Claude MarketplacesSubmit
jacob-j-thomas avatar

User Prompt

jacob-j-thomas/user-context-retrieval-mcp-server

This server gives AI agents a way to interrupt their workflow and ask you clarifying questions when they hit ambiguity or need a design decision. It exposes a single tool, user_prompt, that takes a reason string and an array of questions. When called, it spawns a PowerShell terminal window on your machine with the agent's questions displayed as a numbered list. You type your answers, they get formatted as Q&A pairs and returned to the agent, and it continues executing with your input. Built in .NET 8, ships as standalone executables or a dotnet global tool. Useful for long running agentic tasks where guessing wrong is worse than pausing for thirty seconds of human feedback.

tool
1
transport
STDIO
last updated
Feb 11, 2026
View on GitHub

Tools

1 tools

Public tool metadata for what this MCP can expose to an agent.

user_promptAsks the user clarifying questions mid-task via a pop-up terminal window and returns their answers to the agent.

Asks the user clarifying questions mid-task via a pop-up terminal window and returns their answers to the agent.

No parameter schema in public metadata yet.

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Readme

User Prompt MCP Server

.NET License

mcp-name: io.github.Jacob-J-Thomas/user-prompt

A Model Context Protocol (MCP) server that gives AI agents the ability to ask users clarifying questions mid-task via a pop-up terminal window. Built with .NET 8 and C#.

The Problem

Long-running AI agents (like Claude Code, IDE copilots, or custom agentic workflows) often encounter situations where they need human input — ambiguous requirements, unexpected errors, or design decisions that could go multiple ways. Without a mechanism to ask, the agent either guesses (often incorrectly) or stops entirely and waits for the user to notice.

The Solution

View the full README on GitHub

Details

Repository
github.com/jacob-j-thomas/user-context-retrieval-mcp-server
Categories
AI & LLM Tools, Developer Tools
Package
UserPrompt
Transport
STDIO
Registry
MCP registry, active

Related AI & LLM Tools MCP servers

View all
1kurovu146 avatarMemory Ftskurovu146/claude-memory-mcpLong-term memory for Claude Code with SQLite FTS5 search and BM25 ranking0stars
2mdfifty50-boop avatarAgent Guardmdfifty50-boop/agent-guard-mcpConstitutional guardrails and loop detection for AI agents0stars
3mdfifty50-boop avatarAgent Securitymdfifty50-boop/agent-security-mcpSecurity scanning and threat detection for AI agents0stars
4qmediat avatarGemini Code Context Mcpqmediat/gemini-code-context-mcpCodebase Q&A for Claude Code through Gemini's 1M-token window, with workspace scans and caching.0stars
5arben-adm avatarSequential Thinking Working Notesarben-adm/mcp-sequential-thinkingLocal working notes, decisions, evidence and resumable sessions with SQLite persistence.960stars
6varun29ankus avatarShodh Memoryvarun29ankus/shodh-memoryCognitive memory for AI agents — semantic search, Hebbian learning, knowledge graphs.217stars