Idea RealitySAFE
Pre-build reality check for AI coding agents. Scans GitHub, HN, npm, PyPI, Product Hunt. MCP server. 290+ stars.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
English | 繁體中文
How to check if someone already built your app idea — automatically.
idea-reality-mcp is an MCP server that scans GitHub, npm, PyPI, Hacker News, and Stack Overflow to check if your startup idea already exists. It returns a 0–100 reality score with evidence, trend detection, and pivot suggestions — 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.
Project status (August 2026): Maintenance mode. The tool works, stays free & open source, and the hosted API remains up; bug reports are reviewed, but no new features are planned.
Not just checking — building it? After a reality check, open your idea as a public project on [AngelRun](https://angelrun.vercel.app/new?utm_source=idea-reality&utm_medium=readme&utm_campaign=demand-cta) — ship updates, climb the season, and get seen by angels.
[](https://pypi.org/project/idea-reality-mcp/) [](https://smithery.ai/server/idea-reality-mcp) [](https://opensource.org/licenses/MIT) [](https://github.com/mnemox-ai/idea-reality-mcp/actions/workflows/ci.yml) [](https://github.com/mnemox-ai/idea-reality-mcp) [](https://pepy.tech/project/idea-reality-mcp)
56a4754edf0dOBSERVED · 2026-09-27Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add idea-reality-mcp --env GITHUB_TOKEN=${GITHUB_TOKEN} -- None idea-reality-mcp==0.5.0Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
idea_check | read | Check if a product idea already exists before building it. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (6 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (6)
"http://127.0.0.1:5500", # VS Code Live Server
os.environ.items() ... httpx.
os.environ.items() ... httpx.
return base64.b64decode(cell["base64"])
fastapi, uvicorn, anthropic, libsql-client, httpx, numpy
- 🔴 **Turso ANN 向量索引=放棄(這台建不了)**。crowd 真實延遲**其實才 ~6s 不是 26s**(26s 是我當時猛打 DB 的競爭假象),所以**沒那麼急**。而且 ANN 索引在此環境建不起來:Turso HTTP `/v2/pipeline` **有 ~60s 硬上限**、10k×1536 bulk build 超時斷線;libsql sync client 在 W
Gates applied: no_behavioural_pass.
56a4754edf0dfull audit observations/trust-audit/mcp-server/mnemox-ai__idea-reality.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-27 | 56a4754edf0d | SAFE | B | 89 | first audit |
Questions
What is the Idea Reality MCP server?
Pre-build reality check for AI coding agents. Scans GitHub, HN, npm, PyPI, Product Hunt. MCP server. 290+ stars.
What tools does Idea Reality expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Idea Reality safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Idea Reality need?
It reads ANTHROPIC_API_KEY, EXPORT_KEY, GITHUB_TOKEN, LIBRARIES_IO_KEY, OPENAI_API_KEY, PRODUCTHUNT_TOKEN, STACKEXCHANGE_KEY and TURSO_AUTH_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Idea Reality run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as idea-reality-mcp.
How current is this page?
The grade is for one exact copy of the source (56a4754edf0d), read on 2026-09-27. The repository is watched and re-audited when it changes.