Search for relevant tools using Vector Search + Knowledge Graph.

This tool finds the most relevant MCP servers, skills, and tools for a given query. It uses semantic similarity (ChromaDB) to find matches and optionally expands results using the Knowledge Graph to include dependencies.

Args:

• query (string): Natural language query (e.g., "n8n workflow automation")

• limit (number): Maximum tools to return (default: 10, max: 50)

• include_graph (boolean): Expand with Knowledge Graph (default: true)

• response_format ('json' | 'markdown'): Output format (default: 'json')

Returns: JSON format: { "results": [ { "name": "n8n-workflow-builder", "type": "MCP_Server", "description": "Create and manage n8n workflows", "similarity": 0.89 } ], "stats": { "vectorCount": 3, "graphCount": 4, "totalCount": 7, "tokenEstimate": 7000, "savingsPercent": 92.1 } }

Examples:

• "n8n 워크플로우 자동화" → n8n-workflow-builder, n8n-node-templates, ...

• "TikTok 데이터 분석" → sqlite_tiktok_analytics, pandas-excel, ...

• "Excel 리포트 생성" → pandas-excel, 데이터-구조-파악, ...

Use this tool when you need to find which tools are relevant for a task.

Expand a tool to find its dependencies via Knowledge Graph.

Given a tool name, traverse the Knowledge Graph to find related tools, requirements, and dependencies. Useful for understanding what other tools are needed to complete a task.

Args:

• tool_name (string): Name of the tool to expand (e.g., 'n8n-workflow-builder')

• depth (number): Traversal depth (default: 2, max: 4)

• relation_types (string[]): Filter by relation types (optional)

• response_format ('json' | 'markdown'): Output format

Relation types:

• REQUIRES: Tool A requires Tool B to function

• WORKS_WITH: Tools that commonly work together

• EXECUTABLE_VIA: Tool can be executed via another tool

• OUTPUTS_TO: Tool outputs data to another tool

• BENEFITS_FROM: Tool benefits from using another tool

Returns: { "tool": "n8n-workflow-builder", "dependencies": [ { "name": "n8n-node-templates", "type": "Skill", "relation": "BENEFITS_FROM" } ], "totalCount": 4 }

Use this tool when you know a primary tool and need to find related tools.

Get a complete tool cluster for a task query.

This combines vector search and graph expansion to return a complete set of tools needed for a task. Includes primary tools (semantic matches) and their dependencies (graph expansion), plus usage context.

Args:

• query (string): Natural language task description

• include_context (boolean): Include usage patterns and examples (default: true)

• response_format ('json' | 'markdown'): Output format

Returns: { "primary": [ { "name": "n8n-workflow-builder", "type": "MCP_Server", ... } ], "dependencies": [ { "name": "n8n-node-templates", "type": "Skill", ... } ], "context": { "usagePatterns": ["Use MCP servers for data operations", ...], "examples": ["Primary workflow: n8n-workflow-builder - ...", ...] }, "stats": { "totalTools": 7, "tokenEstimate": 7000, "savingsPercent": 92.1 } }

Use this tool for complete task setup - returns everything needed to start working.

Register a new MCP server or skill to Progressive Loader.

Use this to add tools that can be discovered via toolhub_search.

Args:

• name: Unique tool name (e.g., 'markitdown', 'my-skill')

• type: 'MCP_Server', 'Skill', 'Tool', or 'Command'

• description: What the tool does

• mcpCli: (for MCP_Server) mcp-cli usage info with quickStart, examples, tools

• skillMeta: (for Skill) metadata with summary, when, tokenSize, keywords

Example for MCP_Server: { "name": "markitdown", "type": "MCP_Server", "description": "Convert files to markdown", "mcpCli": { "quickStart": "mcp-cli markitdown convert_to_markdown --uri 'file:///path'", "examples": ["# Convert PDF", "mcp-cli markitdown convert_to_markdown --uri 'file:///doc.pdf'"], "tools": [{"name": "convert_to_markdown", "params": ["uri"]}] } }

Delete a tool from Progressive Loader.

Args:

• tool_id: ID of the tool to delete (usually the tool name)

Use toolhub_list to find tool IDs.

List all tools registered in Progressive Loader with pagination support.

Args:

• type_filter: Filter by type ('MCP_Server', 'Skill', 'Tool', 'Command', 'all')

• limit: Maximum number of tools per page (default: 20, max: 100)

• offset: Number of tools to skip for pagination (default: 0)

Returns count by type, paginated tool list, and pagination info.

Build a tool chain structure based on cluster results or manual definition.

This tool generates chain structures from queries or validates manual chain definitions. It does NOT execute the chain - use toolhub_chain for execution.

Args:

• query (string, optional): Natural language query for auto chain generation

• mcpPath (ChainStep[], optional): Manual chain definition

• autoChain (boolean): If true, generate chain from query (default: true)

• trace (boolean): Enable execution trace for debugging (default: false)

ChainStep format: { "toolName": "sqlite_tiktok_read_query", "toolArgs": "{"query": "SELECT * FROM daily_metrics"}", "inputPath": "$.data", // Optional: JSONPath for input "outputPath": "$.results" // Optional: JSONPath for output }

Examples: Auto chain: { "query": "TikTok 데이터 → Excel 리포트" }

Manual chain: { "mcpPath": [ { "toolName": "sqlite_tiktok_read_query", "toolArgs": "{"query": "SELECT * FROM daily_metrics"}" }, { "toolName": "pandas_excel_create", "toolArgs": "{"data": "CHAIN_RESULT"}" } ], "autoChain": false }

Returns: { "success": true, "result": "...", "chain": { "steps": [...], "executionOrder": [...] }, "trace": [...] // if trace enabled }

Execute a chain of MCP tools sequentially.

Each tool receives the result from the previous tool via CHAIN_RESULT placeholder.

Args:

• mcpPath: Array of tool configurations with:

  • toolName: Full tool name (e.g., 'sqlite_tiktok_read_query')

  • toolArgs: JSON string with arguments

  • inputPath: Optional JSONPath for input filtering

  • outputPath: Optional JSONPath for output filtering

  • outputTransform: Optional data transformation

Example: { "mcpPath": [ { "toolName": "sqlite_tiktok_read_query", "toolArgs": "{"query": "SELECT * FROM daily_metrics"}", "outputTransform": "sqlite→2d" }, { "toolName": "document_edit_create_excel_file", "toolArgs": "{"filepath": "/tmp/report.xlsx", "content": "CHAIN_RESULT"}" } ] }

Returns the final result from the chain execution.

Rediscover tools from all configured MCP servers.

Call this to refresh the list of available tools for chaining. Useful after adding new MCP servers or if tools seem unavailable.

Returns the count and list of discovered tools.

List all tools available for chain execution.

Returns the names of all discovered MCP tools that can be used with toolhub_chain.

Analyze a tool chain and provide related skills, schemas, and transform recommendations.

Call this BEFORE executing a chain to get:

1. Related skills from Knowledge Graph (for reference/patterns)

2. Input schemas for each tool (for correct argument formatting)

3. Recommended transforms between steps (for data compatibility)

Args:

• mcpPath: Array of chain steps to analyze

• include_skills: Include related skills (default: true)

• include_schemas: Include tool schemas (default: true)

• include_transforms: Include transform recommendations (default: true)

Returns: { "steps": [ { "toolName": "sqlite_tiktok_read_query", "inputSchema": {...}, "relatedSkills": [ { "name": "데이터-구조-파악", "summary": "...", "relation": "BENEFITS_FROM" } ], "recommendedTransform": "sqlite→2d" } ], "skillsToLoad": ["n8n-node-templates", "pandas-excel-작업"], "chainValidation": { "valid": true, "warnings": [] } }

Use this to prepare context before toolhub_chain execution.

Check Tool Hub service status.

Returns:

• chromadb: Connection status to vector database

• knowledgeGraph: Knowledge graph file status

• toolCount: Number of registered tools

• version: Server version