LeanCTX provides 61 MCP tools organized into six categories. Each tool is used by the AI automatically - you don't need to learn or type any of these commands.
Core Tools - File & Code
The foundation. These handle file reading, directory exploration, command execution, and code search - the operations that make up 90% of AI coding interactions.
| Tool | What it does | Savings |
|---|---|---|
ctx_read | Smart file read with 10 read modes + session caching | up to 99% |
ctx_multi_read | Batch file reads in one call | fewer round-trips |
ctx_tree | Compact project structure maps | 34-60% |
ctx_shell | Shell commands with 60+ pattern compression. Use raw=true for uncompressed output. | |
ctx_search | Regex code search with compact results | 50-80% |
ctx_edit | Context-aware file editor with create, replace, and replace_all | - |
ctx_delta | Show only changed lines since last read | 80-95% |
ctx_smart_read | Intelligent single-call read with auto-mode | varies |
View full Core Tools documentation →
Intelligence Engine
Tools that go beyond compression - they understand your workflow, detect intent, deduplicate context, and intelligently manage token budgets.
| Tool | What it does |
|---|---|
ctx_fill | Priority-based context filling with a token budget |
ctx_intent | Semantic intent detection + auto file loading |
ctx_context | Multi-turn context state overview |
ctx_graph | Persistent project dependency graph (build, related, symbol, impact) |
ctx_dedup | Cross-file deduplication analysis |
ctx_response | Bi-directional response compression |
ctx_discover | Shell history analysis for missed compression opportunities |
ctx_preload | Proactive context loader - caches task-relevant files at session start |
ctx_semantic_search | Hybrid semantic search (BM25 + embeddings) - find code by meaning, even without keyword overlap |
ctx_overview | Project overview with structure, entry points, and key files |
ctx_prefetch | Pre-load files based on task context and changed files |
ctx_graph_diagram | Mermaid diagrams for dependency graph or call graph |
ctx_compress_memory | Compress memory/config markdown (preserve code/URLs) + create .original backup |
ctx_impact | Impact analysis: trace dependency chains and build graphs |
ctx_architecture | Graph-based architecture analysis: clusters, layers, cycles |
ctx_analyze | Entropy analysis - recommends optimal compression mode |
View full Intelligence Engine documentation →
Session & Monitoring
Session persistence, performance monitoring, compression analysis, and benchmarking - everything you need to measure and optimize your token savings.
| Tool | What it does |
|---|---|
ctx_session | Cross-chat session memory (task, findings, decisions) |
ctx_compress | Compact context checkpoint for chat continuation |
ctx_benchmark | Real token counts per mode - single file or project-wide |
ctx_metrics | Session statistics with USD cost estimates |
ctx_wrapped | Savings report card (weekly / monthly / all-time) |
ctx_cache | Explicit cache management (status, clear, invalidate) |
ctx_gain | Query token savings, GainScore (0–100), cost breakdowns, task classifications, and per-agent statistics. Powered by the GainEngine with embedded ModelPricing. |
ctx_heatmap | File access heatmap - find hot files and cold directories |
View full Session & Monitoring documentation →
Memory & Multi-Agent
Cross-session memory, multi-agent coordination, and task-aware project orientation. New in v2.7.0.
| Tool | What it does |
|---|---|
ctx_knowledge | Persistent project knowledge store - remember facts across sessions |
ctx_agent | Multi-agent coordination - register, post, handoff tasks, sync status |
ctx_share | Multi-agent context sharing - push/pull cached file contexts between agents |
ctx_task | Task delegation and tracking across agents |
ctx_cost | Cost attribution - track token spend per agent and tool |
View full Memory & Multi-Agent documentation →
Workflow & Orchestration
State machines, context handoff, sandboxed code execution, and quality feedback loops.
| Tool | What it does |
|---|---|
ctx_workflow | State-machine workflows with step ordering and evidence |
ctx_handoff | Context transfer between sessions or agents |
ctx_execute | Sandboxed code execution in 11 languages |
ctx_feedback | Quality feedback: latency, token counts, model info |
View Workflow & Orchestration docs →
Analysis & Navigation
Tree-sitter-powered symbol navigation, call graphs, route extraction, and structural outlining.
| Tool | What it does |
|---|---|
ctx_symbol | Find symbol definitions across 18 languages |
ctx_callers | Find all call sites of a function |
ctx_callees | Find all functions called by a symbol |
ctx_outline | Structural outline of a file |
ctx_routes | Extract HTTP routes from web frameworks |
ctx_smells | Code smell detection with graph-enriched scoring (long functions, deep nesting, complexity) |