mcpField
S
Stochastly Desktop

Stochastly Desktop

Local
stochastly.comFinance0Updated 2w ago
RepositoryVisit website

About Stochastly Desktop

Stochastly Desktop is a local launcher connecting MCP clients to the server bundled with the Stochastly desktop app, for researchers using Atelier or Portfolio. It exposes a 29-tool manifest, while the app executes calls and checks licensing.

Key features

  1. 01Expose 29 tools and their input schemas
  2. 02Compose and backtest research graphs
  3. 03Run risk and adversarial checks
  4. 04Combine portfolios and export papers
  5. 05Check desktop-app licensing on each call

Use cases

  1. 01Browse Stochastly tools from an MCP client
  2. 02Backtest research graphs and check for risks
  3. 03Combine a portfolio and export a research paper

MCP support

The launcher connects MCP clients to the server shipped with the Stochastly desktop app over local stdio. Without the app, clients can inspect tool metadata, but calls return a structured notice that the app and required edition are needed.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "com-stochastly-desktop": {
      "command": "uvx",
      "args": [
        "stochastly-mcp"
      ],
      "env": {
        "STOCHASTLY_MCP_SCRIPT": "<STOCHASTLY_MCP_SCRIPT>"
      }
    }
  }
}
Run commanduvx stochastly-mcp
Environment variables to set
STOCHASTLY_MCP_SCRIPTOptional path to the MCP client script supplied by the installed Stochastly app.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypistochastly-mcp0.2.2

Tools

29

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
seedintegerNoRandom seed; the same seed gives the same answer.
n_bootintegerNoNumber of bootstrap resamples.
n_simsintegerNoNumber of simulations for the randomised controls.
run_idstringYesId of a finished run, from backtest_graph or backtest_status.

Details

From the project README

Stochastly MCP

This small public launcher connects an MCP client to the server shipped with the Stochastly desktop app. The app must be installed, running, and licensed for Atelier or Portfolio. The package contains no Stochastly engine code.

Install with pip install stochastly-mcp or run with uvx stochastly-mcp. To run this source instead of the PyPI release, install this directory with pip install ..

Configure a local stdio server with command stochastly-mcp and no arguments:

  • Claude Desktop: add "stochastly": {"command": "stochastly-mcp"} under mcpServers in claude_desktop_config.json.
  • Cursor: add the same entry under mcpServers in .cursor/mcp.json.
  • VS Code: add "stochastly": {"type": "stdio", "command": "stochastly-mcp"} under servers in .vscode/mcp.json.

The server exposes 29 tools, among them node_catalog, compose_graph, backtest_graph, red_flag_check, adversarial_check, portfolio_combine and export_paper. The installed app runs them and checks the licence on every call: portfolio_combine needs Portfolio, every other tool Atelier or Portfolio.

Without the app, the launcher lists the same 29 tools (names, descriptions, input schemas and annotations from stochastly_mcp_data/tools_manifest.json, generated from the app's server), so a client can see what the server offers. Each description then starts with a note that the desktop app is required, and every call to a listed tool returns a structured answer with ok: false, the edition needed and a link to request access. A name the server does not list returns the error Unknown tool, as the app's server does. The manifest is metadata only.

For a nonstandard installation, set STOCHASTLY_MCP_SCRIPT to the installed app's stochastly_mcp.py. This is a local path, not a network endpoint.

Links

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.