English Français العربية

Stochastly Desktop

Registre officiel Recherche et web

Local MCP access to Stochastly desktop nodes, diagnostics and research tools.

Code source Site web Documentation

Installation

Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).

PYPI package stochastly-mcp
Claude Code 
claude mcp add stochastly-desktop -e 'STOCHASTLY_MCP_SCRIPT=<STOCHASTLY_MCP_SCRIPT>' -- uvx stochastly-mcp==0.2.2
Configuration JSON (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "stochastly-desktop": {
            "command": "uvx",
            "args": [
                "stochastly-mcp==0.2.2"
            ],
            "env": {
                "STOCHASTLY_MCP_SCRIPT": "<STOCHASTLY_MCP_SCRIPT>"
            }
        }
    }
}

Variables d'environnement

  • STOCHASTLY_MCP_SCRIPT Optional path to the MCP client script supplied by the installed Stochastly app.

Documentation

Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.

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.

Questions fréquentes

Qu'est-ce que Stochastly Desktop ?

Local MCP access to Stochastly desktop nodes, diagnostics and research tools.

Comment installer Stochastly Desktop ?

Il s'exécute sur votre machine. Dans Claude Code : claude mcp add stochastly-desktop -e 'STOCHASTLY_MCP_SCRIPT=<STOCHASTLY_MCP_SCRIPT>' -- uvx stochastly-mcp==0.2.2. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.

Faut-il une clé API pour Stochastly Desktop ?

Son entrée au registre n'indique aucune clé ni secret obligatoire. Certaines fonctions peuvent tout de même demander un compte auprès du service auquel il se connecte.

Stochastly Desktop est-il open source ?

Oui. Son code est sur GitHub sous licence MIT.

Qui maintient Stochastly Desktop ?

Il est publié par Stochastly. AI.tn le référence sans le maintenir ni le recommander.

Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.