Analyze task complexity and route appropriately with chaos detection, baseline audit and orchestration

Unified M7 Memory System - 5-level cognitive hierarchy with FogOfWar

Memory Levels

• L0 (surface): Ephemeral, seconds-minutes

• L1 (working): Task context, hours-days

• L2 (longterm/project): Project patterns, weeks-months

• L3 (conceptual): Validated patterns, months-years

• L4 (global): Universal knowledge, permanent

Actions

• search: Cascade search L0→L4 with early stop

• search_level: Search specific level

• store: Store with auto-level (default L0)

• store_at: Store at specific level

• get: Get record by ID

• delete: Delete record (from memory AND disk)

• delete_bulk: Delete multiple records by IDs array

• invalidate_bulk: Invalidate multiple records by IDs array

• stats: Memory statistics (deduplicated)

• discover_technical: Add FogOfWar discovery

• query_fog_of_war: Query low confidence areas

• promote: Manual promotion to higher level

• consolidate: Submit validated L2+ summary for needs_consolidation records

• invalidate: Mark record as invalidated

• reload: Reload memory from disk (resync after manual edits)

Unified M7 session management - status, compliance, completion, enforcement

Unified M7 validation operations - audit, visual testing, dependencies, metrics

Manage task scope and prevent scope creep

Initialize complete M7 ecosystem for empty projects - creates Memory Bank, .cursorrules, project structure

Check error journal to avoid repeating past mistakes

[DEPRECATED v5.0] Use mcp_m7_cycle instead. Create M7 file structure for a task

Manage project schema (database, API, architecture) - prevents duplicate databases and maintains project consistency

Automatically generate and manage PROJECT_INDEX.md file with comprehensive project information for AI assistants

Check technology stack for safety patterns and potential issues

Get recommended patterns and antipatterns for a specific technology

Validate code implementation against safety patterns and best practices

Smart console monitoring and error capture

API contract registry management to prevent duplicate methods

Code Impact Analyzer - анализ реальных изменений кода

Simple test tool to verify MCP integration

Orchestrate multiagent collaboration for complex tasks using M7 Hive system.

v3.8.0 Features:

• DYNAMIC MODE (default): AI creates optimal expert team for each task

• PLANNED MODE (new): CNP auction-based coordination with task decomposition

• MODEL SELECTION: Best model chosen per agent based on LiveBench benchmarks

• SELF-LEARNING: System improves over time based on results

• GATEKEEPERS: Style, Architecture, Security validation

Use mode="dynamic" for quick expert analysis (default). Use mode="planned" for complex tasks requiring decomposition and validation. Use mode="fixed" for legacy behavior with predefined agents.

Manage project knowledge base - centralized documentation system with versioning and auto-sync

Safety pipeline: detect jailbreak patterns, verify intent, check outputs. Actions: scan_input | scan_output | full_check | verify_intent | catalog_stats

M7 Code Telemetry - manage consent, view statistics, help improve AI models

M7 v3.0 Style Guardian - Learn and enforce code style patterns.

Actions:

analyze

Analyze a project/directory to learn style patterns.

• path: Directory path to analyze (required)

validate

Validate code against learned style profile.

• code: Code to validate (required)

• file: File path for context

check

Quick check for errors only (blocking issues).

• code: Code to check (required)

• file: File path

fix

Auto-fix code where possible.

• code: Code to fix (required)

• file: File path

learn

Record a user correction for learning.

• original: Original (wrong) code (required)

• corrected: Corrected code (required)

• file: Source file

• context: Additional context

profile

Get current style profile.

stats

Get learning statistics.

export

Export all corrections as JSON.

import

Import corrections from JSON.

• corrections: JSON string of corrections (required)

clear

Clear all learned data.

M7 v3.0 Error Pattern Database - Track AI mistakes and provide preventive warnings.

Actions:

capture

Record an AI mistake.

• category: Error category (required): syntax, type, import, api, logic, style, security, performance, compatibility, other

• title: Error title (required)

• ai_mistake: What AI generated wrong (required)

• correct_solution: What it should have been (required)

• description: Detailed description

• explanation: Why it was wrong

• severity: critical, high, medium, low

• project_id: Project identifier

• tags: Array of tags

check

Check code for potential errors.

• code: Code to check (required)

• file: File path for context

search

Search the error database.

• query: Search text

• category: Filter by category

• severity: Filter by severity

• project_id: Filter by project

• limit: Max results (default: 20)

stats

Get error statistics.

• project_id: Filter by project (optional)

patterns

List or manage error patterns.

• pattern_action: list, enable, or disable

• pattern_id: Pattern ID for enable/disable

correct

Record a correction for an error.

• error_id: Error ID to correct (required)

• original_code: Original wrong code (required)

• corrected_code: Corrected code (required)

report_fp

Report a false positive warning.

• pattern_id: Pattern ID that gave false positive (required)

clear

Clear all error data.

Project Knowledge Graph - analyze code dependencies, detect cycles, find orphans, generate diagrams.

Actions:

build

Build graph from project directory.

• rootPath: Root directory to scan (required)

• include: File patterns to include (default: **/*.ts, **/*.tsx, **/*.js)

• exclude: File patterns to exclude (default: node_modules, dist)

status

Get current graph status and summary.

metrics

Get detailed graph metrics (nodes, edges, coupling, cohesion, health grade).

query

Query nodes with filters.

• nodeType: Filter by type

• name: Filter by name (regex)

• filePath: Filter by path

• limit: Max results

search

Search nodes by name.

• name: Name to search (required)

dependencies

Get dependencies of a node.

• nodeId: Node ID (required)

dependents

Get dependents of a node (what depends on it).

• nodeId: Node ID (required)

impact

Analyze impact of changing a node or file.

• nodeId: Node ID to analyze

• filePath: File path to analyze

cycles

Detect circular dependencies.

• maxCycles: Max cycles to return (default: 100)

• includeTypeOnly: Include type-only cycles

orphans

Find orphan code (unused exports).

diagram

Generate Mermaid diagram.

• diagramType: dependency, class, component, module, impact

• nodeId: Root node for impact diagram

• maxNodes: Max nodes to show

• direction: TB, BT, LR, RL

path

Find shortest path between two nodes.

• nodeId: Source node (required)

• targetId: Target node (required)

critical

Get most critical paths (highest impact nodes).

• limit: Number of nodes to return

export

Export graph to JSON.

import

Import graph from JSON.

• data: JSON string (required)

clear

Clear the graph.

Architectural Advisor - analyze architecture, detect antipatterns, generate C4 diagrams, suggest refactoring.

Actions:

• analyze: Full analysis with score (A-F grade)

• detect_antipatterns: Find architecture problems

• suggest_refactoring: Get actionable improvement steps

• generate_c4: Generate C4 architecture diagrams

• score: Quick score summary

• critical_issues: Only critical problems

• top_suggestions: Best improvement opportunities

M7 v3.0 Cross-Session Learning - Learn from session patterns across time.

Actions:

status

Check cross-session learning system status.

start

Start tracking a new session.

• session_id: Session ID to track (required)

record

Record an action in current session.

• action_data: { type, tool?, input, output, file?, success, userFeedback? }

get_context

Get full project learning context for AI prompts.

search

Search relevant knowledge.

• query: Search query (required)

• limit: Max results (default: 5)

validate

Validate an insight (user feedback).

• insight_id: Insight ID (required)

• valid: true/false (required)

ci_result

Record CI/CD result for insight validation.

• ci_result: { type, success, details?, affectedInsights? }

stats

Get learning statistics.

cleanup

Cleanup old/low-confidence data.

• cleanup_options: { olderThanDays?, belowConfidence? }

format_prompt

Format context for injection into AI prompt.

• query: Optional query for relevant knowledge

M7 Context Visualizer - interactive graph visualization of code dependencies.

Actions:

• start: Start the visualizer server (opens web UI)

• stop: Stop the visualizer server

• status: Check if server is running

• set_context: Update current file/task context

• get_graph: Get graph data as JSON

• focus: Focus on a specific node

• open: Get URL to open visualizer

The visualizer shows:

• Code dependency graph with live updates

• Current editing context ("You are here")

• Impact analysis (what changes affect)

• Navigation history

• Health metrics

Use 'start' to launch, then open the URL in browser.

Start or continue M7 cycle with explicit phase instructions. Use for structured task development through all 7 phases: intake → discovery → architecture → solution → impact → simulation → implementation.

Browse and load past Hive analysis reports.

Use "list" to see all saved reports with dates, topics, and sizes. Use "load" with a filename to bring a full report into the conversation context.

Reports are saved automatically when running mcp_m7_hive_coordinator. Use this tool to reference past analyses in follow-up discussions.

DCCE (Dual-Channel Content Envelope) — generate, validate, render and lint dual-channel content. Two channels: Human View (3-5 sentences for humans) and AI View (structured JSON for machines). AI stays AI, no mimicry.

M7 Mesh — Multi-instance communication and coordination.

Connects M7 instances across machines via relay server, or locally via SQLite.

Remote Relay Actions (set M7_MESH_RELAY, M7_MESH_SECRET, M7_WORKSTATION):

• sync: Full sync — push state, pull peers/changes/messages

• push: Push shared doc to relay (path, content)

• pull: Pull shared doc from relay (path)

• notify: Notify peers about file change (path, summary)

• changes: View file change feed from peers

• ask: Ask a question to specific peer or all (to, question)

• reply: Reply to a message (message_id, answer)

• inbox: View unread messages

• broadcast: Send note to all peers (message)

• log_task: Register M7 task in shared index (task_id, title, status, summary)

• tasks: View shared task index

• push-file: Read local file and push to relay (path) — auto-notifies peer

• pull-file: Pull file from relay and save to local disk (path)

• list-files: List all shared files on relay

Local Mesh Actions (legacy):

• init: Initialize mesh (auto-detects remote if configured)

• status: Show mesh health

• announce: Publish context

• peers: List peers

• request_context: Query peer context

DevOps registry: управление средами, валидация команд, история деплоев

M7 Warmup System — прогрев контекста проекта для нового чата. Загружает полную информацию о проекте и выдаёт отчёт для проверки.

M7 Doctor - диагностика и авто-исправление проблем с .m7/ директорией

Transfer tasks when scope grows beyond original estimate

View and explore the task dependency graph

Litany of Unbinding — AI confesses when it deviated from M7 methodology. Record freestyle mistakes, view the Wall of Shame, track heresy statistics.

Litany of Ignition — Recite sacred texts from the Codex Martianus before beginning work. The Inner Litany, the Sevenfold Rite, and random wisdom from the Archmagos-Forerunner.