MCP.Market

Safe Mind MCP server

by lewo-media·io.github.lewo-media/safe-mind·v0.1.2

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

A85/100grade A
What users say
No reviews yet
Be the first
Safety scan
A85/100

full report

Adoption
Growing

0 stars59 downloads/wk

Reviews

Write one

Nobody has reviewed Safe Mind yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Safe Mind tools (12, 5 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • safe_mind_create_departmentwrite action

    Create one department/area (Tätigkeitsbereich) of the company and return its id and name. Idempotent: if an area with exactly this name exists, that one is returned and nothing is duplicated. Not needed before safe_mind_create_survey, which creates missing areas by name itself. Areas cannot be renamed or deleted through the API. …

  • safe_mind_create_locationwrite action

    Create one location (Standort) of the company and return its id and name. Use it for companies with several sites whose results should be compared; single-site companies do not need locations. Idempotent: if a location with exactly this name exists, that one is returned and nothing is duplicated. Not needed before safe_mind_create_survey, which creates missing locations by name itself. Locations c

  • safe_mind_create_surveywrite action

    Create a survey draft for the psychological risk assessment and return its id, status "draft", dates, participation link and an edit link. Departments and locations are passed by name; missing ones are created, existing ones reused. The draft is not visible to employees yet: the account owner reviews it and starts it in the Safe Mind app via the edit link (payment happens there). Drafts cannot be

  • safe_mind_get_analytics

    Aggregated results of one survey: respondent count, anonymity threshold and the average score per category (scale -1 to +1, higher is better; the Safe Mind app shows the same values times 10). With groupBy the averages are split by department, location, age group or gender. Groups below the anonymity threshold are never returned, only counted in suppressedGroupCount, and individual answers are nev

  • safe_mind_get_api_key

    Log in with email and password of a verified Safe Mind account and create an API key. Call this before any company, survey or analytics tool unless SAFE_MIND_API_KEY is already set. The key is kept in memory for this session only and also returned, so the user can store it as SAFE_MIND_API_KEY for later sessions. Fails if the email is not verified yet (use safe_mind_verify_email) or the credential

  • safe_mind_get_survey

    Show one survey of the company: title, status (draft, active, closed, archived), start and end date, participant limit, anonymity threshold, the participation link for employees and the edit link for the account owner. Read-only. Use it to check a single survey or fetch its links; for an overview of all surveys use safe_mind_list_surveys, for results use safe_mind_get_analytics. Returns a not-foun

  • safe_mind_list_departments

    List the departments/areas (Tätigkeitsbereiche) of the company as id and name. Surveys segment results by these areas. Read-only. Call it before safe_mind_create_department or safe_mind_create_survey to reuse existing names exactly. …

  • safe_mind_list_locations

    List the locations (Standorte) of the company as id and name. Locations are an optional second segmentation next to departments, useful for companies with several sites. Read-only. Call it before safe_mind_create_location to reuse existing names exactly. …

  • safe_mind_list_surveys

    List all surveys of the company, newest first, each with id, title, status (draft, active, closed, archived), start and end date, participant limit, anonymity threshold, participation link and edit link. Read-only. Use it to find the surveyId needed by safe_mind_get_survey and safe_mind_get_analytics. …

  • safe_mind_me

    Show who is connected: name and email of the account and the company (id, name, employee count) that all other tools act on. Use it to check the API key works or to confirm the company before creating anything. Read-only. …

  • safe_mind_registerwrite action

    Create a new Safe Mind account together with its company. Safe Mind runs the legally required psychological risk assessment (Gefährdungsbeurteilung psychischer Belastung, GBU Psyche) for German companies. Use this only when the user has no account yet; for an existing account go straight to safe_mind_get_api_key. No API key needed. Sends a 6-digit verification code to the email address and returns

  • safe_mind_verify_emailwrite action

    Confirm a newly registered account with the 6-digit code from the verification email sent by safe_mind_register. No API key needed. Returns a confirmation message; afterwards call safe_mind_get_api_key. A wrong or expired code returns an error without revealing whether the account exists.

Public scan report

scanner v0.1.10 · 2026-10-30 · same rubric, same numbers if you re-run it

no findings
  • Code scan5 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 13 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10
Overall 85/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Safe Mind compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
85/100
higher than 70% of 48,243 servers
Tools
12
the typical server has 7
Tools that change things
42%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
59
more than 47% of 12,306 servers with a package

What its tools let an agent do: 7 read · 5 change

Release history: 2 versions in the registry since 2026-08-28, latest 2026-10-18, typically one every 50 days.

Install Safe Mind in Claude Code, Cursor or VS Code

Runs npx -y safe-mind-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add safe-mind -- npx -y safe-mind-mcp
Add to Cursor

What the publisher says

From the Safe Mind repository's README, as published. We do not edit it. Read it on GitHub

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.

Quick start

npm install -g safe-mind
safe-mind login --email you@example.com --password '...'
safe-mind surveys create --start 2026-10-01 --weeks 4 --employees 220 \
  --department "Produktion" --department "Verwaltung"

MCP (any MCP client):

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

Documentation

minimum group size are filtered server-side.

  • API reference and examples: https://www.safe-mind.de/developers
  • Anonymity: analytics endpoints only return aggregated results; groups below the

License

MIT

Nothing above is checked by us. What we check is on the safety report.

Safe Mind: common questions

Is Safe Mind MCP server safe?
Yes, by our scan: it is graded A (85/100). Read the Safe Mind safety report
How do I install Safe Mind?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Safe Mind need an API key?
Yes. The registry entry asks for SAFE_MIND_API_KEY.
Is Safe Mind maintained?
The last commit was 19 days ago (2026-10-18). The latest release is v0.1.2.
How does Safe Mind compare with other MCP servers?
safety score 85/100 (higher than 70% of 48,243 servers); tools 12 (the typical server has 7); tools that change things 42% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.