STACK CHECK DOCS PRICING GET STARTED

// MCP TOOL REFERENCE

F Risk Grade Hi-AI · worst category: Destructive

HI-AI TOOLS

36 tools from the Hi-AI MCP Server, categorised by risk level.

View the Hi-AI policy →

// ALL 36 HI-AI TOOLS

READ 22 tools

Read analyze_complexity complexity|how complex|complexity|how complex|difficulty - Analyze code complexity Read analyze_problem analyze this|how to approach|break this down|problem analysis|examine|investigate - Break down complex prob... Read analyze_prompt analyze prompt|rate this|score|how good|prompt quality|evaluate prompt|assess - Analyze prompt quality and ... Read analyze_requirements requirements analysis|what we need|requirements analysis|what we need|analyze requirements|essential featur... Read break_down_problem break down|divide|split into parts|decompose|step by step|subdivide - Break complex problems into sub-problems Read check_coupling_cohesion coupling|cohesion|coupling|cohesion|dependencies check|module structure - Check coupling and cohesion Read enhance_prompt_gemini prompt improvement|gemini strategies|quality improvement|prompt enhancement|gemini strategies|quality impro... Read feature_roadmap roadmap|schedule|timeline|roadmap|timeline|project plan|development schedule - Generate development roadmap Read find_references where used|references|usages|find usage|references|where used - Find symbol references Read find_symbol find function|where is class|variable location|find function|where is|locate - Find symbol definitions Read get_coding_guide guide|rules|convention|guide|rules|convention|standards|best practices - Get coding guide Read get_current_time what time|current time|time now|get time - Get current time Read inspect_network_requests network|API calls|check requests|network|API calls|check requests|network traffic - Inspect network requests Read list_memories list|saved items|show saved|what memories - List saved memories Read monitor_console_logs console log|check errors|show logs|console|check logs|debug output|console errors - Monitor browser console Read prioritize_memory important|priority|prioritize|what matters - Prioritize memories by importance Read recall_memory recall|remember|what was|remind|retrieve - Retrieve from memory Read search_memories find|search|look for|query memories - Search memories by content Read step_by_step_analysis step by step|one at a time|gradually|step by step|one by one|gradually - Perform detailed step-by-step anal... Read suggest_improvements improve|make better|refactoring|improve|make better|refactor|optimize|enhance code - Suggest improvements Read think_aloud_process think about|consider|what do you think|think about it|let me think|reasoning - Generate think-aloud reasoni... Read validate_code_quality quality|review|check|quality|review code|check quality|validate|code review - Validate code quality

WRITE 10 tools

Write apply_quality_rules apply rules|apply standards|apply rules|apply standards|follow conventions|apply - Apply quality rules Write apply_reasoning_framework reasoning framework|systematic analysis|logical thinking|structured reasoning|methodical approach - Apply 9... Write auto_save_context commit|checkpoint|backup|compress|auto-save - Auto-save and compress context Write create_thinking_chain thinking process|chain of thought|reasoning chain|thought flow|sequential thinking - Create sequential thin... Write create_user_stories story|user story|user story|user stories|as a user - Generate user stories from requirements Write format_as_plan as a plan|organize|checklist|format as plan|make a plan|organize this|checklist - Format content into clear... Write generate_prd PRD|product requirements document|product requirements|requirements document|spec document - Generate Produ... Write restore_session_context restore|revert|go back|recover session - Restore previous session context Write save_memory remember|save|store|memorize|keep - Save to long-term memory Write update_memory update|modify|change|edit memory - Update existing memory

DESTRUCTIVE 2 tools

Destructive delete_memory forget|delete|remove|erase - Delete specific memory Destructive enhance_prompt be specific|more detail|clarify|elaborate|vague|enhance|improve prompt - Transform vague requests into clea...

EXECUTE 2 tools

Execute preview_ui_ascii create page|build UI|design component|make page|develop page - Preview UI before coding Execute start_session hi-ai|hello|start|begin session - Start session with context

// FAQ

How many tools does the Hi-AI MCP server have? +

The Hi-AI MCP server exposes 36 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Hi-AI tools? +

Route the Hi-AI server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard; they are enforced on every call before it reaches the server.

What risk categories do Hi-AI tools fall into? +

Hi-AI tools are categorised as Read (22), Write (10), Destructive (2), Execute (2). Each category has a recommended default policy.

Enforce policy on every Hi-AI tool call.

Start from Hi-AI, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Instant setup, no code required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.