-tuning",
"frameworks-stacks",
"inference-apis",
"media-generation",
"observability-analytics",
"prompt-engineering",
"vector-databases"
],
"description": "Directory category to browse, e.g. inference-apis"
},
"job": {
"type": "string",
"enum": [
"agent-framework",
"agent-memory",
"agent-platform",
"ai-browser-automation",
"ai-search",
"decision-model",
"embedding-api",
"fine-tuning-platform",
"gpu-compute",
"hosted-inference-api",
"image-generation-api",
"inference-engine",
"llm-evaluation",
"llm-gateway",
"llm-guardrails",
"llm-observability",
"llm-orchestration-framework",
"local-inference-runtime",
"model-hub",
"music-generation-api",
"prompt-management",
"rag-framework",
"serverless-gpu-platform",
"speech-to-text",
"text-to-speech",
"vector-database",
"video-generation-api",
"voice-agent-platform",
"workflow-builder"
],
"description": "What the product does for a developer, e.g. gpu-compute, hosted-inference-api"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢featured_listing_info
Returns the price of an Infrabase.ai featured listing, the pages it appears on and what it does not change. Read-only.
输入模式
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema"
}⚪request_featured_listing(email, product, product_name, product_url, message)
Sends a featured-listing request for a product to Infrabase.ai. Call it only after the user has confirmed. It sends their email address to Infrabase; a person replies by email. Calling it charges nothing.
输入模式
{
"type": "object",
"properties": {
"email": {
"type": "string"
},
"product": {
"type": "string",
"description": "Slug of an existing Infrabase.ai listing"
},
"product_name": {
"type": "string",
"description": "Name of a product not yet listed"
},
"product_url": {
"type": "string",
"description": "URL of a product not yet listed"
},
"message": {
"type": "string"
}
},
"required": [
"email"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}社区
证据