Attic Standard
io.github.AtticStandardv2.1.0Updated Oct 5, 2026
The global price benchmark for AI inference: 23 price indexes, market KPIs and SKU-level prices.
Overview
Gives an assistant weekly AI inference price indexes, market KPIs and SKU-level model prices from the Attic Standard benchmark.
- What it does
- Attic Standard is a remote MCP server that exposes a published price benchmark for AI inference. Tools such as get_index_benchmarks, get_kpis and get_model_intelligence return 23 indexes across modality, channel, tier, license, origin and use case, plus nine market KPIs and six capability measures. Other tools search priced SKUs, show one model's specs and prices at every vendor, compare a model or family across vendors, list vendors and return a vendor's catalog. Free calls return counts, ranges and redacted samples; PRO calls return vendor names, model names and exact prices.
- When to use it
- Use it when an assistant needs current, sourced inference pricing rather than guesses: comparing distribution channels, checking what a modality or tier costs this week, or finding the cheapest vendor for a given model. It suits pricing research, procurement comparisons and market commentary.
- Requirements
- A remote MCP endpoint at added as a custom connector or in a client config file; clients that reject remote URLs can proxy it with npx mcp-remote. No account is needed for the free tier. PRO detail requires a paid subscription and a key passed as _atom_api_key on each call. Self-hosting needs Node.js and the variables SUPABASE_URL, SUPABASE_SERVICE_ROLE_KEY, TRANSPORT and PORT.
Installation
In SourceWeft
- Open Attic Standard in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"atom-mcp-server": {
"type": "http",
"url": "https://mcp.atticstandard.com/mcp"
}
}
}README
Attic Standard MCP Server
The Global Price Benchmark for AI Inference, as a native tool for AI agents.
One number both sides trust.
Website · Methodology · MCP PRO
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.
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
Free and PRO
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
Claude Desktop, Cursor, Windsurf (config file)
If your client does not accept a remote URL, use the proxy:
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.
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: [email protected]
License
MIT
Source: README.md at commit 0762d2b
Tools
0Version history
1- v2.1.0LatestOct 5, 2026
More servers like Attic Standard
feedback.tools
tools.feedback
Lets an assistant read customer feedback metrics such as CSAT, NPS and CES, search responses, and review AI-generated themes.
Databutler Us Rates
io.github.physics-star-cat
Lets an assistant look up sourced US federal 2026 tax brackets, standard deductions, and payroll and retirement contribution limits.
Databutler Uk Vehicle Rules
io.github.physics-star-cat
Lets an assistant look up UK vehicle tax (VED) bands, the expensive-car supplement, EV rules and MOT fees from a sourced reference.