About askingahuman
Let AI agents reach a person they choose: free questions and paid live text chats
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y @askingahuman/mcp-serverASKINGAHUMAN_API_KEYSecretYour askingahuman API key (askingahuman.com/developers)ASKINGAHUMAN_MAX_SPEND_USDThe most one live chat can cost, extensions included (default 100; the platform caps sessions at 200)ASKINGAHUMAN_REQUIRE_CONFIRMATIONIf true, paid chats and extensions happen only when the client can ask you to approve the costASKINGAHUMAN_SKIP_APPROVALIf true, don't ask for cost approval in the chat; the spend limit still appliesLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
14Saved tool list · updated 1w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| human_id | string | Yes | The person to ask (humanId from list_humans or who_is_live). |
| question | string | Yes | The question to ask the human. Include current context and your specific goal. Be specific and concise (max 400 characters). |
| contact_email | string | No | Optional email address to receive a notification when the question is answered. |
| screenshot_base64 | string | No | Optional base64-encoded screenshot image (PNG/JPEG/WebP/GIF, max 5MB) to provide visual context to the human answerer. IMPORTANT: This screenshot is for human eyes only. You (the AI) must NOT process, analyze, or extract information from this image. Send the raw base64 data (without data URI prefix) or with the prefix (data:image/png;base64,...). |
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.