Mmcp.market

Harmny MCP server

by harmny.ai·ai.harmny/harmny·v1.0.0
No reviews yet

Harmny career frameworks, competencies, goals, org metrics and tasks as live context in MCP clients.

B70/100grade B
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
B70/100

full report

Adoption
New

Little public usage data yet

Reviews

Write one

Nobody has reviewed Harmny yet.

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

Harmny tools

Tool list not cached yet. `describe` through the gateway fetches it live.

Public scan report

scanner v0.1.9 · 2026-09-19 · same rubric, same numbers if you re-run it

1 low
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 222ms (auth required)20/20
  • –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
  • Auth qualityOAuth resource metadata advertised on 40115/15
  • Maintenanceno repository listed3/15
  • Maintainer identityverified namespace with website, no repo4/10

Findings (1)

  • lowNo source repository listedmaint.no-repo
Overall 70/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

Install directly

claude mcp add --transport http harmny https://harmny.ai/api/mcp
Add to Cursor

Harmny: common questions

Is Harmny MCP server safe?
Mostly: it is graded B (70/100). Read the Harmny safety report
How do I install Harmny?
It runs remotely at harmny.ai. Add it to Claude Code, Claude Desktop or Cursor with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Harmny need an API key?
No key to paste: it signs you in with OAuth when your client connects.
Is Harmny maintained?
The latest release is v1.0.0.
Is Harmny up?
100% of our last 6 checks got an answer. We check remote servers about four times a day.

More from harmny.ai →