notavibe
Rank open-source packages on maintenance signals so assistants stop guessing
- Pricing
- Free
- Platforms
- API
- Runs
- Remotely
- Version
- 0.0.1
- Listing updated
- 2 days ago
About notavibe
notavibe is a free MCP server for developer tools. It runs as a hosted remote server, so there is nothing to install locally.
notavibe looks for evidence that a project still has people behind it, and gives an AI coding assistant that evidence when it recommends a package. It currently covers JavaScript and TypeScript projects and the hosted server needs no install or API key.
Each project gets five signals from public data: maintenance activity over the trailing 90 days, how many outside contributors had pull requests merged, adoption measured by dependent projects, whether maintainers (not bots) reply to new issues, and the OpenSSF Scorecard security score. Every signal shows its source, fetch date and a plain rating such as steady, broad or engaged. When there is nothing to measure it says insufficient data rather than guessing.
Its argument is that stars and downloads are easy to inflate, while release cadence and dependent counts are not. The site says dependency discovery, team dashboards and CI integration are planned. Clients that only run local servers can bridge with npx -y mcp-remote.
Install
Run in a terminal
claude mcp add --transport http mcp https://notavibe.dev/mcpAdd to Settings → Connectors → Add custom connector
https://notavibe.dev/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"mcp": {
"url": "https://notavibe.dev/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"mcp": {
"type": "http",
"url": "https://notavibe.dev/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"mcp": {
"serverUrl": "https://notavibe.dev/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"mcp": {
"type": "http",
"url": "https://notavibe.dev/mcp"
}
}
}What it does
- Five maintenance signals
- Activity, contributors, adoption, responsiveness and security posture.
- Sourced ratings
- Each rating shows its source and fetch date.
- Honest gaps
- Reports insufficient data instead of inventing a score.
- Hosted and keyless
- Add a URL to your client; nothing to install.
- Adoption by dependents
- Uses dependent-project counts, bucketed from under 10 to 10k+.
- OpenSSF Scorecard
- Rates security posture as strong, moderate or low.
Good for
- Check whether a library is still maintained before adding it
- Compare two packages on maintainer responsiveness
- Review your dependencies for quiet projects
- Stop an assistant recommending a popular but abandoned package
Pricing
Free
Free, no authentication
Prices change. Check notavibe.dev before you buy.
notavibe FAQ
Which languages are covered?
The site says JS/TS projects.
Does it need an API key?
No, it is free with no authentication.
What does adoption mean here?
The count of dependent projects from the package registry.
What is coming next?
Dependency discovery, team dashboards and CI integration, per the site.
Is notavibe free?
Yes. notavibe is free to use.
How do I add notavibe to Claude Code?
Run this command in your terminal: claude mcp add --transport http mcp https://notavibe.dev/mcp
What are the best alternatives to notavibe?
The closest alternatives to notavibe are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.
Alternatives to notavibe

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
Not checked yet- Remote
- Open source
- 34.5K GitHub stars
- Developer tools

Serena MCP: the IDE for your agent
MCP serverMCP toolkit giving coding agents symbol-level code retrieval and editing
Runs locally- Open source
- 31.5K GitHub stars
- Developer tools

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Ouroboros
MCP serverSpec-first layer that pins requirements and verifies results of AI coding agent work
Runs locally- Open source
- 6.4K GitHub stars
- Developer tools