extract_url — extract MCP Tool
extract_url
(extract url) is one of 35 tools on the
extract
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call extract_url from your client
- Claude Code extract extract_url run in your project directory
- Claude Desktop extract extract_url ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor extract extract_url ~/.cursor/mcp.json
- VS Code extract extract_url .vscode/mcp.json
- Zed extract extract_url ~/.config/zed/settings.json
- Windsurf extract extract_url ~/.codeium/windsurf/mcp_config.json
- Cline extract extract_url ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI extract extract_url ~/.gemini/settings.json
- Grok extract extract_url .mcp.json (in your project root)
- ChatGPT extract extract_url Settings → Connectors → Advanced → Developer mode
- Claude.ai extract extract_url Settings → Connectors → Add custom connector
- LangChain extract extract_url pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http extract https://mart402.com/mcpOther tools on this server
- get_catalog
- quote_parse
- get_receipt
- search_x402_services
- get_sample
- portrait_precheck
- operator_history
- parse_document
- ocr_image
- verify_invoice
- enrich_company
- structured_extract
- jp_company_profile
- document_pipeline
- pdf_merge
- pdf_pages
- pdf_info
- meal_vision
- style_profile
- style_report
- report_pack
- portrait_analysis
- jp_payroll_net
- jp_bonus_net
- jp_social_insurance
- jp_dependent_threshold
- jp_consumption_tax
- jp_business_days
- jp_overtime_wage
- jp_retirement_tax
- jp_mortgage
- jp_payslip_audit
- jp_crypto_tax
- jp_payroll_suite
This list was read from the server itself, by connecting to it and calling tools/list on 24 September 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.