MCP.Market

Lockbox MCP server

online · 100% uptime
by lockbox.run·run.lockbox/lockbox·v0.1.0
No reviews yet

Send API keys and private files to someone else's agent, end-to-end encrypted.

A97/100grade A
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
A97/100

full report

Adoption
Growing

0 stars

Reviews

Write one

Nobody has reviewed Lockbox yet.

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

Lockbox tools

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

Public scan report

scanner v0.1.10 · 2026-10-14 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 174ms (auth required)20/20
  • –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
  • Auth qualityOAuth resource metadata advertised on 40115/15
  • Maintenancelast push 5 days ago15/15
  • Maintainer identitynamespace and repository owner differ; GitHub account older than a year; website matches verified namespace8/10
Overall 97/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Lockbox compares

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

Safety score
97/100
higher than 98% of 4,460 AI and agents servers
Uptime
100%
of our recent checks; the typical remote AI and agents server answers 100%
Response time
103 ms
faster than 86% of 2,331 AI and agents servers

Install Lockbox in Claude Code, Cursor or VS Code

claude mcp add --transport http lockbox https://lockbox.run/mcp
Add to Cursor

What the publisher says

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

Lockbox skills and plugin

Send API keys and private files to someone else's agent, end-to-end encrypted. lockbox.run

This repo holds the agent-facing parts of Lockbox: the lockbox skill and a plugin bundle for Claude Code, Codex and Cursor. The skill teaches your coding agent to use the lockbox CLI (npm i -g @opslane/lockbox) so keys go from one .env to another without being printed or pasted into chat.

Install

Any agent that reads skills (via skills.sh):

npx skills add opslane/lockbox-skills

Claude Code:

claude plugin marketplace add opslane/lockbox-skills
claude plugin install lockbox@opslane

Claude.ai and ChatGPT: add https://lockbox.run/mcp as a connector. The Lockbox panel opens in the chat.

Then install the CLI and sign in:

npm i -g @opslane/lockbox
lockbox login you@company.com

What's here

The CLI and the Lockbox server are not in this repo. Docs: lockbox.run/docs. Security questions: support@lockbox.run.

License

MIT, for the files in this repo. See LICENSE.

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

Lockbox: common questions

Is Lockbox MCP server safe?
Yes, by our scan: it is graded A (97/100). Read the Lockbox safety report
How do I install Lockbox?
It runs remotely at lockbox.run. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Lockbox need an API key?
No key to paste: it signs you in with OAuth when your client connects.
Is Lockbox maintained?
The last commit was 27 days ago (2026-10-08). The latest release is v0.1.0.
Is Lockbox up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of Lockbox?
Servers from other publishers that do the same job: Basic Memory MCP server, Openflowkit MCP server and Ausca MCP server.
How does Lockbox compare with other AI and agents MCP servers?
safety score 97/100 (higher than 98% of 4,460 AI and agents servers); uptime 100% (of our recent checks; the typical remote AI and agents server answers 100%); response time 103 ms (faster than 86% of 2,331 AI and agents servers). Full comparison.

Alternatives to Lockbox

Same job from other publishers: the closest match first, then the best rated.

  • Basic Memory
    Local-first knowledge management with bi-directional LLM sync via Markdown files.
    B
  • Openflowkit
    Architecture diagrams for your agent: draw on the live OpenFlowKit canvas or edit diagram files.
    A
  • Ausca
    Pay-per-call APIs and MCP services for agents, no accounts or keys, with verifiable receipts.
    A
  • ctxlint
    Lint AI agent context files (CLAUDE.md, AGENTS.md, etc.) against your actual codebase
    A