Attic Standard MCP Server
MCP serverAI & modelsYour AI can look up what any AI model costs to run, compare the same model across different vendors, and track market-wide price trends. It draws on a benchmark covering 1,600+ models from 40+ vendors, with 14 price indexes. Use it to find the most cost-effective model before you build or switch.
Use Attic Standard MCP Server in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add Attic Standard MCP Server and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use Attic Standard MCP Server to search models
No key or account is asked for. Not verified by us yet: Ahel has not run a call through it.
Details
Available today. Use it from your connected AI after setup. It ran on Ahel's own infrastructure and offers 8 tools.
No key or account is asked for. Not verified by us yet: Ahel has not run a call through it.
After adding it, ask your AI to compare prices for a model you are considering, or to find the lowest-priced option for a task like text or image generation.
What your AI can do with it
- Search AI models by type, such as text, image, audio, or video
- Compare prices for the same model across different vendors
- Get technical specs and pricing for a single model
- Browse a vendor's full catalog of models and prices
- Pull market-wide stats like median and average prices
- List all tracked vendors with links to their pricing pages
Install Attic Standard MCP Server
The server’s own address, for the clients that take one directly. Or connect Ahel once and every client you use reads it from one address, with the account kept on Ahel rather than in each client’s config.
Claude Code
claude mcp add --transport http --scope user attic-standard-mcp-server 'https://atom-mcp-server-production.up.railway.app/mcp'Run it once in your project, then open /mcp to approve any sign-in the server asks for.
Claude Desktop
https://atom-mcp-server-production.up.railway.app/mcpAdd a custom connector in Settings, paste this address, and approve the sign-in.
Cursor
cursor://anysphere.cursor-deeplink/mcp/install?name=attic-standard-mcp-server&config=eyJ1cmwiOiJodHRwczovL2F0b20tbWNwLXNlcnZlci1wcm9kdWN0aW9uLnVwLnJhaWx3YXkuYXBwL21jcCJ9Open the link and Cursor adds the server at that address.
ChatGPT
https://atom-mcp-server-production.up.railway.app/mcpIn Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.
Codex
codex mcp add attic-standard-mcp-server --url 'https://atom-mcp-server-production.up.railway.app/mcp'Run it once, then sign in with codex mcp login attic-standard-mcp-server if the server asks for an account.
From the project's README
As published by a7om-ai/atom-mcp-server in README.md.
What this is
Attic Standard is the independent price reporting agency for AI inference. Every week it records the published prices of model developers, cloud marketplaces, inference platforms and neoclouds, and turns them into price indexes and market KPIs.
This server puts that data inside any MCP-compatible assistant (Claude, ChatGPT, Cursor, Windsurf, VS Code). Ask "Where is text inference priced this week?" or "Cheapest place to run Llama 3.3 70B?" and the assistant answers from the published benchmark instead of guessing.
The indexes
23 published indexes in six families, each reported for input, cached input and output where the modality has them.
| Family | Indexes | What it answers |
|---|---|---|
| Modality | Text, Multimodal, Image (per image), Image (per megapixel), Video (per second), Video (per clip), Audio, Voice, Embeddings | What does this kind of inference cost? |
| Channel | Model developers, Cloud marketplaces, Inference platforms, Neoclouds | Where is it cheapest to buy? |
| Tier | Flagship, Core, Compact | What does a place higher in a maker's lineup cost? |
| License | Open weights, Restricted weights, Proprietary | What is the price of openness? |
| Origin | United States, China | How do the two model-building countries price? |
| Use case | Reasoning, Coding | What do specialist models cost? |
Each index carries two numbers:
- Benchmark: the chained level, May 2026 = 100 (the average of that month's weeks), with week, month and vs-base changes.
- Spot: what the market charges this week, in dollars. Each model is taken at the median of its vendors' prices, and the spot is the median across those models, with the interquartile range. Its change is stated against its own May 2026 average, month on month and week on week, and because the spot follows the market as it stands, that change reflects models arriving and leaving as well as repricing.
Token prices are per 1,000 tokens. Other modalities use their own unit.
Tools
| Tool | Tier | What it returns |
|---|---|---|
get_index_benchmarks | Free | Every published index at the current week: benchmark level and changes, spot price, range and changes, coverage with the May 2026 basket |
get_price_history | Free / PRO | Weekly index series with the spot price and its range (free); week-by-week price of a model at every vendor, with each repricing (PRO) |
get_kpis | Free | The nine market KPIs: output premium, caching discount, caching availability, repricing activity, repricing depth, post-launch drift, multi-vendor spread, first-party premium, marketplace premium |
get_model_intelligence | Free | Six capability measures: reasoning tier share, long-context saturation, context ceiling, output ceiling spread, training cutoff lag, vendor modality breadth |
get_index_constituents | Free / PRO | What is inside an index basket: composition by channel, origin, tier and license (free); model-by-model basket with vendors (PRO) |
get_market_stats | Free / PRO | Coverage (vendors by channel, models, SKUs, indexes) and price distributions by modality, unit and direction; vendor breakdown on PRO |
list_vendors | Free | The vendor fleet with channel, country and pricing page |
search_models | Free / PRO | Search every priced SKU by modality, vendor, channel, creator, family, tier, license, origin, reasoning, price and context |
get_model_detail | Free / PRO | One model's specs, the indexes it belongs to, and its price at every vendor |
compare_prices | Free / PRO | One model or family across all vendors: cheapest, dearest and spread per direction, with every offer on PRO |
get_vendor_catalog | Free / PRO | One vendor's channel, coverage and full price list |
Free and PRO
| Free | MCP PRO | |
|---|---|---|
| Indexes, index history, market KPIs, model intelligence | Full | Full |
| Vendor list and market coverage | Full | Full |
| Index baskets | Composition counts | Model and vendor detail |
| Search, model detail, comparisons, catalogs, model price history | Counts, ranges, redacted samples | Vendor names, model names, exact prices |
| Price | $0 | $500/month |
The free tier carries everything atticstandard.com publishes. PRO adds the vendor- and SKU-level detail behind it. Subscribe at atticstandard.com/mcp.
Connect
Claude (web and desktop)
Settings → Connectors → Add custom connector
Name: Attic Standard
URL: https://mcp.atticstandard.com/mcp
Claude Desktop, Cursor, Windsurf (config file)
{
"mcpServers": {
"attic-standard": {
"url": "https://mcp.atticstandard.com/mcp"
}
}
}
If your client does not accept a remote URL, use the proxy:
{
"mcpServers": {
"attic-standard": {
"command": "npx",
"args": ["mcp-remote", "https://mcp.atticstandard.com/mcp"]
}
}
}
Connections made with the earlier address, https://atom-mcp-server-production.up.railway.app/mcp, keep working.
PRO key
PRO subscribers receive a key. Tell your assistant to pass it as _atom_api_key on each call, or keep it in a project instruction such as "Use my Attic Standard key XXXX for every Attic Standard tool call."
Example questions
- "Where is text inference priced this week, and how has it moved since May?"
- "Compare the four distribution channels."
- "How much cheaper are open-weight models than proprietary ones?"
- "What share of models dropped in price after launch?"
- "What is inside the flagship index?"
- "Cheapest place to run DeepSeek V3, and who repriced it this quarter?" (PRO)
- "Everything one named vendor sells, with prices." (PRO)
Self-hosting
The hosted server above is the supported way to connect. The code is open so you can see exactly what it reads and how it gates data.
| Variable | Required | Description |
|---|---|---|
SUPABASE_URL | Yes | Database URL |
SUPABASE_SERVICE_ROLE_KEY | Yes (hosted) | Server-side database key, set only in the host's environment |
TRANSPORT | No | stdio (default) or http |
PORT | No | HTTP port (default 3000) |
Stack: TypeScript, Node.js, MCP SDK, Express, Zod, Supabase over REST.
About
Attic Standard publishes the global price benchmark for AI inference: independent, methodology-led and updated weekly across the model developers, cloud marketplaces, inference platforms and neoclouds that sell inference. The name refers to the Attic silver-weight standard of the ancient Greek world, a common measure both sides of a trade accepted.
Products: MCP · Terminal · Feed
Contact: info@atticstandard.com
License
MIT
Tools it gives your AI (8)
| Tool | What it does |
|---|---|
| search_models | Search and filter AI inference models across 40+ vendors and 1,600+ SKUs. Query by modality (Text, Image, Audio, Video, Multimodal), vendor, creator, model family, open-source status, price range... |
| 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... |
| 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. |
| 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... |
| get_market_stats | Aggregate AI inference market intelligence. Returns total vendor/model/SKU counts, price distribution (median, mean, quartiles, min/max), and modality breakdown. |
| get_index_benchmarks | AIPI (ATOM Inference Price Index) — chained matched-model price benchmarks for AI inference. Returns benchmark prices across index families (Text, Image, Audio, Video, Multimodal, Composite) with... |
| get_kpis | ATOM Inference Price Index (AIPI) market-level KPIs. Returns 6 key performance indicators derived from 1,600+ SKUs: - Output Premium: how much more output tokens cost vs input - Caching Savings... |
| list_vendors | List all 41 AI inference vendors tracked by ATOM. Returns vendor name, country, region, and pricing page URL. Optionally filter by region or country. Examples: - "List all vendors" → (no params) |
Signals
- Last commit
- Oct 2026
- Weekly downloads
- 60
- Tools captured
- 8
Advanced
- Delivery
- atom-mcp-server MCP server → your Ahel connector (mcp.ahel.ai) → your AI.
- Item type
- mcp-server
- Key
io-github-a7om-ai-atom-mcp-server- Source
- github.com/a7om-ai/atom-mcp-server
- Hosted endpoint
https://atom-mcp-server-production.up.railway.app/mcp
github.com/a7om-ai/atom-mcp-server
More in AI & models
MCP server · upstash
More in AI & modelsAdButler
MCP server · adbutler
More in AI & modelsottasia
MCP server · aiweather-anurag
More in AI & modelsunphurl
MCP server · 123ergo
More in AI & modelsmicrosoft-learn-mcp
MCP server · microsoftdocs
More in AI & modelsfree-blueprints
MCP server · agent-blueprint
More in AI & models