Monte-Neo strategy verifier MCP Server

The independent verifier for trading strategies written by AI agents and humans. Catch look-ahead bias, hidden trading costs and overfitting before a backtest reaches your money. It runs locally over stdio via the published package.

People who work with backtesting, algorithmic trading and quant and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-09-28 · ★ 8 · #46 OF 344 MAINTAINED FINANCE · VERIFIED 2026-09-30

MIT · Python servers · how we verify → /methodology

01 · Install Monte-Neo strategy verifier

Claude Code

claude mcp add neozork-monte-neo -- uvx monte-neo

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "neozork-monte-neo": {
      "command": "uvx",
      "args": [
        "monte-neo"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

pypi package monte-neo - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.NeoZorK is GitHub-verified and matches the repo owner

03 · What Monte-Neo strategy verifier can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

v0.44.0 · 2026-09-30

Added · Stops inside the bar for target weights. sl_pct, tp_pct and trail_pct now work in the target-weight engine · (fractional weights and universes), using each instrument's high and low. With weights in {-1, 0, 1}…

v0.43.2 · 2026-09-30

Security · Findings from a full security pass (Bandit over all of src, pip-audit over the whole lock file including dev · dependencies, secret scanning of the tree and history, review of every workflow). None touched…

v0.43.1 · 2026-09-30

Quality release after a full check of the product as a customer (clean install from PyPI on Python 3.11, 3.12 and 3.13, · every command, the MCP server on SDK 1.x and 2.x, the Action script, the Docker image, real…

04 · Who maintains Monte-Neo strategy verifier

Monte-Neo strategy verifier is maintained by neozork. It's the only MCP server we track from this author; the repo dates to Jan 2026.

05 · Facts

category
finance - ranked #46 of 344 actively-maintained finance servers as of 2026-09-30.
release cadence
10+ releases in the last 90 days (latest 2026-09-30)
registry
io.github.NeoZorK/monte-neo (active, first published 2026-09-26 · 29 versions)
packages
pypi:monte-neo

06 · Monte-Neo strategy verifier FAQ

What is Monte-Neo strategy verifier?

The independent verifier for trading strategies written by AI agents and humans. Catch look-ahead bias, hidden trading costs and overfitting before a backtest reaches your money. It runs locally over stdio via the published package.

Is Monte-Neo strategy verifier still maintained?

Yes - as of 2026-09-30, its last commit was 2026-09-28 and it shipped 10+ releases in the last 90 days. We re-verify nightly.

How do I install Monte-Neo strategy verifier?

Run `uvx monte-neo`. You can also paste the ready-made client config above.

Does Monte-Neo strategy verifier run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Monte-Neo strategy verifier