Quick Start
Get from zero to a working financial model in four steps.
1. Create your account
Section titled “1. Create your account”Sign up at app.bridgetown.builders. You’ll land on the Dashboard after login.
2. Open Models
Section titled “2. Open Models”Use the sidebar and go to Models (/models) to view your projects.
A project is a versioned workspace that holds your models, data, and dashboards.
3. Connect your AI agent
Section titled “3. Connect your AI agent”Bridge Town speaks the Model Context Protocol (MCP) — bring whichever agent you prefer. Claude.ai is the fastest path because it can connect over OAuth with no API token.
Claude.ai (recommended, no token):
- Click Customize → + → Add custom connector
- Paste
https://app.bridgetown.builders/mcp - Authorise the connection when prompted
See Connecting Claude.ai for full details.
Other clients
Section titled “Other clients”For everything else, generate an API token from Connect AI at app.bridgetown.builders/connect and follow the relevant guide:
- Connecting Claude Code —
claude mcp addone-liner - Connecting Claude Desktop — JSON config via
mcp-remote - Connecting any MCP client — generic Streamable HTTP + bearer token instructions for Codex, Gemini, ChatGPT-compatible runtimes such as OpenCode, and custom in-house agents
The MCP tool surface is identical across clients — only the transport configuration differs.
4. Build your first model
Section titled “4. Build your first model”Open your agent and ask it to build a model:
“Create a 12-month revenue forecast model in my
forecastsproject. Use three product lines: SaaS, Services, and Marketplace. Start from January 2026.”
Your agent will:
- Call
create_fileto write the Python file - Call
runto execute it in the sandbox - Return the results (stdout and output files)
You can then iterate:
“Add a 10% annual growth rate to the SaaS line”
Your agent reads the model, calls patch_file (or update_file) to apply the change, then runs run again.
What’s next?
Section titled “What’s next?”- Agent Workflow Cookbook — complete worked example with tool calls, responses, model code, dashboard creation, and sharing
- MCP Tools Reference — browse the full tool surface
- Projects & Models — understand the data model
- Sandbox Execution — how models run securely
- Dashboards — turn model outputs into interactive, shareable charts
- Team Collaboration — invite teammates, review changes, and merge together
- Multi-Model Pipelines — chain models with the
PIPELINEconvention and/upstreamtransport