$ loading_
Help AI coding agents understand codebase structure, history, docs, and health.
Repowise appears focused on local codebase analysis, with no declared secrets or remote endpoints, and it benefits from being listed in an official registry, open-source, and recently maintained. Overall risk is low, but its normal MCP capabilities for local code execution and repository access warrant use within a controlled project scope.
The materials explicitly state that no keys or environment variables are required. No API tokens, account credentials, or other sensitive authentication secrets are requested, so credential exposure appears minimal.
The materials declare no remote endpoints, and the README content does not describe sending code or user data to third-party services. Based on the available facts, there is no clear data egress path.
The system flags executes-code, indicating that this MCP can execute code or spawn processes locally. This is a normal capability for this class of tools, but it should still be run in a controlled environment with limited working scope.
Its description references graph, git history, docs, decisions, and code health, which reasonably implies access to local repository contents, documentation, and Git history. There is no evidence of system-wide overreach, but it should be assumed to access sensitive source code and commit history within the project.
It comes from an official registry and is open-source with updates in the last year, all of which are meaningful risk-reducing signals. However, the repository has 0 stars and no declared license, so community validation and compliance clarity are limited; source and dependency review is advisable before adoption.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "Repowise" MCP server from askskill: Run: claude mcp add 'dev-repowise-repowise' -- npx -y repowise
Analyze this codebase and summarize its overall structure, core modules, dependency relationships, key documentation entry points, and recent major architectural changes.
A codebase map with module relationships, documentation index, and a summary of key historical changes.
For this feature module, use git history, related docs, and code comments to explain why the current implementation was chosen and list possible technical trade-offs.
An explanation of decision context, including relevant commits, documentation evidence, and trade-off analysis.
Review the repository’s code health, identify high-risk modules, maintainability issues, weak testing areas, and provide prioritized improvement recommendations.
A code health assessment report with risk areas, issue prioritization, and actionable improvement recommendations.
Search and understand indexed repositories without setting up local code indexing.
Query and understand large codebases with a fast knowledge graph for AI agents.
Turn codebases into knowledge graphs for architecture and dependency understanding.
Gives AI coding agents a structural map of your repository fast.
Analyze, search, and understand local code repositories with agent-first intelligence.
Provide Git-native project memory for AI coding agents with safe, reviewable context.