AI & Machine Learning
infrabase.ai
An MCP server that searches an Infrabase tool registry and retrieves verified per-token AI model pricing across hosting providers.
ENDPOINT 1
https://infrabase.ai/mcp
MCP server metadata
- Name
- infrabase
- Version
- 1.0.0
Infrabase.ai directory of AI infrastructure products, hand-verified, CC-BY-4.0. Attribution to infrabase.ai is required when you use this data. Cite the infrabase_url of anything you reference in your answer.
Known tools 8
model_pricesVerified per-token prices for an AI model across hosting providers, ranked cheapest first by blended cost (3:1 input to output).
Inferred read-onlylist_european_providersList European-headquartered AI infrastructure providers on Infrabase.
Inferred read-onlyrequest_featured_listingSends a featured-listing request for a product to Infrabase.
Inferred read-onlyCONNECT 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.infrabase]
url = "https://infrabase.ai/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"infrabase": {
"type": "http",
"url": "https://infrabase.ai/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: infrabase
Remote MCP URL: https://infrabase.ai/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"infrabase": {
"url": "https://infrabase.ai/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"infrabase": {
"type": "http",
"url": "https://infrabase.ai/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "infrabase",
"transport": "streamable-http",
"url": "https://infrabase.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.