Safe Mind

io.github.lewo-mediaPublished by GitHub account lewo-mediav0.1.2Updated Oct 24, 2026

Psychological risk assessments (GBU Psyche) via Safe Mind: surveys, departments, analytics.

VerifiedSTDIODesktop onlyData & AnalyticsBusiness & Commerce

Overview

AI-generated overview

Safe Mind MCP server that lets an assistant work with GBU Psyche psychological risk assessments: surveys, departments and aggregated analytics.

What you can do
  • Create and manage psychological risk assessment surveys, including start date, duration, employee counts and departments
  • Manage departments and organizational structure used in assessments
  • Retrieve analytics and evaluation results, returned only as aggregated figures
  • Register a new Safe Mind account and obtain an API key through the tools themselves
When to use it
Useful for German employers or HR and safety staff who run the legally required psychological risk assessment (GBU Psyche) and want an assistant to set up surveys, organize departments and pull aggregated results.
Requirements
Runs locally as an npm package (safe-mind-mcp) over stdio, typically launched with npx. Needs a Safe Mind account and an API key supplied via the SAFE_MIND_API_KEY environment variable, unless an account is created through the registration tools. Network access to the Safe Mind API.
Before you install
The API key (SAFE_MIND_API_KEY) is a live credential and should be kept out of shared configs. The tools can create surveys and register accounts, which changes data on the Safe Mind platform. Assessment data concerns employees' psychological strain, so check consent, data protection and the server-side anonymity filtering before use.

Installation

In SourceWeft

  1. Open Safe Mind in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Safe Mind Developer Tools

Official CLI and MCP server for Safe Mind - the platform for the legally required psychological risk assessment (Gefährdungsbeurteilung psychischer Belastung, GBU Psyche) in Germany.

PackagenpmPurpose
cli/safe-mindTerminal client for the Safe Mind Public API v1
mcp/safe-mind-mcpMCP server for AI assistants (Claude, ChatGPT, Gemini, Cursor, ...)

Quick start

bash
npm install -g safe-mindsafe-mind login --email [email protected] --password '...'safe-mind surveys create --start 2026-10-01 --weeks 4 --employees 220 \  --department "Produktion" --department "Verwaltung"

MCP (any MCP client):

json
{    "mcpServers": {        "safe-mind": {            "command": "npx",            "args": ["-y", "safe-mind-mcp"],            "env": { "SAFE_MIND_API_KEY": "sm_live_..." }        }    }}

Documentation

  • API reference and examples: https://www.safe-mind.de/developers
  • Anonymity: analytics endpoints only return aggregated results; groups below the minimum group size are filtered server-side.

License

MIT

Source: README.md at commit f034ac1

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

2
  1. v0.1.2LatestOct 18, 2026
  2. v0.1.1Sep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts