risk_read — tw market data MCP Tool
risk_read
(risk read) is one of 41 tools on the
tw market data
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call risk_read from your client
- Claude Code tw market data risk_read run in your project directory
- Claude Desktop tw market data risk_read ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor tw market data risk_read ~/.cursor/mcp.json
- VS Code tw market data risk_read .vscode/mcp.json
- Zed tw market data risk_read ~/.config/zed/settings.json
- Windsurf tw market data risk_read ~/.codeium/windsurf/mcp_config.json
- Cline tw market data risk_read ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI tw market data risk_read ~/.gemini/settings.json
- Grok tw market data risk_read .mcp.json (in your project root)
- ChatGPT tw market data risk_read Settings → Connectors → Advanced → Developer mode
- Claude.ai tw market data risk_read Settings → Connectors → Add custom connector
- LangChain tw market data risk_read pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http tw-market-data https://mcp.twmarketdata.com/mcpOther tools on this server
- list_datasets
- describe_dataset
- query_dataset
- find_related
- search_filings
- explain_provenance
- get_inclusion_proof
- cite_this
- read_primary_text
- ask
- chart
- screen
- query_regime
- calendar
- compare
- get_code_example
- run_recipe
- try_sample
- run_backtest
- get_backtest
- replay_backtest
- list_backtests
- memory_save
- memory_search
- memory_get_watchlist
- memory_replay_query
- run_research
- get_research
- list_pending_actions
- approve_action
- list_alerts
- set_price_alert
- delete_alert
- risk_assess
- agent_activity
- list_factor_findings
- company_health_check
- positioning_read
- macro_regime_read
- supply_chain_read
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.