MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
MCP server that catches fake backtests before you trust them: deflated Sharpe ratio, backtest overfitting (CSCV/PBO), data-snooping tests (White's Reality Check, Hansen's SPA), lookahead checks and pipeline placebos. 20 tools for Claude, Cursor and any MCP client; on npm, the MCP Registry and hosted at canlicapital.com/mcp.
MIT ★ 1 -
backtest-auditoractive
Backtest Auditor: a red-team lint for trading strategies (static lookahead/bias lint, Deflated Sharpe, cost and stability audit), as a Python library and an MCP server.
pypi Apache-2.0 -
Independent verifier for trading strategies written by AI agents and humans: catches look-ahead bias, hidden costs and overfitting. MCP server, CLI, GitHub Action, signed certificates.
pypi MIT ★ 10 -
An LLM auditor that tries to kill trading strategies: look-ahead, cost, random-entry and multiple-testing checks, measured on a 90-case bench of planted flaws and real edges. CLI + MCP server + Claude Code skill.