AI & Machine Learning
aigratis.my.id
MCP server for discovering, comparing, and pricing AI models across gateways, including cost estimates and provider listings.
ENDPOINT 1
https://aigratis.my.id/api/mcp
MCP server metadata
- Name
- aigratis
- Version
- 1.0.0
AIGratis catalogs AI models across API gateways (OpenRouter-style resellers), with prices normalized to USD per 1 million tokens and a flag for free offers. Use search_models to find models (free=true for free ones), compare_model_prices to see every gateway selling one model (cheapest first), estimate_cost to turn a token budget into a monthly bill per gateway, and top_free_gateways to find which gateways give away the most models. Prices are refreshed automatically from each gateway's API; check updatedAt fields when freshness matters. Model slugs used by compare_model_prices and estimate_cost come from suggest_models or search_models (canonicalSlug). All tools are read-only.
Known tools 9
compare_model_pricesEvery gateway offering one canonical model, cheapest input price first.
Inferred read-onlyestimate_costMonthly bill for a model at every gateway, given expected input and output tokens.
Inferred read-onlylist_gatewaysActive AI gateways (providers) in compact form: slug, name, tagline, website, referral link, model count, likes, last sync.
Inferred read-onlyget_gatewayOne gateway's profile plus its full model list with prices, context length, modalities and isFree, sorted by input price.
Inferred read-onlytop_free_gatewaysGateways ranked by how many distinct models they offer for free, with a few well-known example models each.
Inferred read-onlyrecent_changesCatalog events, newest first: models added/removed/returned, price up/down, became free/paid, new gateways.
Inferred read-onlyget_fx_ratesExchange rates used to convert USD prices (perUsd = units of currency per 1 USD).
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.aigratis]
url = "https://aigratis.my.id/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"aigratis": {
"type": "http",
"url": "https://aigratis.my.id/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: aigratis
Remote MCP URL: https://aigratis.my.id/api/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": {
"aigratis": {
"url": "https://aigratis.my.id/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"aigratis": {
"type": "http",
"url": "https://aigratis.my.id/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "aigratis",
"transport": "streamable-http",
"url": "https://aigratis.my.id/api/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.