Vibe Check MCP
vibe-check-mcp-server
A mentor tool for an agent: it asks the agent to stop and check its plan before acting. The README states maintenance mode, and model keys are needed
- 502 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Context goes to the model provider
- The project is in maintenance mode
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add mcp/vibe-check-mcp-serverDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Context goes to the model provider
- The project is in maintenance mode
This is third-party code. Review the repository files before installing.
What it does
Vibe Check MCP works as a mentor: before an agent acts it asks the agent to stop and check its plan. Launch: `npx -y @pv-bhat/vibe-check-mcp start --stdio`, and for HTTP `start --http --port 2091`. Model keys are needed (Gemini, OpenAI, OpenRouter or Anthropic) and context goes to these providers. The README says the project is in maintenance mode with fixes only; the version in the README text is 2.9.0 while GitHub Releases has v2.7.6 from 06.11.2025. MIT license.
Who it is for. For developers who want an agent to check its plan with an independent view before big steps.
Good fit when
- The agent moves to actions too fast without checking the plan
- You need an independent plan check by another model
- You need a mentor MCP server
Not a fit when
- You cannot send context to model providers
- You need an actively developed project: it is in maintenance mode now
Example request
Before deleting the payment module stop and check your plan with an independent viewMCP
- Transport
- stdio, http
- Authentication
- API key
Limitations
Model keys are needed and the project and plan context goes to the provider: check that this is allowed. The project is in maintenance mode with fixes only. We have not verified the author's research figures on improved results. Access is extended.
How to disable. Remove the server entry from the client and the model keys issued for the work.
FAQ
What does Vibe Check MCP do?
It asks an agent to stop and check its plan with an independent view before acting.
What is needed to work?
Model keys (Gemini, OpenAI, OpenRouter or Anthropic) and the context goes to the provider.
Is the project developed?
The README states maintenance mode with fixes only.
Discussion
No questions or reviews yet.
Related
MCP serversA CLI for any MCP server: list and call tools, resources and prompts, run mock and proxy modes, guard access and manage agent configs
An MCP server that lets Claude Code, Codex and other agents call Gemini, GPT, Grok and local models for review, debugging and consensus
A CLI that turns any MCP server, OpenAPI spec or GraphQL endpoint into commands at runtime, with no codegen
An MCP server that installs other MCP servers from npm and PyPI at the agent's request and writes them into the config
A universal MCP CLI client from Apify: persistent sessions, OAuth, JSON output for scripts and shell access to any MCP server for agents
An MCP server that turns a request into a step plan with dependencies and keeps context across agent sessions
README in short
The README describes a mentor MCP server with launch through npx, model keys and maintenance mode. MIT license.