Best Focus AI Skills & MCP Servers

Complete filesystem operations — loads fileread, filewrite, filelist, fileops, filesearch.

File comparison — diff, patch, delta between files or versions.

Inline, extract, and move refactoring — inline variables/functions, extract code to new functions, move between files.

Call graph analysis — callers, callees, call chains.

Structured decision-making — define options, analyze tradeoffs, recommend, and record decisions.

File access heatmap — track read/write patterns, detect hot and cold files.

Track and report token savings — compare FocusMCP usage vs naive full-read, trend over time, ROI.

Dependency graph analysis — imports, exports, circular deps, fan-in/out.

Rename refactoring — rename symbols across files, rename files with import updates, bulk rename with preview.

Security-focused ESLint plugin for Node.js built-in modules (fs, child_process, vm, path, Buffer). Detects command injection, path traversal, code execution vulnerabilities with AI-parseable error messages.

Semantic search using TF-IDF vector space — cosine similarity, intent matching, document similarity.

Session context save and restore — track loaded files and operations, persist sessions to disk.

File operations — move, copy, delete, rename.

Compress text output to save tokens — strip comments, collapse whitespace, abbreviate patterns.

Knowledge base — loads knowledge, fts, graphbuild, graphquery for document indexing and graph-powered search.

Search and replace in files — regex search, in-place replace.

Multi-repo management — register, track, and get stats for multiple repositories.

Session metrics tracking — token usage, costs, duration, and per-tool statistics.

Persistent key-value memory — store and recall information across sessions as JSON files.

Project onboarding workflow — auto-discover project structure, conventions, and key files for a new contributor or AI agent.

Hello-world brick — returns the message it receives. Serves as a smoke test for the FocusMCP pipeline.

Multi-source research — collect info from multiple files/sources, synthesize findings, validate consistency.

Shell command execution — run commands, background processes, kill, and compress output.

Sandboxed code execution — run JavaScript/TypeScript snippets in an isolated VM context.