Token Optimizer MCP

Compress and cache text; primary tool for token reduction.

Retrieve previously cached text by key.

Compress text using Brotli.

Decompress Brotli-compressed text.

Count tokens using tiktoken (GPT-4 tokenizer).

Analyze text and return optimization recommendations.

View cache hit rates and compression ratios.

Clear all cached data (supports olderThan filtering).

Read files with caching and diff-based output (~80% token reduction).

Write files with verification and change tracking.

Line-based file editing with diff-only output (~90% reduction).

Search file contents with match-only output (~80% reduction).

File pattern matching with path-only results (~75% reduction).

Git diffs with diff-only output (~85% reduction).

Git branch listing with structured JSON (~60% reduction).

Git commit history with smart filtering (~75% reduction).

Git merge management with conflict analysis (~80% reduction).

Git status with status-only output (~70% reduction).

HTTP requests with caching and retry logic (~83% reduction on cache hits).

API response caching with TTL/ETag/event-based strategies.

Database queries with connection pooling and caching (~83% reduction).

SQL query analysis with optimization suggestions (~83% reduction).

Database schema analysis with intelligent caching.

GraphQL query optimization with complexity analysis (~83% reduction).

REST API analysis with endpoint discovery (~83% reduction).

ORM query optimization with N+1 detection (~83% reduction).

Database migration tracking (~83% reduction).

WebSocket connection management with message tracking.

TypeScript builds with diff-based change detection.

Test execution with incremental test selection.

ESLint with incremental analysis and auto-fix.

TypeScript type checking with caching.

Package installation with dependency analysis.

Docker operations with layer analysis.

Log aggregation with pattern filtering.

Network diagnostics with anomaly detection.

Process monitoring with resource tracking.

System resource monitoring with performance recommendations.

Multi-tier cache (L1/L2/L3) with 6 eviction strategies (~90% reduction).

Intelligent cache pre-warming with schedule support (~87% reduction).

Real-time dashboards and trend analysis (~88% reduction).

Performance testing and strategy comparison (~89% reduction).

6 compression algorithms with adaptive selection (~89% reduction).

Dependency tracking and pattern-based invalidation (~88% reduction).

ML-based recommendations and bottleneck detection (~89% reduction).

Sharding and consistent hashing (~87% reduction).

Distributed replication with conflict resolution (~88% reduction).

ML-based predictive caching with ARIMA/LSTM (~91% reduction).

Multi-channel alerting (email, Slack, webhook) with routing (~89% reduction).

Time-series metrics with multi-source support (~88% reduction).

Integrates external platforms (Prometheus, Grafana, Datadog) (~87% reduction).

Dashboard widgets with template caching (~88% reduction).

Interactive visualizations with SVG optimization (~92% reduction).

System health checks with state compression (~91% reduction).

Log analysis with pattern detection (~90% reduction).

Scheduled task management (cron / Windows Task Scheduler) (~85% reduction).

User and permission management across platforms (~86% reduction).

Structural code search with AST indexing (~83% reduction).

Session-level token usage statistics and savings breakdown.

Project-wide token analysis and cost estimation.

Compress large file operations from the current session.

Token usage breakdown by hook phase (PreToolUse, PostToolUse, etc.).

Token usage breakdown by tool/action (Read, Write, Grep, etc.).

Token usage breakdown by MCP server.

Export analytics data in JSON or CSV format with filtering.