Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-vibe-check vibe check: function foo() { return 1; }"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Your code has energy. Time to find out what kind.
An MCP server that gives your code a vibe check — assigning personality types to functions, rating variable name energy, and suggesting more aesthetic alternatives. Because userData was never the right name. It should be soulContainer.
Personality types for functions — Is handleSubmit a main character, or does it have NPC behavior? Find out.
Variable energy ratings — x gets "cryptic oracle energy (3/10)". MAXIMUM_RETRY_COUNT gets "dramatic monologue energy (9/10)". They earned it.
Aesthetic name suggestions — isValid → vibesPassing. error → chaosEvent. You're welcome.
Overall vibe score — A completely arbitrary number between 1 and 10 that means nothing and everything.
Code aesthetic assessment — Qualitative vibes. Unscientific. Occasionally accurate.
Related MCP server: MCP Code Reviewer
Input:
function handleSubmit(userData, isValid) {
const result = userData.name;
return result;
}Output:
{
"overallVibe": "cozy cottage-core with hints of cyberpunk",
"vibeScore": 6.8,
"functions": [
{
"name": "handleSubmit",
"personality": "main character energy",
"assessment": "This function carries the entire plot"
}
],
"variables": [
{
"name": "userData",
"energy": 7,
"assessment": "classic protagonist (7/10) — reliable, not flashy",
"suggestion": "soulContainer"
},
{
"name": "isValid",
"energy": 7,
"assessment": "classic protagonist (7/10) — reliable, not flashy",
"suggestion": "vibesPassing"
},
{
"name": "result",
"energy": 5,
"assessment": "functional but uninspired (5/10) — exists, which is something",
"suggestion": "manifestation"
}
],
"codeAesthetic": "Your code reads like a mystery novel — lots of setup, unclear payoff",
"recommendation": "Consider adding more comments for dramatic tension"
}npx mcp-vibe-checkAdd to your .mcp.json:
{
"mcpServers": {
"vibe-check": {
"command": "npx",
"args": ["-y", "mcp-vibe-check"]
}
}
}Then ask Claude: "What vibes does this codebase give off?"
Your functions can be:
Type | Meaning |
main character energy | Carries the entire plot |
side quest vibes | Important but easily forgotten |
NPC behavior | Does its job without complaint |
protagonist arc | Started simple, evolved into something bigger |
villain origin story | Nobody asked for this complexity |
comic relief | Technically unnecessary, yet essential |
mentor energy | Older, wiser, called at critical moments |
chosen one potential | Untested but destined for greatness |
Is this useful for code review? No. That's the point.
Will this improve my code quality? Statistically unlikely. Spiritually, possibly.
Why does console.log hurt my vibe score?
Because it's not aesthetic. Use a proper logger. Your stdout deserves better.
My function got "NPC behavior". Should I be offended? Only if your function has feelings. Which, based on this tool, it might.
"Not all code reviews need to be actionable. Some just need to be vibes."
Get a vibe check on your code. Assigns personality types to functions, rates variable name energy, and suggests more aesthetic alternatives.
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes | A snippet of code to vibe-check |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full burden. It accurately discloses the tool's output behaviors (personality types, energy ratings, suggestions), but does not explicitly state whether it modifies code or is read-only. The word 'suggests' implies non-destructiveness, but it could be more transparent about side effects and return format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, concise and well-structured. It front-loads the core purpose and elaborates with concrete details, with zero wasted text.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple one-parameter tool with no output schema, the description is mostly complete. It describes the input and the nature of the output (personality types, energy ratings, suggestions), though it could be slightly more explicit about the exact response format. Overall, adequate for the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with the parameter 'code' described as 'a snippet of code to vibe-check'. The description adds no extra semantics beyond this, so it meets the baseline but doesn't enrich parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function with specific actions: assigns personality types, rates variable name energy, suggests alternatives. It's a specific verb+resource ('vibe check on code') and effectively distinguishes the tool's quirky purpose even without siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for when to use the tool (when you want a vibe check on your code). Since there are no sibling tools, no exclusions or alternatives are needed. The usage context is evident from the described actions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0vibe-checkScored across 1 tool
With only one tool, there is no possibility of confusion or overlap with other tools. The tool's purpose is clearly distinct by virtue of being the only tool in the server.
A single tool name cannot have inconsistencies. The name 'vibe-check' is descriptive and follows a clear, if not standard, convention appropriate for its function.
The server has a narrow, focused purpose—providing vibe checks on code. One tool is slightly below the typical 3-15 range, but it is perfectly reasonable for this specific, limited scope.
The tool covers the full stated purpose: assigning personality types, rating variable name energy, and suggesting aesthetic alternatives. There are no obvious missing operations within its defined domain.
AI colleagues that keep your standards, your project and their reasoning between sessions
Read-only AI coding tools for change verification, release readiness, capacity, and guidance.
Lints + auto-fixes how AI coding agents discover any new product. 24 rules, 6 tools, score 0-100.
Agentic code review, no signup to try: reality gates + frontier-model review, with veto.
