call-a-human-mcpSAFE
MCP server that gives any AI phone a friend options : ask a human or request approval via Slack or macOS dialogs before taking irreversible actions.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Your AI agent is about to delete the production database. Do you want it to just go ahead?
call-a-human-mcp is an MCP server that gives any AI agent a pause button — it can ask you a question or request your approval before taking action, and it won't proceed until you respond.
Claude: request_approval("Drop table users_backup — 2.1GB, irreversible")
Slack: ⚠️ AI Agent requesting approval
Action: Drop table users_backup — 2.1GB, irreversible
[Approve] [Deny]
← you click Deny
Claude: "Understood, skipping the deletion."Works with Claude Desktop, Cursor, Windsurf, and any MCP-compatible agent. Notifications via Slack, Telegram, or macOS system dialogs.
Two tools:
The tool call blocks until you respond (or the timeout expires).
More: Use cases · Slack permissions · Troubleshooting · Discord
5-minute quick start
Pick the path that matches your setup:
Option A: CLI (macOS dialogs)
No Slack or Telegram account needed. Works with Claude Desktop on macOS via native system dialogs.
1. Clone and install:
git clone https://github.com/nishantmodak/call-a-human-mcp cd call-a-human-mcp uv sync
2. Verify it works:
CALL_HUMAN_
717a7afda8abOBSERVED · 2026-10-10Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add call-a-human-mcp --env SLACK_APP_TOKEN=${SLACK_APP_TOKEN} --env SLACK_BOT_TOKEN=${SLACK_BOT_TOKEN} --env TELEGRAM_BOT_TOKEN=${TELEGRAM_BOT_TOKEN} -- uvx call-a-human-mcp{
"mcpServers": {
"call-a-human-mcp": {
"command": "uvx",
"args": [
"call-a-human-mcp"
],
"env": {
"SLACK_APP_TOKEN": "${SLACK_APP_TOKEN}",
"SLACK_BOT_TOKEN": "${SLACK_BOT_TOKEN}",
"TELEGRAM_BOT_TOKEN": "${TELEGRAM_BOT_TOKEN}"
}
}
}
}Exposed tools (2)
2 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
ask_human | read | Ask the human a free-form question and wait for their text reply. |
request_approval | read | Ask the human to approve or deny a proposed action before executing it. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (4 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- found
Findings (2)
"SLACK_BOT_TOKEN": "xoxb-your-bot-token",
> **Full permissions reference:** [docs/slack-permissions.md](docs/slack-permissions.md)
Gates applied: no_behavioural_pass.
717a7afda8abfull audit observations/trust-audit/mcp-server/nishantmodak__call-a-human-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-10 | 717a7afda8ab | SAFE | B | 89 | first audit |
Questions
What is the call-a-human-mcp MCP server?
MCP server that gives any AI phone a friend options : ask a human or request approval via Slack or macOS dialogs before taking irreversible actions.
What tools does call-a-human-mcp expose?
2 in total: 2 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is call-a-human-mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does call-a-human-mcp need?
It reads SLACK_APP_TOKEN, SLACK_BOT_TOKEN and TELEGRAM_BOT_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does call-a-human-mcp run?
It speaks sse and stdio, so it runs as a local process your client starts. It is published on PyPI as call-a-human-mcp.
How current is this page?
The grade is for one exact copy of the source (717a7afda8ab), read on 2026-10-10. The repository is watched and re-audited when it changes.