Driftcheck
MCP serverCompares a running mobile app screen with its Figma frame and suggests code fixes
Runs locally- 5 tools
- Free
- Design and media
Compares a running mobile app screen with its Figma frame and suggests code fixes
Runs locallyLocal MCP server to edit git-native API requests, environments and scripts in Baton
Runs locallyBridge assistants to the Tabellum database client; writes need your click in the app
Runs locally
Local BM25 search over your Cursor, Claude, ChatGPT and Cline chat history
Runs locallyCited recall of past Codex and Claude Code chats, kept on your Windows PC
Runs locallyPicks the minimum code an LLM needs to review a git diff, locally and deterministically
Runs locallyRead-only witness for local git projects and sites, naming what would be lost
Runs locallyRead-only search of an OSINT tool and guide registry, with consent classes for each tool
Not checked yetLet a coding agent use temporary credentials without the values entering the chat
Runs locally
Start, stop and inspect the EnvKit local PHP and Node dev stack from an assistant
Runs locallyRead your Golem agent fleet sessions, live activity and signed record from any client
Not checked yetLocal token-usage scanner that scores your AI coding efficiency and ranks you on a board
Runs locallyMCP server that supplies the template and checker for building single-file AI agents
Not checked yetLocal memory vault for coding agents: layered Markdown, Git history and a validity check
Runs locallyCheck dashboardbase widget responses and setup files against the live contract
Runs locallyRead-only filesystem, git and allowlisted-task access to local project folders
Runs locally
Search a local, exact archive of your Claude Code conversations and edited files
Runs locallyInspect and optimize GLB models, then give an avatar a Solana wallet and a voice
Runs locallyCC0 sample files for tests: find one, get its URL and SHA-256, verify a local copy
Runs locallyRead-only security scanner for code, infrastructure files and AI agent config
Runs locallyOne markdown journal per project that your AI must read before it edits or runs anything
Runs locallyEncrypted local vault where your AI fetches API keys on demand and scans code for leaks
Runs locallyLocal approvals and audit so coding agents use credentials without ever seeing them
Runs locallyMCP server that corrects misheard names and jargon in dictated prompts before agents act
Runs locally