risk_tail_models — Risk Desk MCP Tool
risk_tail_models
(risk tail models) is one of 29 tools on the
Risk Desk
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call risk_tail_models from your client
- Claude Code Risk Desk risk_tail_models run in your project directory
- Claude Desktop Risk Desk risk_tail_models ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor Risk Desk risk_tail_models ~/.cursor/mcp.json
- VS Code Risk Desk risk_tail_models .vscode/mcp.json
- Zed Risk Desk risk_tail_models ~/.config/zed/settings.json
- Windsurf Risk Desk risk_tail_models ~/.codeium/windsurf/mcp_config.json
- Cline Risk Desk risk_tail_models ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI Risk Desk risk_tail_models ~/.gemini/settings.json
- Grok Risk Desk risk_tail_models .mcp.json (in your project root)
- ChatGPT Risk Desk risk_tail_models Settings → Connectors → Advanced → Developer mode
- Claude.ai Risk Desk risk_tail_models Settings → Connectors → Add custom connector
- LangChain Risk Desk risk_tail_models pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http riskdesk https://riskdesk.avidquant.com/mcpOther tools on this server
- risk_desk_status
- risk_tail
- risk_exposure
- risk_stress
- risk_backtest
- risk_derivatives_greeks
- risk_derivatives_grid
- risk_derivatives_historical
- risk_covariance
- risk_var_attribution
- risk_es_attribution
- risk_factor_exposure
- risk_limits
- risk_what_if
- risk_liquidity
- risk_stress_replay
- risk_reverse_stress
- risk_scenario_scale
- risk_saccr
- risk_exposure_profile
- risk_credit_asrf
- risk_credit_copula
- risk_frtb_imcc
- risk_frtb_ima_capital
- risk_frtb_pla
- risk_frtb_backtest
- risk_frtb_sbm_fx
- risk_scenario_library
This list was read from the server itself, by connecting to it and calling tools/list on 10 November 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.