
English | ηΉι«δΈζ
idea-reality-mcp
How to check if someone already built your app idea β automatically.
idea-reality-mcp is an MCP server that scans GitHub, npm, PyPI, Hacker News, Product Hunt, and Stack Overflow to check if your startup idea already exists. It returns a 0β100 reality score with evidence, trend detection, and pivot suggestions β so your AI agent can decide whether to build, pivot, or kill the idea before writing any code.
When to use this: You're about to start a new project and want to know if similar tools already exist, how competitive the space is, and whether the market is growing or declining.
How it works
-
Describe your idea in plain English β e.g. "a CLI tool that converts Figma designs to React components"
-
idea_check scans 6 databases in parallel (GitHub repos + stars, Hacker News discussions, npm/PyPI packages, Product Hunt launches, Stack Overflow questions)
-
Get a 0β100 reality score with trend direction (accelerating/stable/declining), top competitors, and AI-generated pivot suggestions
What you get
You: "AI code review tool"
idea_check β
βββ reality_signal: 92/100
βββ trend: accelerating β
βββ market_momentum: 73/100
βββ GitHub repos: 847 (45% created in last 6 months)
βββ Top competitor: reviewdog (9,094 β)
βββ npm packages: 56
βββ HN discussions: 254 (trending up)
βββ Verdict: HIGH β market is accelerating, find a niche fast
One score. Six sources. Trend detection. Your agent decides what to do next.
Try it in your browser β no install
Why not just Google it?
Your AI agent never Googles anything before it starts building. idea_check runs inside your agent β it triggers automatically whether you remember or not.
Google ChatGPT idea-reality-mcp Who runs it You, manually You, manually Your agent, automatically Output 10 blue links "Sounds promising!" Score 0-100 + evidence Sources Web pages None (LLM) GitHub + HN + npm + PyPI + PH + SO Price Free Paywall Free & open-source (MIT)
Modes
Mode Sources Use case quick (default) GitHub + HN Fast sanity check, < 3 seconds deep GitHub + HN + npm + PyPI + Product Hunt + Stack Overflow Full competitive scan
Scoring weights
Source Quick Deep GitHub repos 60% 22% GitHub stars 20% 9% Hacker News 20% 14% npm β 18% PyPI β 13% Product Hunt β 14% Stack Overflow β 10%
If a source is unavailable, its weight is redistributed automatically.
Tool schema
idea_check
Parameter Type Required Description
idea_text string yes Natural-language description of idea
depth "quick" | "deep" no "quick" = GitHub + HN (default). "deep" = all 6 sources
Full output example
{
"reality_signal": 72,
"duplicate_likelihood": "high",
"trend": "accelerating",
"sub_scores": { "market_momentum": 73 },
"evidence": [
{"source": "github", "type": "repo_count", "query": "...", "count": 342},
{"source": "github", "type": "max_stars", "query": "...", "count": 15000},
{"source": "hackernews", "type": "mention_count", "query": "...", "count": 18},
{"source": "npm", "type": "package_count", "query": "...", "count": 56},
{"source": "pypi", "type": "package_count", "query": "...", "count": 23},
{"source": "producthunt", "type": "product_count", "query": "...", "count": 8},
{"source": "stackoverflow", "type": "question_count", "query": "...", "count": 120}
],
"top_similars": [
{"name": "user/repo", "url": "https://github.com/...", "stars": 15000, "description": "..."}
],
"pivot_hints": [
"High competition. Consider a niche differentiator...",
"The leading project may have gaps in..."
]
}
CI: Auto-check on Pull Requests
Use idea-check-action to validate feature proposals:
name: Idea Reality Check
on:
issues:
types: [opened]
jobs:
check:
if: contains(github.event.issue.labels.*.name, 'proposal')
runs-on: ubuntu-latest
steps:
- uses: mnemox-ai/idea-check-action@v1
with:
idea: ${{ github.event.issue.title }}
github-token: ${{ secrets.GITHUB_TOKEN }}
Optional config
export GITHUB_TOKEN=ghp_... # Higher GitHub API rate limits
export PRODUCTHUNT_TOKEN=your_... # Enable Product Hunt (deep mode)
Auto-trigger: Add one line to your CLAUDE.md, .cursorrules, or .github/copilot-instructions.md:
When starting a new project, use the idea_check MCP tool to check if similar projects already exist.
Roadmap
-
v0.1 β GitHub + HN search, basic scoring
-
v0.2 β Deep mode (npm, PyPI, Product Hunt), keyword extraction
-
v0.3 β 3-stage keyword pipeline, Chinese term mappings, LLM-powered search
-
v0.4 β Score History, Agent Templates, GitHub Action
-
v0.5 β Temporal signals, trend detection, market momentum
-
v0.6 β Onboarding CLI (
idea-reality setup,config,doctor) -
v1.0 β Idea Memory Dataset (opt-in anonymous logging)
Star History
Found a blind spot?
If the tool missed obvious competitors or returned irrelevant results:
-
Open an issue with your idea text and the output
-
We'll improve the keyword extraction for your domain
Contributing
See CONTRIBUTING.md (ηΉι«δΈζ).
License
MIT β see LICENSE
Built by Mnemox AI Β· [emailΒ protected]
# 1. Install
uvx idea-reality-mcp
# 2. Add to your agent
claude mcp add idea-reality -- uvx idea-reality-mcp # Claude CodeQuick Start
# 1. Install
uvx idea-reality-mcp
# 2. Add to your agent
claude mcp add idea-reality -- uvx idea-reality-mcp # Claude Code
3. Ask your agent: "Before I start building, check if this already exists: a CLI tool that converts Figma designs to React components"
That's it. The agent calls idea_check and returns: reality_signal, top competitors, and pivot suggestions.
Other MCP clients Claude Desktop / Cursor β add to config JSON:
{
"mcpServers": {
"idea-reality": {
"command": "uvx",
"args": ["idea-reality-mcp"]
}
}
}
Config location: macOS ~/Library/Application Support/Claude/claude_desktop_config.json Β· Windows %APPDATA%\Claude\claude_desktop_config.json Β· Cursor .cursor/mcp.json
Smithery (remote, no local install):
npx -y @smithery/cli install idea-reality-mcp --client claude
Setup & Configuration
First-time guided setup:
idea-reality setup
This walks you through:
-
Terms acceptance β data collection policy and disclaimer
-
Platform detection β auto-detects Claude Desktop, Claude Code, Cursor, Windsurf, Cline
-
Config generation β prints the exact JSON snippet for your platform
-
Health check β verifies MCP server, tools, and scoring engine
Platform Configs
idea-reality config # interactive menu
idea-reality config claude_code # auto-installs via CLI
idea-reality config cursor # prints Cursor config
idea-reality config raw_json # generic MCP JSON
Supported: Claude Desktop Β· Claude Code Β· Cursor Β· Windsurf Β· Cline Β· Smithery Β· Docker
Health Check
idea-reality doctor # core checks (~2s)
idea-reality doctor --full # + GitHub API, all 6 sources, Anthropic API
Usage
MCP tool call (any MCP-compatible agent):
{
"tool": "idea_check",
"arguments": {
"idea_text": "a CLI tool that converts Figma designs to React components",
"depth": "deep"
}
}
REST API (no MCP required):
curl -X POST https://idea-reality-mcp.onrender.com/api/check \
-H "Content-Type: application/json" \
-d '{"idea_text": "AI code review tool", "depth": "quick"}'
Python:
import httpx
resp = httpx.post("https://idea-reality-mcp.onrender.com/api/check", json={
"idea_text": "AI code review tool",
"depth": "deep"
})
print(resp.json()["reality_signal"]) # 0-100
Free. No API key required.
No common issues documented yet. If you hit a problem, the repository's GitHub Issues page is the best place to look.