call-a-human-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SLACK_APP_TOKEN | No | Slack Socket Mode app token (xapp-...) | |
| SLACK_BOT_TOKEN | No | Slack Bot OAuth token (xoxb-...) | |
| SLACK_CHANNEL_ID | No | Slack channel ID to post into | |
| TELEGRAM_CHAT_ID | No | Telegram chat/group ID | |
| CALL_HUMAN_CHANNEL | No | Notification channel: cli, slack, or telegram | |
| CALL_HUMAN_TIMEOUT | No | Seconds to wait before auto-denying (default: 300) | |
| TELEGRAM_BOT_TOKEN | No | Telegram bot token from BotFather | |
| CALL_HUMAN_AUDIT_LOG | No | Path to JSONL audit log file |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ask_humanA | Ask the human a free-form question and wait for their text reply. Use this when you need information only a human can provide: a preference, a clarification, credentials, or a decision on an ambiguous situation. The tool blocks until the human replies or the timeout expires. |
| request_approvalA | Ask the human to approve or deny a proposed action before executing it. Call this before any irreversible or high-stakes action (deleting data, sending messages, modifying production systems, spending money, etc.). The tool blocks until the human approves/denies or the timeout expires. Returns {"approved": bool, "reason": str} where reason is the human's username or name if available. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: request_approval is a structured yes/no gate for high-stakes actions, while ask_human is an open-ended prompt for information or clarification. There is no realistic scenario where an agent would confuse which tool to call.
Both tool names follow the same verb_noun pattern with snake_case (request_approval, ask_human). The naming is short, predictable, and directly reflects each tool's action and target.
Two tools is slightly below the typical 3-15 range, but it is reasonable for a narrowly scoped human-in-the-loop server. Each tool covers a distinct and essential interaction mode, and adding more tools would likely be unnecessary.
The server's domain is human interaction, and the two primary needs—requesting approval and asking a free-form question—are both covered. There are no obvious dead ends or missing operations for the stated purpose.