Refactor
This MCP server provides code refactoring capabilities through regex-based search and replace operations across file systems, enabling AI agents to perform bulk code transformations with pattern matching and context filtering. Built using TypeScript with the Model Context Protocol SDK, glob for file discovery, and Zod for validation, it offers two core tools: code_refactor for executing search-and-replace operations with optional context patterns to limit scope, and code_search for finding code patterns and returning file locations with grouped line numbers. The implementation supports glob patterns for file filtering, directory-based searches, regex capture groups for complex replacements, and context-aware filtering to target specific code sections like import blocks, making it valuable for large-scale code migrations, API updates, refactoring legacy codebases, and building AI assistants that need programmatic code transformation capabilities across multiple files without manual find-and-replace operations.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/myuon/refactor-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Refactor from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.