Token Optimizer MCP server

Read from the package source without running it. The installed server may list more.

• alert_manager

  Comprehensive alerting system with multi-channel notifications, intelligent routing, and 89% token reduction through aggressive caching and history aggregation

• analyze_optimization

  Analyze text and provide recommendations for optimization including compression benefits and token savings.

• analyze_project_tokens

  Analyze observed token usage across multiple sessions within a project. Aggregates session logs and identifies top contributors. Cost is Not priced unless the caller supplies an effective input-token rate; any resulting value is a cost equivalent, not an invoice.

• anomalyexplainer

  Explain anomalies with root cause analysis, hypothesis generation, and remediation suggestions

• cache_analytics

  Comprehensive cache analytics with 88%+ token reduction. Real-time dashboards, trend analysis, alerting, heatmaps, bottleneck detection, and cost optimization.

• cache_audit

  Report Anthropic prompt-cache economics for this project: measured cache-read input, cache-write input, hit rate, and warm prefix size read from a Claude Code transcript, plus likely invalidation sources. Cost equivalents are labeled Anthropic-specific, excluded from universal savings, and are not invoices.

• cache_benchmark

  Cache Performance Benchmarking with 89% token reduction through comprehensive testing and analysis. Features: - Strategy comparison (LRU vs LFU vs FIFO vs TTL vs size vs hybrid) - Load testing with configurable concurrency and ramp-up - Latency profiling with percentiles (p50, p90, p95, p99, p99.9) - Throughput testing (operations per second) - Comprehensive reports in markdown, HTML, JSON, PDF -

• cache_compression

  Advanced compression strategies for cache optimization with 89%+ token reduction. Supports 6 algorithms (gzip, brotli, lz4, zstd, snappy, custom), adaptive selection, dictionary-based compression, and delta compression for time-series data.

• cache_invalidation

  Comprehensive cache invalidation with 88%+ token reduction, dependency tracking, pattern matching, scheduled invalidation, and distributed coordination

• cache_optimizer

  Advanced cache optimization with 89%+ token reduction. Analyzes performance, benchmarks strategies, provides ML-based recommendations, detects bottlenecks, and performs cost-benefit analysis.

• cache_partition

  Advanced cache partitioning and sharding with 87%+ token reduction through consistent hashing, automatic rebalancing, and partition isolation

• cache_replication

  Distributed cache replication with 88%+ token reduction. Supports primary-replica and multi-primary modes, strong/eventual consistency, automatic conflict resolution, failover, incremental sync, and health monitoring.

• cache_warmup

  Intelligent cache pre-warming with 87%+ token reduction, featuring schedule-based warming, pattern analysis, dependency resolution, and progressive warming strategies

• checkpoint_handoffwrite action

  Create or restore a resumable checkpoint and return a takeover receipt.

• clear_cache

  Clear all cached data. Use with caution.

• cognition_record

  Verify external grader evidence, then propose and activate evidence-backed cognition authored by the active model. Use operation=verify-evidence before recording unfamiliar evidence.

• compress_text

  Compress text using Brotli, returned as a base64 string. Intended for AT-REST STORAGE/caching (reduces bytes ~50%). NOTE: base64 tokenizes poorly, so the output usually has MORE LLM tokens than the input — do NOT feed the result into a model context expecting savings. The response includes originalTokens/compressedTokens and a warning when the output would increase tokens.

• context_delta

  Compute a unified-diff delta for a file in a given session so the model only sees changes since the last snapshot. Operations: compute-delta, seed, clear.

• context_page

  Obtain bounded decision-specific cognition. Returns an explicit empty result when nothing safe applies.

• context_receipt_verify

  Verify that one adapter-delivered context receipt and its correction trace to authenticated external grader evidence.

• count_tokens

  Count tokens in text using the pluggable tokenizer framework (#124). Picks a model-specific tokenizer (tiktoken for GPT/Claude, Google AI REST for Gemini, content-aware heuristic fallback).

• custom_widgetwrite action

  Create and manage custom dashboard widgets with 88% token reduction through template caching and configuration compression

• data_visualizerwrite action

  Create and manage interactive data visualizations with 92% token reduction through SVG/Canvas optimization and configuration caching

• decompress_text

  Decompress base64-encoded Brotli-compressed text.

• expand

  Retrieve the full output behind a preview reference, served from the local store rather than by re-running anything.

• export_analytics

  Export all analytics data in JSON or CSV format. Supports filtering by date range, hook phase, tool name, and MCP server. Useful for external analysis, reporting, and data integration.

• fleet_audit

  Look across every project on this machine at once: which projects hold the cost (ranked with dollar figures), which fixes

• get_action_analytics

  Get detailed token usage analytics broken down by tool/action (Read, Write, Grep, Bash, count_tokens, etc.). Shows which tools consume the most tokens and identifies optimization opportunities for specific operations.

• get_cache_stats

  Get cache statistics including hit rate, compression ratio, and token savings.

• get_cached

  Retrieve previously cached and optimized text. Returns the original text if found in cache.

• get_hook_analytics

  Get detailed token usage analytics broken down by hook phase (PreToolUse, PostToolUse, SessionStart, PreCompact, UserPromptSubmit). Shows which hook phases consume the most tokens and where optimization efforts should be focused.

• get_mcp_server_analytics

  Get detailed token usage analytics broken down by MCP server (token-optimizer, filesystem, github, etc.). Shows which MCP servers are contributing the most to token usage and helps identify cross-server optimization opportunities.

• get_optimization_report

  Get a provenance-gated token report. Verified savings require a materialized MCP payload before and after optimization; historical and tool-reported estimates are excluded. Direct API-price equivalents use each exact captured model and route; ambiguous operations remain unpriced.

• get_session_stats

  Get comprehensive statistics from the PowerShell wrapper session tracker including system reminders, tool operations, and total tokens with accurate tiktoken-based counting.

• health-monitor

  Monitor health status of systems, services, and applications with dependency tracking. Supports 8 operations: check, register-check, update-check, delete-check, get-status, get-history, configure-dependencies, get-impact. Achieves 87% token reduction through status caching and dependency graph compression.

• health_monitor

  Monitor system and application health with 91% token reduction through health state compression and metric aggregation

• install_doctor

  Check that this installation actually works. Runs the real hook binaries with synthetic payloads and asserts a large read

• intelligent-assistant

  Provides intelligent assistance including contextual help, suggestions, explanations, and troubleshooting

• knowledge_graph

  Build and query knowledge graphs with 91% token reduction through intelligent caching. Supports graph building, pattern querying, path finding, community detection, node ranking, relation inference, visualization, and export.

• log_dashboard

  Interactive log analysis dashboard with filtering, searching, pattern detection, and 90% token reduction through intelligent caching and compression

• metric_collector

  Comprehensive metrics collection and aggregation with multi-source support, time-series compression, and 88% token reduction through delta encoding and intelligent caching

• model_routing

  Which model tier this project's work actually goes better on, measured from episode outcomes in the client transcript

• monitoring_integration

  External monitoring platform integration with 87% token reduction through data compression and intelligent caching

• natural-language-query

  Natural language query translation and optimization

• optimize_session

  Analyzes operations in the current session from the session JSONL log, identifies large text blocks from file-based tools (Read, Write, Edit), compresses them, and stores them in the cache to reduce future token usage. Returns a summary of the optimization.

• optimize_text

  Compress and cache text to reduce token usage. Returns compressed version and saves to cache for future use.

• outcome_report

  Record correctness-first task outcome and deterministic grader evidence.

• pattern-recognition

  Pattern detection and analysis in logs, metrics, and events

• performance-tracker

  Tracks and analyzes performance metrics (CPU, memory, response times, throughput) with advanced statistical capabilities. Supports 8 operations: track, query, analyze-trends, forecast, compare, detect-regressions, get-baseline, generate-report. Achieves 89%+ token reduction through intelligent caching and data aggregation.

• predictive-analytics

  Predictive modeling and forecasting for system metrics

• predictive_cache

  ML-based predictive caching with 91%+ token reduction using ARIMA, exponential smoothing, LSTM, and collaborative filtering

• recommendation-engine

  Intelligent recommendations for optimization and resource allocation

• smart-dashboard

  Unified dashboard management with widget management and multi-source data integration. Supports 8 operations: check, register-check, update-check, delete-check, get-status, get-history, configure-dependencies, get-impact. Achieves 87% token reduction through status caching and dependency graph compression.

• smart_api_fetchwrite action

  Execute HTTP requests with intelligent caching and retry logic. Features: - Automatic retry with exponential backoff (1s, 2s, 4s, 8s) - Response caching with TTL-based invalidation (default: 5 minutes) - Request deduplication for in-flight requests - Circuit breaker pattern (opens after 5 consecutive failures) - ETag/Cache-Control header support - 83% average token reduction through intelligent ou

• smart_ast_grep

  Perform structural code search with 83% token reduction through AST indexing and caching

• smart_branch

  List and manage git branches with 60% token reduction through structured JSON output and smart filtering

• smart_buildwrite action

  Run TypeScript build with intelligent caching, diff-based change detection, and token-optimized output

• smart_cache

  Advanced multi-tier cache with 90%+ token reduction, 6 eviction strategies, stampede prevention, and automatic tier management

• smart_cache_api

  API Response Caching with 83% token reduction through intelligent cache management. Features: - Multiple caching strategies (TTL, ETag, Event-based, LRU, Size-based) - Intelligent cache key generation with query normalization - Pattern-based and tag-based invalidation - Stale-while-revalidate support - Cache hit rate analysis and recommendations - Cache warming and preloading Actions: - get: Retri

• smart_complexity

  Analyze code complexity metrics including cyclomatic, cognitive, Halstead, and maintainability index (70-80% token reduction)

• smart_config_read

  Read and parse configuration files (JSON, YAML, TOML) with 83% token reduction through schema-aware caching and intelligent diffing

• smart_database

  Database query optimizer with connection pooling, circuit breaking, and 83% token reduction. Supports query execution, EXPLAIN analysis, performance optimization, health monitoring, slow query detection, and batch operations.

• smart_dependencies

  Analyze project dependencies with 83% token reduction through graph caching and incremental updates

• smart_diff

  Get git diffs with 85% token reduction through diff-only output and smart filtering

• smart_docker

  Docker operations with build/run/stop/logs support, image layer analysis, and optimization suggestions

• smart_edit

  Edit files with 90% token reduction through line-based operations and diff-only output

• smart_env

  Smart environment variable analyzer with security checking and suggestions (83% token reduction)

• smart_exports

  Analyze TypeScript/JavaScript export statements with intelligent caching. Tracks exports, detects unused exports, and provides optimization suggestions. Achieves 75-85% token reduction through export analysis summarization.

• smart_glob

  Search files with glob patterns and 75% token reduction through path-only results and smart filtering

• smart_graphql

  GraphQL query optimizer with complexity analysis and caching (83% token reduction)

• smart_grep

  Search file contents with 80% token reduction through match-only output and smart filtering

• smart_imports

  Analyze TypeScript/JavaScript import statements with intelligent caching. Detects unused imports, missing imports, and provides optimization suggestions. Achieves 75-85% token reduction through import analysis summarization.

• smart_install

  Package installation with dependency analysis, conflict detection, and smart caching for npm/yarn/pnpm

• smart_lintwrite action

  Run ESLint with intelligent caching, incremental analysis, and auto-fix suggestions

• smart_log

  Get git commit history with 75% token reduction through structured JSON output and smart filtering

• smart_logs

  System log aggregation and analysis with multi-source support, pattern filtering, error detection, and insights

• smart_merge

  Manage git merges with 80% token reduction through structured status and conflict management

• smart_migration

  Database migration tracker with status monitoring and 83% token reduction. Supports listing migrations, checking status, viewing history, rollback operations, and migration generation.

• smart_network

  Network diagnostics and monitoring with connectivity testing, port scanning, DNS resolution, and anomaly detection

• smart_orm

  ORM query optimizer with N+1 detection (83% token reduction)

• smart_package_json

  Analyze package.json with dependency resolution, version conflict detection, and security scanning. Provides 83% token reduction through intelligent caching.

• smart_processes

  Monitor and analyze system processes with anomaly detection and resource tracking

• smart_read

  Read files with 80% token reduction through intelligent caching, diff-based updates, and syntax-aware optimization

• smart_refactor

  Provides intelligent refactoring suggestions with code examples and impact analysis (75-85% token reduction)

• smart_rest

  REST API analyzer with endpoint discovery and health scoring (83% token reduction)

• smart_schema

  Database schema analyzer with intelligent caching and 83% token reduction. Supports PostgreSQL, MySQL, and SQLite. Provides schema introspection, relationship analysis, index recommendations, and schema diff.

• smart_security

  Security vulnerability scanner with pattern detection and intelligent caching (83% token reduction)

• smart_sql

  SQL query analyzer with optimization suggestions and execution plan analysis (83% token reduction)

• smart_status

  Get git status with 70% token reduction through status-only output and smart filtering

• smart_symbols

  Extract and analyze TypeScript/JavaScript symbols with scope, type, and reference information (75-85% token reduction)

• smart_system_metrics

  System resource monitoring with CPU, memory, disk usage tracking, anomaly detection, and performance recommendations

• smart_testwrite action

  Run the project's tests (Jest, Vitest, Mocha, AVA or node --test) with

• smart_tsconfig

  Parse and analyze TypeScript configuration with 83% token reduction. Resolves extends chains, detects issues, and caches results for 7 days.

• smart_typecheckwrite action

  Run TypeScript type checking with intelligent caching and categorized error reporting

• smart_typescript

  Incremental TypeScript compilation with dependency tracking and intelligent caching (83% token reduction)

• smart_websocket

  WebSocket connection manager with message tracking (83% token reduction)

• smart_workflow

  Intelligent CI/CD workflow file analysis with 83% token reduction. Analyzes GitHub Actions, GitLab CI, CircleCI, and Azure Pipelines workflows with syntax validation, security analysis, and performance recommendations.

• smart_writewrite action

  Write files with 85% token reduction through verification, atomic operations, and change tracking

• token_audit

  The one thing to run. A single ranked queue of what is costing the most in this project -- waste detectors, prompt-cache

• waste_audit

  Report behavioural token waste in this project, ranked by cost per session and compared against the previous week.

• Code scan1333 source files scanned10/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 0 days ago15/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Grade history

• 2026-09-19restoreD → Cscore 69: npm install lifecycle script present; eval / new Function used; npm install lifecycle script present

Token Optimizer: common questions

Is Token Optimizer MCP server safe?

With care: it is graded C, so read the findings first (69/100). Read the Token Optimizer safety report

How do I install Token Optimizer?

It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.

Does Token Optimizer need an API key?

No secret keys are declared. It reads 1 setting from the environment.

Is Token Optimizer maintained?

The last commit was in the last day (2026-09-19). The latest release is v7.2.0.

What can I use instead of Token Optimizer?

Servers from other publishers that do the same job: Visual Memory MCP server.