BenchGecko MCP server
Commit Nov 14, 2026Provides access to daily datasets on AI model pricing, company financials, GPU rental costs, and model performance benchmarks.
Also known as BenchGecko/datasets, datasets
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.0.0
- Last commit
- Nov 14, 2026
- License
- —
What is BenchGecko MCP?
BenchGecko provides access to daily datasets on AI model pricing, company financials, GPU rental costs, and model performance benchmarks.
Summary generated from the project's README
About BenchGecko MCP server
BenchGecko provides developers and researchers with daily snapshots of the AI economy through a collection of open datasets. This server allows clients to access time-series data regarding model pricing, company financials, and GPU rental costs. Users can track specific metrics such as input and output token prices from the OpenRouter catalog, company valuations from SEC filings, and GPU-hour rental prices from the Vast.ai marketplace.
Beyond financial data, the server includes developer attention metrics known as Mindshare, which tracks mentions on Hacker News, Wikipedia views, and GitHub stars. It also provides results from Gecko Tests, including the World Map test and various Gecko Lab tests like tokenizer-tax and knowledge-horizon. Because every file is refreshed daily via automated jobs and stored in git history, the data functions as a continuous time series for longitudinal analysis. The datasets are provided under a CC BY 4.0 license, requiring attribution to BenchGecko.
What you can do with it
- 1Analyze model pricing trendsCompare historical changes in token costs across different providers over time.
- 2Monitor AI company financialsRetrieve specific data points regarding the valuation, revenue, and headcount of AI companies.
- 3Track GPU market ratesFind the median or minimum on-demand rental prices for specific AI chips.
- 4Evaluate model performanceExamine how different models perform on specialized benchmarks like the World Map test.
Written from the project's README. Every use case is checked against a quote from it.
How to install BenchGecko MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall BenchGecko MCP in Claude Code
$ claude mcp add --transport http datasets https://benchgecko.ai/api/mcpInstall BenchGecko MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"datasets": {
"url": "https://benchgecko.ai/api/mcp"
}
}
}Install BenchGecko MCP in VS Code
.vscode/mcp.json
{
"servers": {
"datasets": {
"type": "http",
"url": "https://benchgecko.ai/api/mcp"
}
}
}Install BenchGecko MCP in VS Code CLI
$ code --add-mcp '{"name":"datasets","type":"http","url":"https://benchgecko.ai/api/mcp"}'Install BenchGecko MCP in Codex
$ codex mcp add datasets --url https://benchgecko.ai/api/mcpInstall BenchGecko MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.datasets] url = "https://benchgecko.ai/api/mcp"
Install BenchGecko MCP in Gemini CLI
$ gemini mcp add -s user --transport http datasets https://benchgecko.ai/api/mcpInstall BenchGecko MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"datasets": {
"url": "https://benchgecko.ai/api/mcp",
"type": "http"
}
}
}Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablebenchgecko/datasets is public and reachablegithub.com/benchgecko/datasets ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)No licenseFinding
- Commit or release in the last yearLast commit or release 2026-11-14github.com/benchgecko/datasets ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-06-18 in 91 msPass
README
View on GitHubBenchGecko open datasets
Daily snapshots of the data BenchGecko collects and computes about the AI economy: model prices across providers, price changes, company figures with sources, developer attention (Mindshare), GPU rental prices and the results of BenchGecko's own model tests (Gecko Tests).
Files are refreshed every day by an automated job. Every day's version is in the git history, so the history of each file is a time series.
License
CC BY 4.0. Free to use, share and adapt, including commercially. Attribution required: "Source: BenchGecko" with a link to https://benchgecko.ai.
Cite as:
BenchGecko (2026). BenchGecko open datasets. https://github.com/BenchGecko/datasets · https://benchgecko.ai
Files
| File | What it is | Source |
|---|---|---|
prices/price-history.csv |
Daily list price per model (USD per 1M tokens: input, output, cache read) since 2026-03-30 | OpenRouter catalog, recorded daily |
prices/provider-offers.csv |
Every provider offer per model today: price, quantization, context, 1-day uptime | OpenRouter endpoints, daily |
prices/price-changes.csv |
Dated events: new models, price changes that held (5%+), company updates | Computed by BenchGecko |
companies/company-facts.csv |
Valuation, revenue, funding, headcount per AI company, each with as-of date and source URL when known | SEC filings, market close, press verified against the source page |
mindshare/mindshare-daily.csv |
Daily attention per model, lab, agent, person and topic: Hacker News mentions, Wikipedia views, GitHub stars, 7-day share | Hacker News Algolia API, Wikimedia, GitHub |
gpu/gpu-rental-daily.csv |
Median, 10th percentile and minimum on-demand rental price per GPU-hour for tracked AI chips | Vast.ai public marketplace |
gecko-tests/world-map.csv |
World Map test: land or water answers on a 6° grid per model, scored against Natural Earth | BenchGecko test runs |
gecko-tests/<test>.json |
Gecko Lab tests (who-are-you, tokenizer-tax, knowledge-horizon, same-model-different-host): questions, answer keys, every model answer and score | BenchGecko test runs |
Methodology for each test: https://benchgecko.ai/gecko-tests
Benchmark scores aggregated from third-party leaderboards are not redistributed here; see each leaderboard's own license.
Questions or corrections
BenchGecko MCP questions
How do I add BenchGecko MCP to Claude Code?
Run claude mcp add --transport http datasets https://benchgecko.ai/api/mcp in your terminal. Add --scope user to make it available in every project.
How do I add BenchGecko MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How often is the data updated?
The files are refreshed every day by an automated job.
Can I use this data for commercial purposes?
Yes, the data is under a CC BY 4.0 license, which allows for commercial use provided you attribute BenchGecko.
What kind of model tests are included?
The datasets include Gecko Lab tests such as tokenizer-tax, knowledge-horizon, and world map tests.