🧠 Vibe Check MCP

Created By
PV-Bhata year ago
The definitive Vibe Coder's sanity check MCP server: Prevent cascading errors in AI workflows by implementing strategic pattern interrupts. Uses tool call "Vibe Check" with LearnLM 1.5 Pro (Gemini API), fine-tuned for pedagogy and metacognition to enhance complex workflow strategy, and prevents tunnel vision errors.
Overview

what is Vibe Check MCP?

Vibe Check MCP is a metacognitive pattern interrupt system designed to enhance AI-assisted development by preventing common pitfalls such as tunnel vision and misalignment in coding workflows.

how to use Vibe Check MCP?

To use Vibe Check MCP, integrate it into your AI development environment by following the installation instructions and utilizing its three main tools: vibe_check, vibe_distill, and vibe_learn.

key features of Vibe Check MCP?

  • Pattern interrupt mechanism (vibe_check) to break tunnel vision.
  • Meta-thinking anchor point (vibe_distill) for recalibrating complex workflows.
  • Self-improving feedback loop (vibe_learn) to build pattern recognition over time.

use cases of Vibe Check MCP?

  1. Preventing scope creep during project development.
  2. Enhancing AI agent performance by providing critical feedback.
  3. Streamlining complex coding tasks through effective planning and review phases.

FAQ from Vibe Check MCP?

  • Can Vibe Check MCP be used with any AI development framework?

Yes! Vibe Check MCP is designed to integrate with various AI development environments.

  • Is there a cost associated with using Vibe Check MCP?

No, Vibe Check MCP is open-source and free to use.

  • How does Vibe Check MCP improve AI coding workflows?

By providing strategic interventions that prevent common errors and enhance overall project alignment.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
PV-Bhat
Star
65
Language
TypeScript
License
MIT license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago