mcpbeat Sign in

Stochastly Desktop MCP Server

by stochastly Your server? Claim it
local only

Stochastly Desktop runs on your own machine — the client starts it, so there is no endpoint to ping. 205 installs a week from pypi. Last commit 16 Oct 2026.

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

Installs per day peak 1 046 · avg 73 · -55% w/w
a month agotoday
205
Installs / week
pypi · stochastly-mcp
0
Stars
0 open issues
16 Oct 2026
Last commit
from GitHub
MIT
License
Python

What changed 1

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 16 October 2026. No other catalogue keeps this.

16 Oct the owner changed

Nothing serious here today

Today is the operative word: we check Stochastly Desktop every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add desktop -- uvx stochastly-mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "desktop": {
      "command": "uvx",
      "args": [
        "stochastly-mcp"
      ]
    }
  }
}
~/.codex/config.toml
[mcp_servers.desktop]
command = "uvx"
args = ["stochastly-mcp"]
.cursor/mcp.json
{
  "mcpServers": {
    "desktop": {
      "command": "uvx",
      "args": [
        "stochastly-mcp"
      ]
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "desktop": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "stochastly-mcp"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: STOCHASTLY_MCP_SCRIPT (Optional path to the MCP client script supplied by the installed Stochastly app).

Alternatives to Stochastly Desktop

same job, measured the same way
Obsidian Vault MCP Server
by oleksandrkucherenko

Access Obsidian vaults via Local REST API - read, search, and interact with notes

49 installs/wk local only
Netexpert MCP
by omodaka9375

Cross-platform local-network diagnostics & security-posture MCP server — 31 tools.

843 installs/wk local only
MCP Chainladder
by datalattice

Actuarial chain-ladder reserving: IBNR, Mack stochastic stats, and assumption diagnostics.

114 installs/wk local only
Docs
by empryo

Search and read Empryo's documentation. Read-only, no auth, no local access.

4 tools answering
Grandpa's AI
by wescorp

Search Grandpa's AI research on age reversal, robotics, AI, and space — 5 read-only MCP tools.

5 tools answering
Bunpro MCP Server
by alexxanddr

Read-only access to Bunpro profile, reviews, study statistics, vocabulary, and search.

375 installs/wk local only
Tomcat
by sarath-451

Local MCP server for AI-assisted Apache Tomcat management and diagnostics

14 installs/wk local only
OfficeIMO Document Tools
by evotecit

Inspect, search, fetch, and convert local documents and mail stores with bounded access.

local only

Stochastly Desktop — questions

Answers built from our own checks of this server.

Why is there no uptime for Stochastly Desktop?
Stochastly Desktop runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package stochastly-mcp was installed 205 times last week.
How do I connect Stochastly Desktop?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls stochastly-mcp straight from pypi; nothing to host, nothing to sign up for.
How many people use Stochastly Desktop?
The pypi package stochastly-mcp was installed 205 times in the last week. Week over week that is -55%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Stochastly Desktop open source?
Yes — it is published under the MIT licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.