{
  "markdown": "# TimeWeaver MCP\n\n**Synthetic time-series test data, on demand, inside your AI client.** Generate realistic series with configurable trend, seasonality, noise, anomalies, and multiple correlated streams — perfect for testing dashboards, charts, monitoring/alerting, forecasting models, and anomaly detection. Output as JSON, CSV, or SQL.\n\nPart of the [fixturelab](https://github.com/FixtureForge) test-data tools. Its sibling [SeedWeaver](https://github.com/FixtureForge/seedweaver-mcp) does relational/database test data.\n\n## Why\n\nLLMs are unreliable at hand-generating coherent time-series — trends drift, \"seasonality\" doesn't actually repeat, and correlations between series are fake. TimeWeaver generates data with **verifiable statistical properties**: a linear trend really has the slope you asked for, a seasonal cycle really repeats at its period, two correlated series really hit the target correlation, and AR(1) noise really has the autocorrelation you set.\n\n## Install\n\n```\nnpx -y timeweaver-mcp\n```\n\nAdd to your MCP client config (e.g. Claude Desktop `claude_desktop_config.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"timeweaver\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"timeweaver-mcp\"]\n    }\n  }\n}\n```\n\nTo unlock Pro, add your license key:\n\n```json\n{\n  \"mcpServers\": {\n    \"timeweaver\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"timeweaver-mcp\"],\n      \"env\": { \"TIMEWEAVER_LICENSE\": \"YOUR-KEY-HERE\" }\n    }\n  }\n}\n```\n\n## Tools\n\n- **`generate_timeseries`** — generate data from a preset and/or explicit components (length, frequency, baseline, trend, seasonality, noise, anomalies, correlated series). Output JSON / CSV / SQL.\n- **`list_presets`** — list built-in presets: `ecommerce_sales`, `server_cpu`, `iot_temperature`, `website_traffic`, `stock_price`, `api_latency_ms`.\n\n## Examples\n\n> \"Generate 90 days of daily e-commerce sales using the ecommerce_sales preset.\"\n\n> \"Generate 3 correlated server CPU series over 500 minutes with correlation 0.8, as CSV.\"\n\n> \"Make an hourly temperature series with a daily cycle and a level shift on day 5, as SQL into a table called readings.\"\n\n## Free vs Pro\n\n| | Free | Pro |\n|---|---|---|\n| Points per series | 200 | up to 100,000 |\n| Series | 1 | up to many, correlated |\n| Trend | none / linear | + exponential, logistic |\n| Seasonality | 1 cycle | multiple cycles |\n| Noise | gaussian | + AR(1) autocorrelated |\n| Anomalies | – | spikes, level shifts, trend changes, dropouts |\n| Output | JSON | + CSV, SQL |\n| Deterministic seed | – | ✓ |\n\nPro: **$19/mo** or **$39 one-time** → https://fixtureforge.gumroad.com/l/timeweaver\n\n## License\n\nMIT (the server code). Pro features require a valid license key.\n",
  "bytes": 2680,
  "sha": "7a046acb40bc5ee0fe62efccf7a65e08d2c176824364978215d676c7d1bbb77e",
  "repo_slug": "fixtureforge/timeweaver-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_fixtureforge_timeweaver_mcp_d156106f/readme"
}