io.github.Rosentic/rosentic
Deterministic cross-branch conflict detection for AI coding agents
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
rosentic-mcpclaude mcp add rosentic -- uvx rosentic-mcp==0.1.1{
"mcpServers": {
"rosentic": {
"command": "uvx",
"args": [
"rosentic-mcp==0.1.1"
]
}
}
}Documentation
From the project's README on GitHub, refreshed weekly. Links open on GitHub.
Contents
Rosentic - Cross-Branch Merge Safety
Rosentic checks whether your active branches are compatible with each other before merge. It detects broken function signatures, HTTP route conflicts, and schema mismatches across 15+ languages using deterministic AST analysis.
This is not AI code review. Rosentic finds structural contract conflicts that would cause runtime failures after merge - the kind of breaks that tests don't catch because they only run on one branch at a time.
Install
pip install rosentic-mcpThen add to your editor's MCP config:
{
"mcpServers": {
"rosentic": {
"command": "rosentic-mcp",
"args": [],
"env": {}
}
}
}Works with Cursor, Claude Code, Cline, Windsurf, and any editor that supports MCP.
What it does
Rosentic gives your AI coding agent three MCP tools:
| Tool | Purpose |
|---|---|
check_conflicts | Scan a repo for cross-branch contract conflicts |
explain_conflict | Explain a specific finding and what to do about it |
list_branches | List active branches so the agent can choose what to scan |
Example conflicts Rosentic catches
- Branch A adds a required parameter to
createOrder(). Branch B callscreateOrder()with the old signature. Both pass CI. Merge breaks production. - Branch A changes
POST /api/usersto requireemailin the request body. Branch B's frontend still sends the old payload. - Branch A removes a field from a GraphQL type that Branch B's query depends on.
How it works
Before you push, open a PR, or merge, your agent runs a cross-branch compatibility check. It calls check_conflicts, which scans your repo's branch heads using tree-sitter AST parsing and reports any conflicts.
No code leaves your machine. The scan runs locally against your git repo.
Compared to Semgrep Guardian
Semgrep Guardian checks each file for security vulnerabilities and code issues. Rosentic checks whether your branches are compatible with each other. They solve different problems and work well together:
- Semgrep Guardian: "Is this code safe and correct on its own?"
- Rosentic: "Will this branch break other branches when merged?"
Links
Frequently asked questions
What is io.github.Rosentic/rosentic?
Deterministic cross-branch conflict detection for AI coding agents
How do I install io.github.Rosentic/rosentic?
It runs on your machine. In Claude Code: claude mcp add rosentic -- uvx rosentic-mcp==0.1.1. For other clients, paste the JSON configuration from this page into their MCP settings.
Does io.github.Rosentic/rosentic need an API key?
Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.
Is io.github.Rosentic/rosentic open source?
Its code is public on GitHub, but the repository does not declare a standard license.
Who maintains io.github.Rosentic/rosentic?
It is published by Rosentic. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.