Hemrock
Sign in

MCP Server

Connect Claude Desktop or Claude.ai to Hemrock's financial modeling prompt library. Context primers, task prompts, and sanity checks, pulled automatically into every AI conversation about your model.

Free
Open, no auth, no limits
Connect in Claude.ai

Settings → Connectors → Add MCP Server

Endpoint URL›https://mcp.hemrock.com/mcp
Claude Desktop config›
{
  "mcpServers": {
    "hemrock": {
      "type": "url",
      "url": "https://mcp.hemrock.com/mcp",
      "name": "Hemrock"
    }
  }
}
Claude.ai connector›

Settings → Connectors → Add MCP Server, then paste:

https://mcp.hemrock.com/mcp

What it does

Built to edit means using AI to customize a proven model instead of generating from scratch. For that to work, the AI needs to understand the model's structure, conventions, and guardrails before it starts making changes. Copy-pasting a primer every time is friction.

The MCP server exposes Hemrock's prompt library as tools any MCP-compatible AI client can call. Ask Claude to "use the Hemrock context primer for the cap table model" and it pulls the right orientation, the right format conventions, and the right warnings automatically.

Available tools

get_context

Orient your AI before it touches a spreadsheet. Pulls universal modeling context plus any template-specific primer.

get_prompts

Task-specific prompts for a given template. Filter by task type (orientation, revenue, expenses, fundraising, analysis, presentation).

get_checks

Sanity-check prompts to catch hallucinated formulas, hard-coded values, confused metrics, and other common AI mistakes.

get_best_practices

Modeling best practices by topic: formatting, structure, inputs, assumptions, review, sharing.

Example usage

“Use the Hemrock MCP to get the context primer for the cap table model.”
“Get me the fundraising prompts for the Standard Financial Model.”
“Run the sanity checks on this fund model and tell me what's wrong.”

Why this matters

AI without context makes plausible-looking mistakes. Wrong cell references, hard-coded values where formulas should be, confused metrics, silent breakage. The context primer and prompts catch most of that before the AI ever touches a cell.

If you're editing a Hemrock model with AI, connect the MCP. If you're editing something else, the patterns still apply: orient first, prompt with guardrails, verify before trusting the output.

Related