Ask Human adds human-in-the-loop responses to AI, preventing errors on sensitive tasks like passwords and API endpoints.
by Add new capabilities to Claude beyond text generation
Example: Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example: Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example: Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Time estimate: 15-60 minutes depending on server complexity
Prerequisites
Pulumi Infrastructure as Code
Pulumi Infrastructure as Code enables infra as a code operations, with tools for querying resources and running CLI comm
WhatsApp MCP
Send and receive WhatsApp messages directly from Claude and other AI assistants. Search conversations, manage contacts,
MCP Use
The fullstack MCP framework for developing MCP apps for ChatGPT, Claude, and building MCP servers for AI agents. Connect
Genkit
Genkit — consume MCP resources or expose powerful Genkit tools as a server for streamlined development and integration.
Screenshot Capture
Capture screenshots across macOS, Windows, and Linux using advanced screen capture and recording software for analysis,
I recommend Ask Human for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
Ask Human reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
We evaluated Ask Human against two servers with overlapping tools; this profile had the clearer scope statement.
Ask Human is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
We evaluated Ask Human against two servers with overlapping tools; this profile had the clearer scope statement.
I recommend Ask Human for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
I recommend Ask Human for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
Ask Human is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
Strong directory entry: Ask Human surfaces stars and publisher context so we could sanity-check maintenance before adopting.
Strong directory entry: Ask Human surfaces stars and publisher context so we could sanity-check maintenance before adopting.
showing 1-10 of 46
Share your MCP server with the developer community
Select a client to integrate this server.
Claude Desktop configuration
{
"mcpServers": {
"ask-human": {
"command": "ask-human-mcp",
"args": [
"--timeout",
"900"
]
}
}
}Creates a markdown file-based workflow where AI can escalate questions to humans instead of making incorrect assumptions or hallucinating answers.
Ask Human is a community-built MCP server published by masony817 that provides AI assistants with tools and capabilities via the Model Context Protocol. Ask Human adds human-in-the-loop responses to AI, preventing errors on sensitive tasks like passwords and API endpoints. It is categorized under productivity, developer tools.
You can install Ask Human in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
stop your ai from hallucinating. gives it an escape route when confused instead of false confidence.
ai blurts out an endpoint that never existed
the agent makes assumptions that are simply not true and has false confidence
repeat x100 errors and your day is spent debugging false confidence and issues when you could simply ask a question
an mcp server that lets the agent raise its hand instead of hallucinating. feels like mentoring a sharp intern who actually asks before guessing.
agent → ask_human()
⬇
question lands in ask_human.md
⬇
you swap "PENDING" for the answer
⬇
agent keeps coding
### Q8c4f1e2a
ts: 2025-01-15 14:30
q: which auth endpoint do we use?
ctx: building login form in auth.js
answer: PENDING
you drop:
answer: POST /api/v2/auth/login
boom. flow continues and hopefully the issues are solved.
pip install ask-human-mcp
ask-human-mcp
.cursor/mcp.json:
{
"mcpServers": {
"ask-human": { "command": "ask-human-mcp" }
}
}
restart cursor and vibe.
ask_human(question, context)ask_human.md with unique IDthe ai receives your answer and keeps coding!
ask-human-mcp --help
ask-human-mcp --port 3000 --host 0.0.0.0 # http mode
ask-human-mcp --timeout 1800 # 30min timeout
ask-human-mcp --file custom_qa.md # custom q&a file
ask-human-mcp --max-pending 50 # max concurrent questions
ask-human-mcp --max-question-length 5000 # max question size
ask-human-mcp --rotation-size 10485760 # rotate file at 10mb
cursor (local):
{
"mcpServers": {
"ask-human": {
"command": "ask-human-mcp",
"args": ["--timeout", "900"]
}
}
}
cursor (http):
{
"mcpServers": {
"ask-human": {
"url": "http://localhost:3000/sse"
}
}
}
claude desktop:
{
"mcpServers": {
"ask-human": {
"command": "ask-human-mcp"
}
}
}
| thing | default | what it does |
|---|---|---|
| question length | 10kb | max characters per question |
| context length | 50kb | max characters per context |
| pending questions | 100 | max concurrent questions |
| file size | 100mb | max ask file size |
| rotation size | 50mb | size at which files are archived |
ask the human a question and wait for response.
answer = await ask_human(
"what database should i use for this project?",
"building a chat app with 1000+ concurrent users"
)
list_pending_questions() → get questions waiting for answersget_qa_stats() → get stats about the q&a sessiongit clone https://github.com/masonyarbrough/ask-human-mcp.git
cd ask-human-mcp
pip install -e ".[dev]"
ask-human-mcp
pytest tests/ -v
black ask_human_mcp tests
ruff check ask_human_mcp tests
mypy ask_human_mcp
would love any contributors
use the github issue tracker to report bugs or request features.
you can also just email me: mason@kallro.com
include:
see CHANGELOG.md for version history.
mit license - see LICENSE file for details.
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.