ActionBox Human Input MCP Server

by actionbox Your server? Claim it

answering

ActionBox Human Input is answering right now. Last checked 3 min ago.

Human review for AI agents: ask through ActionBox and retrieve a typed decision before proceeding.

Uptime history 73 hours of history

73 hours agonow

100.0%

Uptime 24h

92 of 92 checks

—

Tools

hidden behind auth

619 ms

Response time

average over 24h

API key

Access

streamable-http

Nothing serious here today

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

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 3 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add human-input --transport http https://api.actionbox.cloud/mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "human-input": {
      "url": "https://api.actionbox.cloud/mcp"
    }
  }
}

~/.codex/config.toml

[mcp_servers.human-input]
url = "https://api.actionbox.cloud/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "human-input": {
      "url": "https://api.actionbox.cloud/mcp"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "human-input": {
      "url": "https://api.actionbox.cloud/mcp"
    }
  }
}

This endpoint answered with an authorization challenge. The server is running, but you need an API key from its owner to call it.

Endpoints

URL	Transport	State	Latency	Checked
https://api.actionbox.cloud/mcp	streamable-http	needs key	574 ms	3 min ago

Alternatives to ActionBox Human Input

same job, measured the same way

Phronesis Hermes

by phronesisintel

Decision-assurance for AI agents: an auditable action boundary + receipt before it acts.

answering

Qorami

by loicfontaine-max

Check an email before an AI agent sends it: send / ask a human / block. Detects prompt injection.

21 installs/wk local only

Robrain

by adelinamart

Self-hosted decision memory for AI coding agents; warns before re-proposing a rejected approach.

105 installs/wk local only

Vulnify

by vulnify

Ask Vulnify before an AI agent acts. Check, record, and read policy decisions.

981 installs/wk answering

Tently

by tently-team

Tently, the AI PR reviewer for GitHub: agents check team decisions before they write code.

356 installs/wk local only

Impact Preview

by agent-polis

Impact preview for AI agents - see what changes before any action executes.

95 installs/wk local only

Quirna

by quirna

Ask a human before your agent acts: approval requests decided on a phone.

37 installs/wk local only

flixconomy.ai: humans and Ari for agents

by flixconomy

Real humans for AI agents: ask a question or rent a human for a task. Prepaid in EUR.

16 tools answering

ActionBox Human Input — questions

Answers built from our own checks of this server.

Why is there no tool list for ActionBox Human Input?

The server answered our handshake with an authorization challenge, so it is running — but it will not describe its tools to an anonymous client. To see them you need to connect with your own credentials. We record it as alive, not as broken: 100.0% of checks in the last 24 hours got a reply.

Is ActionBox Human Input working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 619 ms. The bar chart above shows every period we have measured.

How do I connect ActionBox Human Input?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address. You will need your own key: it refuses anonymous clients.

Does ActionBox Human Input need an API key?

Yes. Every time we knock, ActionBox Human Input answers with an authorization challenge instead of its tool list — that is how we know it is running and gated rather than broken. Bring your own credentials and it will talk.

How fast is ActionBox Human Input?

It answers our handshake in 619 ms on average, which is faster than 17% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.