Bridge Town MCP Server

@Bridge-Town

Repository Homepage

Basic information

About Bridge Town MCP Server

Public documentation and registry metadata for the Bridge Town hosted MCP connector.

#finance#gsheets#financial-model#mcp-server #sandbox #database-access #collaboration

Bridge Town MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "bridge-town": {
      "transportType": "streamable-http",
      "url": "https://api.bridgetown.builders/mcp"
    }
  }
}

Bridge Town MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

This server requires authentication. Tool discovery may require signing in or credentials from the provider.

Fetch the live tool list directly from this server's endpoint using the button above.

Overview

What is Bridge Town?

Bridge Town is an MCP-native, git-versioned financial modeling platform for FP&A teams and finance leaders. AI agents use Bridge Town tools to create projects, write Python model files, run models in isolated cloud sandboxes, query data, write outputs to Google Sheets, create dashboards, branch scenarios, and collaborate with teammates.

How to use Bridge Town?

For Claude.ai, navigate to Customize → Add custom connector and paste https://api.bridgetown.builders/mcp, then approve the OAuth prompt. Generic MCP clients supporting Streamable HTTP can configure a server with the endpoint and a bearer token (btk_); for clients that require stdio, use the provided shim with npx github:Bridge-Town/financial-modeling-mcp and set the BRIDGE_TOWN_API_TOKEN environment variable.

Key features of Bridge Town

MCP-native financial modeling with 75+ tools
Git-versioned projects and scenario branching
Cloud execution in isolated, no‑outbound‑network sandboxes
Google Sheets integration with drive.file OAuth scope
OAuth and bearer‑token authentication for any MCP client
MCP resources for health, skills, and templates

Use cases of Bridge Town

Build and run financial models as code using AI agents
Branch and merge scenarios for what‑if analysis
Write model outputs directly to Google Sheets
Collaborate on models with teammates via pull requests
Automate FP&A workflows with skill templates and prompts

Frequently asked questions

Does Bridge Town run its own AI model?

No. Bridge Town does not run a server‑side LLM or proxy your prompts. The AI client and model provider handle the conversation; Bridge Town only receives structured MCP tool calls.

What transport does Bridge Town use?

The hosted server uses MCP Streamable HTTP. For local MCP hosts that require a stdio binary, a minimal shim (forwarding to the same HTTP endpoint) is available via `npx github:Bridge-Town/financial-modeling-mcp`.

How do I authenticate with Bridge Town?

Claude.ai uses OAuth automatically. For generic clients, generate a token (starting with `btk_`) at `https://app.bridgetown.builders/connect` and include it as a Bearer token in the `Authorization` header or via the shim’s `BRIDGE_TOWN_API_TOKEN` environment variable.

Where are my financial models executed?

Model execution runs in isolated cloud containers with no outbound network access. Bridge Town is tenant‑isolated and OAuth‑backed.

Can Bridge Town access any Google Sheet?

No. Bridge Town uses Google’s `drive.file` scope, so it can only access Sheets a user explicitly selects through the Bridge Town flow or Sheets created by Bridge Town.

Comments

More Developer Tools MCP servers

Kaiva Bridge

Kaiva Bridge turns your API, database or documents into a managed MCP server for Claude, ChatGPT, Cursor and VS Code. Point it at an OpenAPI or Swagger spec, an API docs link, a cURL command, a Postman collection, a Grap

Moxie Docs

Jackalope-Dev

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

OrangePro

Aamir Siddiqui

OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

Raccha AI

Shree Mandadi

MCP-first toolbox for agents: namespaced key-value storage, a FIFO queue, auth, and a handful of stateless utility tools (JWT decode, hashing, cert inspection, CIDR math). Free while in early access. This repository is a

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.