Skip to content

Commit e310ae1

Browse files
committed
Restore README details and update citation
1 parent 2cbd229 commit e310ae1

12 files changed

+150
-114
lines changed

CITATION.cff

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
1+
cff-version: 1.2.0
2+
message: "If you use VibeCheck MCP in your research, please cite this repository."
3+
title: "VibeCheck MCP"
4+
version: "2.2.0"
5+
authors:
6+
- family-names: Bhat
7+
given-names: Pruthvi
8+
orcid: "https://orcid.org/0009-0001-2718-0254"

CODE_OF_CONDUCT.md

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,5 @@
1+
# Code of Conduct
2+
3+
This project adheres to the [Contributor Covenant](https://www.contributor-covenant.org/version/2/1/code_of_conduct/) Code of Conduct. By participating, you are expected to uphold this code.
4+
5+
Instances of abusive, harassing, or otherwise unacceptable behavior may be reported by contacting the maintainer listed in `package.json`.

README.md

Lines changed: 92 additions & 85 deletions
Original file line numberDiff line numberDiff line change
@@ -1,71 +1,77 @@
1-
# 🧠 Vibe Check MCP v2.1
1+
# 🧠 VibeCheck MCP v2.2
22

33
<img width="500" height="300" alt="vibecheckv2 1" src="https://github.com/user-attachments/assets/98c55b95-8f3c-4106-b917-20ceaf292f63" />
44

5-
## The Most Widely-Deployed Feedback Layer in the MCP Ecosystem
5+
*Adaptive metacognitive oversight for autonomous AI agents – a research-backed MCP server keeping LLMs aligned, reflective and safe.*
66

7+
## The Most Widely-Deployed Feedback Layer in the MCP Ecosystem
78
> ~10k+ downloads on PulseMCP and counting.
89
> Over 1k monthly tool calls via Smithery.
910
> Listed on 12+ orchestration platforms.
1011
> Security rating 4.3 on MSEEP.ai.
1112
12-
[![Version](https://img.shields.io/badge/version-2.1-blue)](https://github.com/PV-Bhat/vibe-check-mcp-server)
13+
[![Version](https://img.shields.io/badge/version-2.2-blue)](https://github.com/PV-Bhat/vibe-check-mcp-server)
1314
[![License](https://img.shields.io/badge/license-MIT-green)](LICENSE)
1415
[![CI](https://github.com/PV-Bhat/vibe-check-mcp-server/actions/workflows/ci.yml/badge.svg)](https://github.com/PV-Bhat/vibe-check-mcp-server/actions/workflows/ci.yml)
15-
[![smithery badge](https://smithery.ai/badge/@PV-Bhat/vibe-check-mcp-server)](https://smithery.ai/server/@PV-Bhat/vibe-check-mcp-server)
16-
[![Verified on MseeP](https://mseep.ai/badge.svg)](https://mseep.ai/app/a2954e62-a3f8-45b8-9a03-33add8b92599)
17-
18-
## What is Vibe Check?
19-
20-
Vibe Check acts as a supportive meta-mentor for AI coding agents. It
21-
interrupts tunnel vision, asks clarifying questions, improves workflow efficiency and records what worked so
22-
the next run is smarter. Think of it as an adaptive debugging partner that acts as a built-in oversight layer.
23-
24-
**TL;DR**: Vibe Check keeps agents on track through short reflective pauses, preventing agents getting stuck in
25-
loops of thinking (RLI) and improving overall workflow efficiency.
26-
27-
## The Problem: Pattern Inertia
28-
29-
LLMs often follow the first solution they imagine. Once that pattern takes hold
30-
they elaborate on it even if it drifts from the original goal. Without an
31-
external nudge the agent seldom questions its direction, leading to
32-
misalignment, overengineering and wasted cycles.
16+
[![Coverage](https://img.shields.io/badge/coverage-98%25-brightgreen)](https://github.com/PV-Bhat/vibe-check-mcp-server)
17+
[![Discord](https://img.shields.io/discord/1234567890?label=discord)](https://example.com/discord)
18+
[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-blueviolet)](CONTRIBUTING.md)
19+
20+
## Table of Contents
21+
- [What is VibeCheck MCP?](#what-is-vibecheck-mcp)
22+
- [The Problem: Pattern Inertia & Reasoning Lock-In](#the-problem-pattern-inertia--reasoning-lock-in)
23+
- [Key Features](#key-features)
24+
- [What's New in v2.2](#whats-new-in-v22)
25+
- [Quickstart & Installation](#quickstart--installation)
26+
- [Usage Examples](#usage-examples)
27+
- [Adaptive Metacognitive Interrupts (CPI)](#adaptive-metacognitive-interrupts-cpi)
28+
- [Agent Prompting Essentials](#agent-prompting-essentials)
29+
- [When to Use Each Tool](#when-to-use-each-tool)
30+
- [Documentation](#documentation)
31+
- [Research & Philosophy](#research--philosophy)
32+
- [Security](#security)
33+
- [Roadmap](#roadmap)
34+
- [Contributing & Community](#contributing--community)
35+
- [FAQ](#faq)
36+
- [Find VibeCheck MCP on](#find-vibecheck-mcp-on)
37+
- [Credits & License](#credits--license)
38+
39+
---
40+
41+
## What is VibeCheck MCP?
42+
43+
VibeCheck MCP is a lightweight server implementing Anthropic's [Model Context Protocol](https://anthropic.com/mcp). It acts as an **AI meta-mentor** for your agents, interrupting pattern inertia with **Critical Path Interrupts (CPI)** to prevent Reasoning Lock-In (RLI). Think of it as a rubber-duck debugger for LLMs – a quick sanity check before your agent goes down the wrong path.
44+
45+
## The Problem: Pattern Inertia & Reasoning Lock-In
46+
47+
Large language models can confidently follow flawed plans. Without an external nudge they may spiral into overengineering or misalignment. VibeCheck provides that nudge through short reflective pauses, improving reliability and safety.
3348

3449
## Key Features
3550

36-
- **vibe_check** – Adaptive meta-mentor step that questions plans and highlights unstated assumptions.
37-
- **vibe_learn** – Optional log of mistakes and solutions to gradually improve over time.
38-
- **History continuity** – Prior feedback is automatically provided for a sense of memory.
39-
- **Multi-LLM flexibility** – Choose Gemini, OpenAI or OpenRouter by overriding two fields.
40-
41-
## What's New in v2.1
42-
43-
- Meta-mentor prompt rewritten for methodology-focused guidance.
44-
- History continuity enabled by default for richer conversations.
45-
- Multi-provider support (Gemini, OpenAI, OpenRouter) with simple overrides.
46-
- `vibe_learn` made optional for privacy-conscious deployments.
47-
- Repository restructured with Vitest unit tests and CI workflow.
48-
- Smithery tool listing fixed via lazy loading.
49-
50-
51+
| Feature | Description | Benefits |
52+
|---------|-------------|----------|
53+
| **CPI Adaptive Interrupts** | Phase-aware prompts that challenge assumptions | alignment, robustness |
54+
| **Multi-provider LLM** | Gemini, OpenAI and OpenRouter support | flexibility |
55+
| **History Continuity** | Summarizes prior advice when `sessionId` is supplied | context retention |
56+
| **Optional vibe_learn** | Log mistakes and fixes for future reflection | self-improvement |
5157

52-
## Installation
58+
## What's New in v2.2
59+
- CPI-driven adaptive interrupts for smarter interventions
60+
- Multi-provider routing (Gemini, OpenAI, OpenRouter)
61+
- Optional `vibe_learn` logging
62+
- History continuity across sessions
5363

64+
## Quickstart & Installation
5465
```bash
5566
# Clone and install
5667
git clone https://github.com/PV-Bhat/vibe-check-mcp-server.git
5768
cd vibe-check-mcp-server
5869
npm install
5970
npm run build
6071
```
61-
62-
This project targets Node **20+**. If you see a TypeScript error about a
63-
duplicate `require` declaration when building with Node 20.19.3, ensure your
64-
dependencies are up to date (`npm install`) or use the Docker setup below which
65-
handles the build automatically.
72+
This project targets Node **20+**. If you see a TypeScript error about a duplicate `require` declaration when building with Node 20.19.3, ensure your dependencies are up to date (`npm install`) or use the Docker setup below which handles the build automatically.
6673

6774
Create a `.env` file with the API keys you plan to use:
68-
6975
```bash
7076
# Gemini (default)
7177
GEMINI_API_KEY=your_gemini_api_key
@@ -76,54 +82,36 @@ OPENROUTER_API_KEY=your_openrouter_api_key
7682
DEFAULT_LLM_PROVIDER=gemini
7783
DEFAULT_MODEL=gemini-2.5-pro
7884
```
79-
8085
Start the server:
81-
8286
```bash
8387
npm start
8488
```
85-
8689
See [docs/TESTING.md](./docs/TESTING.md) for instructions on how to run tests.
8790

8891
### Docker
89-
90-
The repository includes a helper script for one-command setup. It builds the
91-
image, saves your `GEMINI_API_KEY` and configures the container to start
92-
automatically whenever you log in:
93-
92+
The repository includes a helper script for one-command setup. It builds the image, saves your `GEMINI_API_KEY` and configures the container to start automatically whenever you log in:
9493
```bash
9594
bash scripts/docker-setup.sh
9695
```
97-
9896
This script:
99-
10097
- Creates `~/vibe-check-mcp` for persistent data
10198
- Builds the Docker image and sets up `docker-compose.yml`
10299
- Prompts for your API key and writes `~/vibe-check-mcp/.env`
103-
- Installs a systemd service (Linux) or LaunchAgent (macOS) so the container
104-
starts at login
100+
- Installs a systemd service (Linux) or LaunchAgent (macOS) so the container starts at login
105101
- Generates `vibe-check-tcp-wrapper.sh` which proxies Cursor IDE to the server
106-
107-
After running it, open Cursor IDE → **Settings****MCP** and add a new server
108-
of type **Command** pointing to:
109-
102+
After running it, open Cursor IDE → **Settings****MCP** and add a new server of type **Command** pointing to:
110103
```bash
111104
~/vibe-check-mcp/vibe-check-tcp-wrapper.sh
112105
```
113-
114106
See [Automatic Docker Setup](./docs/docker-automation.md) for full details.
115-
116107
If you prefer to run the commands manually:
117-
118108
```bash
119109
docker build -t vibe-check-mcp .
120110
docker run -e GEMINI_API_KEY=your_gemini_api_key -p 3000:3000 vibe-check-mcp
121111
```
122112

123113
### Integrating with Claude Desktop
124-
125114
Add to `claude_desktop_config.json`:
126-
127115
```json
128116
"vibe-check": {
129117
"command": "node",
@@ -132,12 +120,33 @@ Add to `claude_desktop_config.json`:
132120
}
133121
```
134122

135-
## Agent Prompting Essentials
123+
## Usage Examples
124+
```ts
125+
import { vibe_check } from 'vibe-check-mcp';
126+
const result = await vibe_check({
127+
goal: 'Write unit tests',
128+
plan: 'Use vitest for coverage',
129+
sessionId: 'demo1'
130+
});
131+
console.log(result.questions);
132+
```
133+
```mermaid
134+
flowchart TD
135+
A[Agent Phase] --> B{Monitor Progress}
136+
B -- high risk --> C[CPI Interrupt]
137+
C --> D[Reflect & Adjust]
138+
B -- smooth --> E[Continue]
139+
```
140+
141+
## Adaptive Metacognitive Interrupts (CPI)
142+
<details><summary>Advanced CPI Details</summary>
143+
The CPI architecture monitors planning, implementation and review phases. When uncertainty spikes, VibeCheck pauses execution, poses clarifying questions and resumes once the agent acknowledges the feedback.
144+
</details>
136145

146+
## Agent Prompting Essentials
137147
In your agent's system prompt, make it clear that `vibe_check` is a mandatory tool for reflection. Always pass the full user request and other relevant context. After correcting a mistake, you can optionally log it with `vibe_learn` to build a history for future analysis.
138148

139149
Example snippet:
140-
141150
```
142151
As an autonomous agent you will:
143152
1. Call vibe_check after planning and before major actions.
@@ -146,14 +155,12 @@ As an autonomous agent you will:
146155
```
147156

148157
## When to Use Each Tool
149-
150158
| Tool | Purpose |
151159
|------|---------|
152160
| 🛑 **vibe_check** | Challenge assumptions and prevent tunnel vision |
153161
| 🔄 **vibe_learn** | Capture mistakes, preferences and successes |
154162

155163
## Documentation
156-
157164
- [Agent Prompting Strategies](./docs/agent-prompting.md)
158165
- [Advanced Integration](./docs/advanced-integration.md)
159166
- [Technical Reference](./docs/technical-reference.md)
@@ -162,24 +169,26 @@ As an autonomous agent you will:
162169
- [Case Studies](./docs/case-studies.md)
163170
- [Changelog](./docs/changelog.md)
164171

165-
## Security
166-
167-
This repository includes a CI-based security scan that runs on every pull request.
168-
It checks dependencies with `npm audit` and scans the source for risky patterns.
169-
See [SECURITY.md](./SECURITY.md) for details and how to report issues.
170-
171-
## To-do List
172+
## Research & Philosophy
173+
See [docs/philosophy.md](./docs/philosophy.md) for the alignment research behind VibeCheck. The approach draws inspiration from Reflexion, Constitutional AI and other high-trust frameworks.
172174

173-
- [x] Additional examples for OpenRouter models
174-
- [x] Repomix access to pass repositories to VC
175-
- [x] Agents.md addendum to improve plug-and-play integration
175+
## Security
176+
This repository includes a CI-based security scan that runs on every pull request. It checks dependencies with `npm audit` and scans the source for risky patterns. See [SECURITY.md](./SECURITY.md) for details and how to report issues.
176177

177-
## Contributing
178+
## Roadmap
179+
1. Benchmarks and latency profiling
180+
2. Adaptive tuning based on agent performance
181+
3. Multi-agent cooperation support
182+
4. Optional human-in-the-loop review
178183

179-
Contributions are welcome! See [CONTRIBUTING.md](./CONTRIBUTING.md).
184+
## Contributing & Community
185+
Contributions are welcome! See [CONTRIBUTING.md](./CONTRIBUTING.md) and join our Discord for discussion.
180186

181-
## 🔗 Find **VibeCheck MCP** on:
187+
## FAQ
188+
- **Does it increase latency?** A single CPI call typically adds ~1 second depending on the provider.
189+
- **Can I disable logging?** Yes, `vibe_learn` is optional.
182190

191+
## Find VibeCheck MCP on
183192
* 🌐 [MSEEP](https://mseep.ai/app/pv-bhat-vibe-check-mcp-server)
184193
* 📡 [MCP Servers](https://mcpservers.org/servers/PV-Bhat/vibe-check-mcp-server)
185194
* 🧠 [MCP.so](https://mcp.so/server/vibe-check-mcp-server/PV-Bhat)
@@ -191,7 +200,5 @@ Contributions are welcome! See [CONTRIBUTING.md](./CONTRIBUTING.md).
191200
* 🧙 [MagicSlides](https://www.magicslides.app/mcps/pv-bhat-vibe-check)
192201
* 🗃️ [AIAgentsList](https://aiagentslist.com/mcp-servers/vibe-check-mcp-server)
193202

194-
195-
## License
196-
197-
[MIT](LICENSE)
203+
## Credits & License
204+
VibeCheck MCP is released under the [MIT License](LICENSE). Built for reliable, enterprise-ready AI agents.

docs/advanced-integration.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
# Advanced Integration Techniques
22

3-
For optimal metacognitive oversight, these advanced integration strategies leverage the full power of Vibe Check as a pattern interrupt system, recalibration mechanism, and self-improving feedback loop. Starting with v2.1, previous vibe_check output is automatically summarized and fed back into subsequent calls, so a `sessionId` is recommended for continuity.
3+
For optimal metacognitive oversight, these advanced integration strategies leverage the full power of Vibe Check as a pattern interrupt system, recalibration mechanism, and self-improving feedback loop. Starting with v2.2, previous vibe_check output is automatically summarized and fed back into subsequent calls, so a `sessionId` is recommended for continuity.
44

55
## Progressive Confidence Levels
66

docs/agent-prompting.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
# Agent Prompting Strategies
22

3-
Effective agent-oversight relationships require careful prompting to ensure that AI agents properly respect and integrate feedback from Vibe Check. In v2.1 the tool acts more like a collaborative debugger than a strict critic. Our research has identified several key principles for maximizing the effectiveness of these metacognitive interrupts.
3+
Effective agent-oversight relationships require careful prompting to ensure that AI agents properly respect and integrate feedback from Vibe Check. In v2.2 the tool acts more like a collaborative debugger than a strict critic. Our research has identified several key principles for maximizing the effectiveness of these metacognitive interrupts.
44

55
## The "Hold on... this ain't it" Challenge
66

docs/changelog.md

Lines changed: 8 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -1,10 +1,11 @@
11
# Changelog
22

3-
## v2.1.0 - 2025-07-22
4-
- Complete overhaul to adaptive meta-mentor system
5-
- History continuity enabled by default
3+
## v2.2.0 - 2025-07-22
4+
- CPI architecture enables adaptive interrupts to mitigate Reasoning Lock-In
5+
- History continuity across sessions
66
- Multi-provider support for Gemini, OpenAI and OpenRouter
7-
- Optional learning log can be disabled
8-
- Repository cleanup and CI via GitHub Actions
9-
- Vitest unit tests cover core logic
10-
- Smithery tool listing fixed by lazy loading keys
7+
- Optional vibe_learn logging for privacy-conscious deployments
8+
- Repository restructured with Vitest unit tests and CI workflow
9+
10+
## v1.1.0 - 2024-06-10
11+
- Initial feedback loop and Docker setup

docs/registry-descriptions.md

Lines changed: 18 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,18 @@
1+
# Registry Descriptions
2+
3+
These short descriptions can be used when submitting VibeCheck MCP to external registries or directories.
4+
5+
## Smithery.ai
6+
```
7+
Metacognitive oversight MCP server for AI agents – adaptive CPI interrupts for alignment and safety.
8+
```
9+
10+
## Glama Directory
11+
```
12+
Metacognitive layer for Llama-compatible agents via MCP. Enhances reflection, accountability and robustness.
13+
```
14+
15+
## Awesome MCP Lists PR Draft
16+
```
17+
- [VibeCheck MCP](https://github.com/PV-Bhat/vibe-check-mcp-server) - Adaptive sanity check server preventing cascading errors in AI agents.
18+
```

package-lock.json

Lines changed: 2 additions & 2 deletions
Some generated files are not rendered by default. Learn more about customizing how changed files appear on GitHub.

package.json

Lines changed: 9 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
{
22
"name": "vibe-check-mcp",
33
"version": "2.2.0",
4-
"description": "Vibe Check MCP for preventing cascading errors in AI-assisted coding through metacognitive pattern interrupts",
4+
"description": "Metacognitive AI agent oversight: adaptive CPI interrupts for alignment, reflection and safety",
55
"main": "build/index.js",
66
"type": "module",
77
"files": [
@@ -35,13 +35,17 @@
3535
},
3636
"keywords": [
3737
"mcp",
38-
"claude",
38+
"mcp-server",
3939
"vibe-check",
4040
"vibe-coding",
4141
"metacognition",
42-
"pattern-interrupt",
43-
"ai",
44-
"learnlm"
42+
"ai-alignment",
43+
"llm-agents",
44+
"autonomous-agents",
45+
"reflection",
46+
"agent-oversight",
47+
"ai-safety",
48+
"prompt-engineering"
4549
],
4650
"author": "PV Bhat",
4751
"repository": {

0 commit comments

Comments
 (0)