Marketgenius MCP Server

Our free Marketgenius investment tools as live, interactive React MCP Apps.

Tools

Last Updated

Jun 14, 2026

What is the Marketgenius MCP Server?

The Marketgenius MCP server gives AI agents structured, permission-aware access to Marketgenius through the Model Context Protocol. With 17 pre-built actions, agents can read, create, and update Marketgenius data on behalf of authorized users.

Willow ships the Marketgenius MCP server as part of an enterprise control plane. Every call runs behind SSO (Okta, Azure AD), enforces RBAC and least-privilege at runtime, writes to a full audit trail, and integrates with Splunk and Loki for SIEM visibility. Connect from Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code, n8n, or any custom agent. Install once, distribute org-wide, and see exactly how Marketgenius is being used by every AI agent in your stack.

Tools

mg_list

List all available Marketgenius tools with their names, descriptions, categories, and resource URIs. Use mg_list to discover what's available, or filter by category.

mg_calculator_cagr

Open the CAGR Calculator React MCP App UI. ALWAYS ask first — never call this tool silently: "Open the calculator directly, or pre-fill it with your inputs?" IF directly → call this tool now with no params. STOP. Do not ask anything else. IF pre-fill → collect only the input schema fields — do not guess or invent field names.

mg_calculator_cagr_update

Update one or more fields in the already-open CAGR Calculator. ALWAYS call mg_calculator_cagr_state first — the user may have changed values manually in the GUI and you must not overwrite them. Pass the version you received from that call (or from the open tool if updating immediately after opening). Only pass the fields the user explicitly asked to change; omit all others. Send all changes in a single call — multiple sequential calls lose intermediate updates (only the last one applies).

mg_calculator_cagr_sync

Sync user-entered field values of the open CAGR Calculator back to the session store so the model can read them via the state tool. Called by the View after any field change; hidden from the model.

mg_calculator_cagr_state

Read the current field values of the open CAGR Calculator. Call this before answering any question about the current values — the user may have changed fields manually in the GUI. Do not call this on a loop; call it once on demand.

mg_calculator_dividend

Open the Dividend Calculator React MCP App UI. ALWAYS ask first — never call this tool silently: "Open the calculator directly, or pre-fill it with your inputs?" IF directly → call this tool now with no params. STOP. Do not ask anything else. IF pre-fill → ask "By amount invested or by number of shares?", then collect only the input schema fields matching that mode — do not guess or invent field names.

mg_calculator_dividend_update

Update one or more fields in the already-open Dividend Calculator. ALWAYS call mg_calculator_dividend_state first — the user may have changed values manually in the GUI and you must not overwrite them. Pass the version you received from that call (or from the open tool if updating immediately after opening). Only pass the fields the user explicitly asked to change; omit all others. Send all changes in a single call — multiple sequential calls lose intermediate updates (only the last one applies).

mg_calculator_dividend_sync

Sync user-entered field values of the open Dividend Calculator back to the session store so the model can read them via the state tool. Called by the View after any field change; hidden from the model.

mg_calculator_dividend_state

Read the current field values of the open Dividend Calculator. Call this before answering any question about the current values — the user may have changed fields manually in the GUI. Do not call this on a loop; call it once on demand.

mg_calculator_market_cap

Open the Market Cap Calculator React MCP App UI. ALWAYS ask first — never call this tool silently: "Open the calculator directly, or pre-fill it with your inputs?" IF directly → call this tool now with no params. STOP. Do not ask anything else. IF pre-fill → ask "Would you like to pre-fill share price and shares outstanding?", then collect only the input schema fields matching that mode — do not guess or invent field names.

1–10 of 17 tools

Customize Tools

Edit descriptions, modify arguments, select tools, or add new ones

Set Up Your Marketgenius MCP Server in Minutes

Add the following configuration to your MCP client. Authentication is handled via OAuth. Compatible with Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code, n8n, and any MCP-compatible agent.

Claude Desktop

claude_desktop_config.json

{
  "mcpServers": {
    "willow-marketgenius": {
      "type": "http",
      "url": "https://<org>.mcp-s.com/mcp/mcp/marketgenius"
    }
  }
}

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "willow-marketgenius": {
      "type": "http",
      "url": "https://<org>.mcp-s.com/mcp/mcp/marketgenius"
    }
  }
}

Claude Code

CLI

claude mcp add willow-marketgenius --transport http https://<org>.mcp-s.com/mcp/mcp/marketgenius

n8n

HTTP Request Node

{
  "url": "https://<org>.mcp-s.com/mcp/mcp/marketgenius",
  "method": "POST"
}

Or click "Install with Willow" above to set up automatically with SSO and RBAC preconfigured.

Enterprise Governance for Marketgenius

Willow adds the layer Marketgenius and every other SaaS doesn't ship out of the box: every call runs behind SSO (Okta, Azure AD), enforces RBAC and least-privilege at runtime, writes to full audit logs, and detects shadow AI usage across your stack. One MCP gateway. Any agent. Every tool.

Marketgenius MCP Server FAQ

What is the Marketgenius MCP server?

The Marketgenius MCP server is a Model Context Protocol implementation that lets AI agents like Claude, Cursor, and ChatGPT read and write Marketgenius data through a standardized interface. Willow hosts and governs this server so enterprises can roll it out without a security review backlog.

How is Willow's Marketgenius MCP server different from the official one?

The official Marketgenius MCP server is scoped to a single user's account and does not include enterprise governance. Willow's version adds SSO, RBAC, audit logging, shadow AI detection, and centralized control over which actions agents can take across the entire org.

Which AI clients work with the Marketgenius MCP server?

Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code with MCP support, n8n, and any custom agent built with OpenAI Agents SDK, LangChain, Vercel AI SDK, or Anthropic SDK.

Is the Marketgenius MCP server secure? How does Willow handle authentication?

Every call runs behind your existing SSO (Okta, Azure AD). Per-user OAuth scopes the agent to exactly what that user can do in Marketgenius, nothing more. No credentials reach the LLM. Every action writes to an audit trail.

Can I limit which Marketgenius actions agents can take?

Yes. Willow lets you scope agents to specific actions, specific projects, or specific environments. Toggle actions on or off in the dashboard, or enforce policy via infrastructure-as-code through GitHub.

How do I detect shadow Marketgenius MCP servers in my org?

Willow's browser extension and discovery service surface unmanaged MCP servers, skills, and AI agents across the org. If a developer installed an unapproved Marketgenius MCP locally, you'll see it.

What does the Marketgenius MCP server cost?

Pricing depends on org size and deployment model (SaaS, dedicated cloud, self-host). See withwillow.ai/pricing or contact sales for a quote.

How do I install the Marketgenius MCP server with Willow?

Install via the Willow Connect Panel in one click, or paste the JSON snippet above into your Claude Desktop, Cursor, or Claude Code config. SSO and RBAC inherit from your existing Willow setup.