Connection check
local install
token-optimizer-mcp
Context-window optimization: caching, compression & smart file tools that cut tokens 60-90%.
Tools
86
GitHub stars
508
Installs / wk
3.2k
Licence
MIT
Transport
stdio
Last checked
never
Tools & capabilities
86 toolsRead from the published package source — this server runs locally, so there is no endpoint to query. Names are taken from the code, not observed at runtime, and descriptions are often absent.
alert_manager
from source
analyze_optimization
from source
Analyze text and provide recommendations for optimization including compression benefits and token savings. Analyze text and provide recommendations for optimization including compression benefits and token savings.
analyze_project_tokens
from source
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 ef… 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
from source
autoremediation
from source
cache_analytics
from source
cache_compression
from source
cache_invalidation
from source
cache_optimizer
from source
cache_partition
from source
cache_replication
from source
cache_warmup
from source
checkpoint_handoff
from source
clear_cache
from source
Clear all cached data. Use with caution. Clear all cached data. Use with caution.
cognition_record
from source
compress_text
from source
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 LL… 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_page
from source
context_receipt_verify
from source
count_tokens
from source
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 f… 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_widget
from source
data_visualizer
from source
decompress_text
from source
Decompress base64-encoded Brotli-compressed text. Decompress base64-encoded Brotli-compressed text.
export_analytics
from source
get_action_analytics
from source
get_cached
from source
Retrieve previously cached and optimized text. Returns the original text if found in cache. Retrieve previously cached and optimized text. Returns the original text if found in cache.
get_cache_stats
from source
Get cache statistics including hit rate, compression ratio, and token savings. Get cache statistics including hit rate, compression ratio, and token savings.
get_hook_analytics
from source
get_mcp_server_analytics
from source
get_optimization_report
from source
get_session_stats
from source
Get comprehensive statistics from the PowerShell wrapper session tracker including system reminders, tool operations, and total tokens with accurate tiktoken-based counting. Get comprehensive statistics from the PowerShell wrapper session tracker including system reminders, tool operations, and total tokens with accurate tiktoken-based counting.
health_monitor
from source
knowledge_graph
from source
log_dashboard
from source
metric_collector
from source
monitoring_integration
from source
optimize_session
from source
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 t… 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
from source
Compress and cache text to reduce token usage. Returns compressed version and saves to cache for future use. Compress and cache text to reduce token usage. Returns compressed version and saves to cache for future use.
outcome_report
from source
predictive_cache
from source
sentiment_analysis
from source
smart_ast_grep
from source
smart_branch
from source
smart_build
from source
smart_cache
from source
smart_complexity
from source
smart_config_read
from source
smart_cron
from source
smart_database
from source
smart_dependencies
from source
smart_diff
from source
smart_docker
from source
smart_edit
from source
smart_env
from source
smart_exports
from source
smart_graphql
from source
smart_imports
from source
smart_install
from source
smart_lint
from source
smart_log
from source
smart_logs
from source
smart_merge
from source
smart_migration
from source
smart_network
from source
smart_orm
from source
smart_package_json
from source
smart_pretty
from source
smart_process
from source
smart_processes
from source
smart_read
from source
smart_refactor
from source
smart_rest
from source
smart_schema
from source
smart_security
from source
smart_service
from source
smart_sql
from source
smart_status
from source
smart_symbols
from source
smart_system_metrics
from source
smart_test
from source
smart_tsconfig
from source
smart_typecheck
from source
smart_typescript
from source
smart_user
from source
smart_websocket
from source
smart_workflow
from source
smart_write
from source