Conductor for QuickBooks Desktop

is.conductorPublished by conductor.isOfficial publisherv1.0.1Updated Nov 8, 2026

All 256 operations on all 62 QuickBooks Desktop and Enterprise object types, for Claude and ChatGPT

VerifiedStreamable HTTPWeb executableFinanceBusiness & Commerce

Overview

AI-generated overview

Hosted MCP server that lets an assistant read and change QuickBooks Desktop and Enterprise data through Conductor, covering all 256 operations on 62 object…

What you can do
  • Query documentation for the QuickBooks Desktop API and TypeScript SDK
  • Write and run TypeScript SDK code in an isolated sandbox to perform QuickBooks operations
  • Work across all 256 operations on the 62 QuickBooks Desktop and Enterprise object types
  • Return whatever the sandboxed code prints or returns as the tool result
When to use it
Useful when an assistant needs to look up, create, or update QuickBooks Desktop or Enterprise records such as customers, invoices, or other accounting objects, and when repeatable, scripted accounting tasks are preferred over manual entry.
Requirements
A Conductor account and secret key. Claude and ChatGPT clients connect to the hosted endpoint and sign in via OAuth; other clients send the key in the Authorization header or the x-conductor-secret-key header. Clients limited to local stdio servers need Node.js and CONDUCTOR_SECRET_KEY to run the bridge package.
Before you install
The secret key grants access to your QuickBooks company data, so store it carefully. Operations can create and modify accounting records, not just read them; the read-only flag only applies to the local bridge. Code runs in a sandbox without web or filesystem access, but results are returned to the assistant, and data is processed by Conductor's hosted service.

Installation

In SourceWeft

  1. Open Conductor for QuickBooks Desktop in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/is.conductor%2Fquickbooks-desktop/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "conductor-for-quickbooks-desktop": {
      "type": "http",
      "url": "https://mcp.conductor.is/"
    }
  }
}

README

QuickBooks Desktop Node.js MCP Server

Installation

The tools run on Conductor's hosted MCP server at https://mcp.conductor.is/. Claude (claude.ai, Claude Desktop, mobile, Cowork) and ChatGPT add that URL as a custom connector and sign in, and Claude Code adds it with claude mcp add and signs in from /mcp. Codex CLI, Cursor and VS Code send your Conductor secret key in the Authorization header. Clients that run only local (stdio) servers use this package, a thin bridge to the hosted server: it needs only Node.js and CONDUCTOR_SECRET_KEY, and the tools still run on the hosted server. The full per-client guide is at docs.conductor.is/usage/mcp.

Direct invocation

You can run the bridge directly via npx:

sh
export CONDUCTOR_SECRET_KEY="sk_conductor_..."npx -y conductor-node-mcp@latest

Via MCP Client

There is a partial list of existing clients at modelcontextprotocol.io. If you already have a client, consult their documentation to install the MCP server.

For a stdio client with a JSON config (one with no remote-server support), the entry looks like this; replace only sk_conductor_... with your secret key:

json
{  "mcpServers": {    "conductor": {      "command": "npx",      "args": ["-y", "conductor-node-mcp"],      "env": {        "CONDUCTOR_SECRET_KEY": "sk_conductor_..."      }    }  }}

Add "--code-allow-http-gets" to args for read-only access. Set CONDUCTOR_MCP_URL in env to point the bridge at a different server, for example a self-hosted --transport=http instance (see "Running remotely" below).

Cursor

If you use Cursor, you can install the MCP server by using the button below. You will need to set your environment variables in Cursor's mcp.json, which can be found in Cursor Settings > Tools & MCP > New MCP Server.

[Add to Cursor]

VS Code

If you use MCP, you can install the MCP server by clicking the link below. You will need to set your environment variables in VS Code's mcp.json, which can be found via Command Palette > MCP: Open User Configuration.

Open VS Code

Claude Code

If you use Claude Code, connect it to the hosted server by running the command below in your terminal, replacing sk_conductor_... with your secret key.

claude mcp add --transport http conductor https://mcp.conductor.is/ --header "Authorization: Bearer sk_conductor_..."

Code Mode

This MCP server is built on the "Code Mode" tool scheme. In this MCP Server, your agent will write code against the TypeScript SDK, which will then be executed in an isolated sandbox. To accomplish this, the server will expose two tools to your agent:

  • The first tool is a docs search tool, which can be used to generically query for documentation about your API/SDK.

  • The second tool is a code tool, where the agent can write code against the TypeScript SDK. The code will be executed in a sandbox environment without web or filesystem access. Then, anything the code returns or prints will be returned to the agent as the result of the tool call.

Using this scheme, agents are capable of performing very complex tasks deterministically and repeatably.

Running remotely

Launching the package with --transport=http runs the actual MCP server (the mode https://mcp.conductor.is/ runs) using Streamable HTTP transport. The --port setting can choose the port it will run on, and the --socket setting allows it to run on a Unix socket. Code execution in this mode needs Deno on the server.

Authorization can be provided via the Authorization header using the Bearer scheme.

Additionally, authorization can be provided via the following headers:

HeaderEquivalent client optionSecurity scheme
x-conductor-secret-keyapiKeyBearerAuth

A configuration JSON for this server might look like this, assuming the server is hosted at http://localhost:3000:

json
{  "mcpServers": {    "conductor_node_api": {      "url": "http://localhost:3000",      "headers": {        "Authorization": "Bearer <auth value>"      }    }  }}

Source: packages/mcp-server/README.md at commit b07f9b5

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v1.0.1LatestNov 8, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Conductor integrations