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 models.
A model is a versioned workspace that holds your files, 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.
Your selected provider processes the AI conversation under your agreement. Bridge Town does not host or invoke the language model; it receives the MCP tool calls your client sends.
Claude.ai (recommended, no token):
- Click Customize → + → Add custom connector
- Paste
https://api.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:
The supported-client roster below is generated from the Connect AI catalog. Open Connect AI for the exact command, configuration path, and verification step.
| Client | Authentication | Setup |
|---|---|---|
Claude.ai (claude-ai) | oauth | OAuth connection |
ChatGPT (chatgpt) | oauth | OAuth connection |
Claude Code (claude-code) | token | command |
Claude Desktop (claude-desktop) | token | config |
Codex (codex) | token | command and config |
Cursor (cursor) | token | config |
GitHub Copilot (copilot) | token | command and config |
Gemini CLI (gemini-cli) | token | command |
Windsurf (windsurf) | token | config |
Amp (amp) | token | command |
Mistral Vibe (mistral-vibe) | oauth | OAuth connection |
OpenCode (opencode) | token | command and config |
Kimi Code (kimi-code) | token | command and config |
Z Code (z-code) | token | gui |
Qwen Code (qwen-code) | token | command and config |
Cline (cline) | token | config |
Goose (goose) | token | config |
Aider (aider) | token | unsupported |
Droid (droid) | token | command |
The MCP tool surface is identical across clients. The Anthropic Messages API MCP connector is tools-only; full MCP clients can also surface Bridge Town resources and prompts.
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 in my
forecastsmodel. Use three product lines: SaaS, Services, and Marketplace. Start from January 2026.”
Your agent will:
- Call
create_modelif the model does not exist - Call
commit_filesto write the Python model and supporting files - Call
run_modelwithmode="sync"to 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 commit_files to apply the
change, then calls run_model 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
- Models & Files — 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-File Pipelines — chain files with the
PIPELINEconvention and/upstreamtransport