Rosentic MCP Server

@Rosentic

Basic information

About Rosentic MCP Server

Deterministic cross-branch conflict detection for AI coding agents. Scans your git repo for function signature mismatches, HTTP route conflicts, and schema breaks across branches using tree-sitter AST analysis. Catches the merge failures that CI misses because tests only run on o

#git#merge-conflicts#cross-branch#code-safety#tree-sitter#function-signatures#schema-validation #ai-agents

Rosentic MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "rosentic": {
      "command": "rosentic-mcp",
      "args": [],
      "env": {}
    }
  }
}

Rosentic MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Rosentic?

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—the kind of structural contract conflicts that cause runtime failures after merge.

How to use Rosentic?

Install the Rosentic plugin in Cursor by running /add-plugin rosentic or searching “Rosentic” in the Plugin Marketplace. Prerequisite: install the rosentic-mcp command via pip install rosentic-mcp. Once installed, the Cursor agent automatically uses three MCP tools—check_conflicts, explain_conflict, and list_branches—to run cross-branch compatibility checks at push, PR, or merge time.

Key features of Rosentic

Cross-branch contract conflict detection before merge
Catches broken function signatures and HTTP route conflicts
Detects schema mismatches across 15+ languages
Deterministic AST analysis (not AI code review)
All scans run locally; no code leaves your machine
Includes MCP tools, skill, and rule for Cursor agent

Use cases of Rosentic

Before pushing a branch, verify it won’t break other branches
Open a PR with confidence that no hidden contract conflicts exist
Prevent runtime failures when one branch adds a required parameter and another uses the old signature
Catch HTTP route or GraphQL type changes that would break dependent branches after merge

Frequently asked questions

What kind of conflicts does Rosentic detect?

Rosentic finds broken function signatures, HTTP route conflicts, and schema mismatches (including GraphQL) across 15+ languages using deterministic AST analysis.

How is Rosentic different from 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.

Does Rosentic send my code to the cloud?

No. All scans run locally against your git repo. No code leaves your machine.

What are the installation prerequisites?

You need Cursor and the `rosentic-mcp` Python package installed via `pip install rosentic-mcp`. The plugin is then added via `/add-plugin rosentic` or the Plugin Marketplace.

What MCP tools does Rosentic provide?

It provides `check_conflicts` (scan repo for cross-branch contract conflicts), `explain_conflict` (explain a specific finding), and `list_branches` (list active branches for the agent to choose).

Comments

More Developer Tools MCP servers

SSH MCP Server

hypnosis

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

Casefile

azimov777

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

Eased

easedui

Eased is a library of motion-first React components for shadcn, installed with the shadcn CLI.

Yocoolab

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

FARPY

mangomunchr

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP