SOJO Planning Assistant MCP Server

Endpoint

Hosted endpoint · transport

Connect

This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):

For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:

If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:

Tools

• query_database — ⭐ PRIMARY TOOL - Use this FIRST for any SOJO-specific question. This tool uses intelligent RAG retrieval to find SQL patterns, documentation, and domain knowledge. It handles production data, equipment specs, machine capabilities, and company-specific information. ⚠️ PRODUCTION vs MACHINE DATA: - Production totals ("how many did we produce?") → Assembly Build views (NetSuite) - Efficiency/uptime…
• list_tables — List available tables in a database schema. ⚠️ PREFER query_database FIRST - It has built-in knowledge of table structures and optimized SQL patterns. Only use list_tables if query_database doesn't have the information you need. Databases: - planning (default): SYSTEMS_DATA.METADATA (changeovers, line specs) + SYSTEMS_DATA.SILVER (PLANNING_FORMAT, NS_MAIN pricing/margins) + SYSTEMS_DATA.SILVER (…
• describe_table — Get table schema (columns, data types). ⚠️ PREFER query_database FIRST - It has built-in knowledge of table schemas and optimized SQL patterns for common queries (profitability, changeovers, efficiency). Only use describe_table if you need raw column details not available through query_database. Key tables (with schema): - ITEM_SOP_RECORD (SYSTEMS_DATA.SILVER): SOP operational data (headcount, p…
• get_table_sample — Get sample rows from a table. ⚠️ PREFER query_database FIRST - It has optimized SQL patterns that already know the correct columns and joins. Only use get_table_sample for edge cases where you need to see raw data not covered by query_database. Returns first N rows (default: 5).
• analyze_dieline — ALWAYS use this tool when a user uploads or shares a carton, dieline, packaging blueprint, or box drawing image — even if they just ask "what are the dimensions?" Do NOT try to read dimensions from the image yourself — this tool has reference guides and CLIP matching that produce far more accurate results. Also use this tool for: "carton dimensions", "case dimensions", "flap dimensions", "can thi…
• analyze_pallet_pattern — Check pallet pattern compatibility against SOJO's commissioned patterns. THREE-STEP PROCESS (mirrors dieline analysis): STEP 0 — GET REFERENCES: Call with pack_config ONLY (and optionally can_size, shipper_type). Returns all commissioned patterns grouped by palletizer (DMM, Vention Cobot, Vention Industrial, Top Tier) with shipper dims, cases/layer, layers, efficiency. Also returns CLIP vi…

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.

Work with this as data

Every MCP server here is available over the APIs.io API and to AI agents over MCP.

curl "https://apis.io/api/v1/mcp/sojo-planning-assistant-mcp-server"

curl "https://apis.io/api/v1/mcp?limit=25"