{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_pavt8fwq8sum","handle":"backtester-mcp","url":"https://wellknown.network/agents/backtester-mcp","links":{"self":"https://wellknown.network/agents/backtester-mcp/record.json","html":"https://wellknown.network/agents/backtester-mcp","markdown":"https://wellknown.network/agents/backtester-mcp/record.md","api":"https://wellknown.network/api/v1/agents/backtester-mcp","status":"https://wellknown.network/api/v1/agents/backtester-mcp/status","claim":"https://wellknown.network/agents/backtester-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/backtester-mcp/claim.json","badge":"https://wellknown.network/agents/backtester-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:backtester-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"backtester-mcp","summary":"Local-first backtesting engine with built-in overfitting detection","description":"# backtester-mcp\n\nLocal-first backtesting engine with built-in overfitting detection. Asset-class agnostic. MCP-native.\n\n![License](https://img.shields.io/badge/license-Apache%202.0-blue)\n![Python](https://img.shields.io/badge/python-3.10%2B-green)\n![Tests](https://github.com/bcosm/backtester-mcp/actions/workflows/test.yml/badge.svg)\n\n## The Problem\n\nQuantConnect requires Docker + C#, supports 9 hardcoded asset classes, and ships zero statistical robustness tools. Solo quants and AI agents need something that's `pip install`, works on any price series (equities, crypto, prediction markets) and tells you if your strategy is overfit before you risk real money.\n\nbacktester-mcp is a validation layer for AI-generated trading strategies. Vectorized execution on NumPy + Numba, automatic overfitting detection via PBO, walk-forward validation, execution scenario analysis, and a native MCP server so AI agents can validate strategies directly.\n\n## Quick Start\n\n```bash\npip install backtester-mcp\n```\n\nRuns on synthetic data out of the box, no datasets to download:\n\n```python\nimport numpy as np\nfrom backtester_mcp import backtest\n\n# synthetic price series, reproducible\nrng = np.random.default_rng(0)\nprices = np.cumprod(1 + rng.normal(0, 0.01, 2000))\n\n# moving average crossover signal\nfast = np.convolve(prices, np.ones(10) / 10, mode=\"full\")[:len(prices)]\nslow = np.convolve(prices, np.ones(50) / 50, mode=\"full\")[:len(prices)]\nsignals = np.where(fast > slow, 1.0, -1.0)\nsignals[:50] = 0\n\nresult = backtest(prices, signals)\nprint(result.metrics)\n```\n\nTo run against a real dataset, clone the repo (`git clone https://github.com/bcosm/backtester-mcp`) and point `load()` at anything in `datasets/` or your own CSV/Parquet file.\n\n## Key Features\n\n| Feature | QuantConnect | backtester-mcp |\n|---|---|---|\n| Setup | Docker + .NET | `pip install` |\n| Engine | C# (Python wrapper) | Pure Python + NumPy + Numba |\n| Asset classes | 9 hardcoded | Any price series |\n| Overfitting detection | None | …","publisher":null,"homepage":null,"repository":null,"version":"0.1.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:backtester-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"finance.markets","name":"Markets & Trading","confidence":0.791,"provenance":"derived"},{"slug":"dev.version-control","name":"Version Control","confidence":0.745,"provenance":"derived"}],"categories":["dev","finance"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"backtester-mcp","registry":"pypi","observedAt":"2026-09-09T10:29:17.450Z","publishedAt":"2026-04-14T15:55:59.338446Z","latestVersion":"0.1.0"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"backtester-mcp","url":"https://pypi.org/project/backtester-mcp/","firstSeenAt":"2026-09-09T10:26:28.024Z","fetchedAt":"2026-09-09T10:26:28.024Z","normalizedAt":"2026-09-09T10:26:28.024Z"}]},"firstSeenAt":"2026-09-09T10:26:28.024Z","updatedAt":"2026-09-09T10:29:17.450Z"}