Connect ATOM Pricing Intelligence and your agent gets 9 tools, among them compare_prices, get_index_benchmarks, get_kpis. It answers at https://atom-mcp-server-production.up.railway.app/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 10 September 2026; the last check, on 19 October 2026, succeeded.
The Global Price Benchmark for AI Inference. 1,600+ SKUs, 40+ vendors, 14 price indexes.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
compare_prices | Cross-vendor price comparison for a specific model or model family. Shows the same model (or family) priced across different vendors, sorted cheapest first. Essential for cost optimization and vendor selection. Examples: - "Compare Llama 3. Inputs: model_name, model_family, direction, modality, limit, _atom_api_key |
get_index_benchmarks | AIPI (ATOM Inference Price Index) — chained matched-model price benchmarks for AI inference. Returns benchmark indexes across four categories: - Modality: Text, Multimodal, Image, Audio, Video, Voice, Embeddings - what does this type of inf Inputs: index_code, index_category, limit, _atom_api_key |
get_kpis | ATOM Inference Market KPIs — 9 cost and structure metrics derived from live pricing data across all tracked vendors: - Output Price Premium: how much more output tokens cost vs input - Caching Discount Rate: average discount for cached inpu Inputs: _atom_api_key |
get_market_stats | Aggregate AI inference market intelligence. Returns total vendor/model/SKU counts, price distribution (median, mean, quartiles, min/max), and modality breakdown. Optionally filter by modality. Examples: - "AI inference market overview" → (n Inputs: modality, _atom_api_key |
get_model_detail | Deep dive on a single AI model: technical specs + pricing across all vendors. Returns model_registry data (context window, parameters, open-source status, training cutoff, model family) plus all SKU pricing across every vendor that offers t Inputs: model_name, _atom_api_key |
get_model_intelligence | ATOM Model Intelligence — 6 capability and coverage metrics derived from the metadata behind every tracked model. Complements the pricing KPIs in get_kpis. Returns 6 metrics: - Reasoning Tier Share: % of general-purpose text models that are Inputs: _atom_api_key |
get_vendor_catalog | Full catalog for a specific vendor: all models, modalities, and pricing. Returns vendor metadata (country, region, pricing page URL) plus every model and SKU they offer. Examples: - "What does Together AI sell?" → vendor="Together AI" - "Op Inputs: vendor, modality, direction, limit, _atom_api_key |
list_vendors | List all AI inference vendors tracked by ATOM. Returns vendor name, country, region, and pricing page URL. Vendors span four channel types: Model Developers, Cloud Marketplaces, Inference Platforms, and Neoclouds. Optionally filter by regio Inputs: region, country, _atom_api_key |
search_models | Search and filter AI inference models across all tracked vendors and SKUs. Query by modality (Text, Image, Audio, Video, Multimodal), vendor, creator, model family, open-source status, price range, context window, and parameter count. Retur Inputs: modality, vendor, creator, model_family, open_source, direction |
Every block below points at https://atom-mcp-server-production.up.railway.app/mcp. Pick your client and copy.
claude mcp add --transport http atom-pricing-intelligence https://atom-mcp-server-production.up.railway.app/mcp
{
"mcpServers": {
"atom-pricing-intelligence": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://atom-mcp-server-production.up.railway.app/mcp"]
}
}
}{
"mcpServers": {
"atom-pricing-intelligence": {
"url": "https://atom-mcp-server-production.up.railway.app/mcp"
}
}
}{
"servers": {
"atom-pricing-intelligence": {
"type": "http",
"url": "https://atom-mcp-server-production.up.railway.app/mcp"
}
}
}{
"context_servers": {
"atom-pricing-intelligence": {
"url": "https://atom-mcp-server-production.up.railway.app/mcp"
}
}
}{
"mcpServers": {
"atom-pricing-intelligence": {
"serverUrl": "https://atom-mcp-server-production.up.railway.app/mcp"
}
}
}{
"mcpServers": {
"atom-pricing-intelligence": {
"url": "https://atom-mcp-server-production.up.railway.app/mcp"
}
}
}name: ATOM Pricing Intelligence
version: 0.0.1
schema: v1
mcpServers:
- name: ATOM Pricing Intelligence
type: streamable-http
url: https://atom-mcp-server-production.up.railway.app/mcp{
"mcpServers": {
"atom-pricing-intelligence": {
"httpUrl": "https://atom-mcp-server-production.up.railway.app/mcp"
}
}
}{
"mcpServers": {
"atom-pricing-intelligence": {
"type": "http",
"url": "https://atom-mcp-server-production.up.railway.app/mcp"
}
}
}{
"mcpServers": {
"atom-pricing-intelligence": {
"url": "https://atom-mcp-server-production.up.railway.app/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fatom-mcp-server-production.up.railway.app%2Fmcp&type=streamable_http&id=atom-pricing-intelligence&name=ATOM%20Pricing%20Intelligence
It answered our last check on 19 October 2026 in 289 ms. Over 6 checks since 10 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
9, as returned by the server's own tools/list on 12 September 2026: compare_prices, get_index_benchmarks, get_kpis, get_market_stats, get_model_detail, get_model_intelligence, get_vendor_catalog, list_vendors, and 1 more.
It answered our last check on 19 October 2026 in 289 ms. Over 6 checks since 10 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://atom-mcp-server-production.up.railway.app/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.a7om-ai. Endpoint host: atom-mcp-server-production.up.railway.app. ARD identifier: urn:air:io.github.a7om-ai:mcp:atom-mcp-server.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.