BackCrew GorillaDesk MCP Server

Think of this like a brand-new employee on their first day, not a business partner.

A new hire only does the exact tasks you've shown them, nothing more, until you decide they're ready for more responsibility. That's the idea behind this project: it connects an AI assistant like Claude or ChatGPT to your GorillaDesk account, so you can ask for things in plain English instead of clicking through the GorillaDesk app yourself.

One honest difference from the rest of this series, up front: GorillaDesk's own public tools don't yet let us build the "responsibility levels" the other BackCrew MCP servers have (more on that below), so for now, this one really is more all-or-nothing once you hand it a key. Read How this keeps you safe before you set it up.

Built by BackCrew, part of a series of free tools like this for the software pest control companies use every day.

Not a developer? That's fine. Everything up through "Testing it safely" is written for you: no coding background needed, and no computer jargon without an explanation first.

Contents

• What this actually does

• Why use an independent MCP server instead of the platform's own AI?

• What this server can't do yet (read this before you get your hopes up)

• Also from BackCrew

• Some words you'll see, explained

• How this keeps you safe

• What it can do

• How to set it up

• Connecting it to Claude

• Things you can try asking

• Testing it safely

• For developers

• What's next

• Built by BackCrew

• License

Related MCP server: gorgias-mcp

What this actually does

Let's be upfront about what this is, because it's easy to oversell: it's not some all-knowing assistant that understands your business and runs things for you. It's a specific, named list of actions that an AI assistant is allowed to trigger when you ask in plain English. It doesn't have judgment about your business. It just matches what you ask for to the closest thing on its list and does exactly that. Nothing more.

Once it's running, you can ask things like:

"Find the customer record for Dana Ruiz and add a note that she prefers afternoon appointments."

"List every lead-status customer we've added this month."

"Who are our technicians, and what's Mike's license number?"

And it does the clicking for you: the same actions you'd take yourself, just faster, in plain English.

Why use an independent MCP server instead of the platform's own AI?

Software platforms are increasingly shipping their own built-in AI features. Worth knowing why you might still reach for this instead:

• No plan-tier gates. Native AI features are often locked to a platform's most expensive plan. This project just needs API access, which is usually available on lower tiers too.

• Cross-platform, not walled off. A platform's own AI only sees that platform's own data; it has no reason to work fluently with your accounting software, another CRM, or your email, since those are somebody else's product. An MCP-connected assistant can have multiple servers attached at once (this one plus another BackCrew server covering a different part of your business), so it can work across your whole stack in one conversation.

• Your choice of AI, not theirs. You keep using whichever assistant you already trust (Claude, ChatGPT, whatever) instead of learning a new vendor-specific AI interface.

What this server can't do yet (read this before you get your hopes up)

Be upfront about this: GorillaDesk's public tools are small right now. This server covers 9 actions across 5 areas: Company info, Users, Customers, Customer Notes, and Phone Types.

That's it. There's currently nothing public for jobs, scheduling, invoicing, estimates, technician routes, materials, or leads as their own thing, even though GorillaDesk the product clearly has all of that. Either the rest sits behind a bigger-account tier that isn't publicly documented, or it just hasn't been opened up yet.

We're shipping this at its true, honest size instead of padding it with guessed-at features that don't actually work. If GorillaDesk opens up more, this server (and this README) grows with it. See What's next.

You don't need a GorillaDesk account just to look at this project or try it out. It starts up and shows you everything it can do with zero setup; it only asks for your GorillaDesk key once you actually try to use it on your real account.

Also from BackCrew

This is one of several MCP connectors BackCrew builds, same idea, different software. We've also got QuickBooks for the accounting side, plus CRM connectors like HubSpot and GoHighLevel for lead and marketing data. Full list and what's live right now: see ROADMAP.md.

Beyond this repo: once a business gets comfortable with an AI assistant reading its data, there's often more it wants to do with it, like catching missed calls faster, processing invoices and paperwork automatically, following up on quotes without someone having to remember, reactivating customers who've gone quiet, or pulling reports without digging through the software. That's a separate, scoped conversation, not part of this free, open-source repo. Same contact as in Built by BackCrew below if it's something you want to explore.

Some words you'll see, explained

• API: short for "Application Programming Interface." A locked door into GorillaDesk's data that only software (not a person clicking a mouse) can open. This project is a key that opens that door.

• MCP: short for "Model Context Protocol." The standard way an AI assistant like Claude or ChatGPT is told "here's exactly what you're allowed to do, and how to do it." This project speaks that standard, which is why it plugs into Claude (and similar tools) with no custom setup.

• Server: a small program that sits between your AI assistant (Claude, ChatGPT, etc.) and GorillaDesk, translating requests back and forth. You start it once and leave it running; you never interact with it directly.

• Repo (short for "repository"): the folder of code for this whole project. "Clone the repo" just means "download a copy of this project."

• API key: a long, private password-like code that proves a request is really coming from you. You'll generate one from your own GorillaDesk account (steps below) and never share it.

• Terminal: a plain-text window on your computer where you type commands instead of clicking buttons. We walk you through this step by step.

• Tool: one specific action the AI is allowed to take. Each one is listed and named individually; there's no hidden catch-all action.

How this keeps you safe

Here's the honest version, not the sales version: the other servers in this series can be dialed down to "look only" mode with a couple of settings, and even when you turn on more, you pick exactly how much. GorillaDesk's public tools don't give us enough to build that same dial for this one yet: once you hand this server your GorillaDesk key, it can do anything that key is allowed to do (which, given the small scope above, is mostly customer records and notes; there's no invoicing or job-deletion risk here regardless).

What that means in practice:

• Treat your GorillaDesk key with extra care: it's the only thing standing between "just looking things up" and "changing customer records."

• If you only ever want to look things up and never write anything, the honest way to do that today is simple: just don't ask the AI to create or update anything. There's no software switch to flip yet.

• We'll add the same tiered read-only-by-default system the rest of this series has the moment GorillaDesk's public tools support it. See What's next.

What it can do

9 actions in total. See What this server can't do yet for what's missing.

How to set it up

Do these three steps in order. Each one gathers everything you need before you move to the next. You won't have to jump back and forth.

Step 1: Make a folder for this on your computer

Before touching anything technical, just pick a spot and create an empty folder.

1. Open Finder (Mac) or File Explorer (Windows)

2. Go to your Desktop or Documents, anywhere easy to find again

3. Create a new folder and name it something like backcrew-gorilladesk

That's it. You now know exactly where this project is going to live. Keep this Finder/Explorer window handy: you'll need to find this folder again in Step 3.

Step 2: Get your GorillaDesk key

Do this next, entirely inside GorillaDesk (no terminal yet).

1. Log into your GorillaDesk account

2. Click Addons in the menu

3. Click API

4. Generate a key

5. Copy the key, then paste it somewhere temporary (a Notes app, a blank email draft) so you don't lose it before Step 3

Full details, if you want a second reference: GorillaDesk API authentication docs.

You now have everything GorillaDesk needs to give you. Time to move to the terminal.

Step 3: Install it

This is one continuous set of steps: do them in order, in the same terminal window.

1. Open a terminal. On a Mac, press Cmd + Space, type "Terminal," and hit enter. On Windows, click the Start menu, type "PowerShell," and hit enter. Use PowerShell rather than Command Prompt: a couple of the commands below, like pwd, only work in PowerShell.

2. Move into the folder you made in Step 1. Type cd (with a space after it), then drag your backcrew-gorilladesk folder from Finder/Explorer straight into the terminal window (it'll fill in the full path for you), then press Enter.

3. Download the project into that folder. Paste this exactly and press Enter:

   git clone https://github.com/jayson-svg/backcrew-mcp-gorilladesk.git .

   (The period at the end matters: it downloads into the folder you're already in, instead of making a new one. If your computer asks to install "command line developer tools" the first time you use git, say yes, that's normal on a Mac that's never used git before.)

4. Install what the project needs to run. Paste and press Enter:

   npm install

5. Get it ready to use. Paste and press Enter:

   npm run build

6. Get the folder's exact location (you'll need this in Step 4). Paste and press Enter:

   pwd

   This prints something like /Users/yourname/Desktop/backcrew-gorilladesk. Copy that whole line: you'll paste it into Claude's settings next.

7. Create your settings file. Paste and press Enter:

   cp .env.example .env

8. Open that new file in a text editor. On a Mac: type open -e .env and press Enter. On Windows: type notepad .env and press Enter.

9. Paste in the key you copied in Step 2. Find the line that says GORILLADESK_API_KEY= and paste your key right after the =, no spaces.

10. Save the file and close it. (Cmd+S / Ctrl+S, then close the window.)

That's the whole install. Keep that pwd output from step 6 handy: the next section uses it.

Connecting it to Claude

This step comes last on purpose: it needs the exact folder location from Step 3, and now you have it.

Claude Desktop / Claude Code

1. Open Claude's settings file. For Claude Desktop, this is claude_desktop_config.json; Claude's own settings menu will show you where to find it.

2. Add this, replacing PASTE_YOUR_PWD_OUTPUT_HERE with what pwd printed in Step 3.6, and your_key_here with your GorillaDesk key again. If you're on Windows, swap any backslashes in that path for forward slashes (for example C:/Users/yourname/Desktop/... instead of C:\Users\yourname\Desktop\...), since the config file needs regular slashes.

{
  "mcpServers": {
    "gorilladesk": {
      "command": "node",
      "args": ["PASTE_YOUR_PWD_OUTPUT_HERE/dist/index.js"],
      "env": {
        "GORILLADESK_API_KEY": "your_key_here"
      }
    }
  }
}

3. Save the file and restart Claude completely (quit it, don't just close the window).

You should now see GorillaDesk show up as something Claude can use. Nothing more to do: no need to go back to GorillaDesk or the terminal.

This also works with ChatGPT and other MCP-compatible AI tools (Cursor, Windsurf, and others); the setup step is basically the same.

Things you can try asking

• "Show me every customer with status 'lead' created in the last two weeks"

• "Look up the customer with account number 5047 and pull up their locations"

• "Add a note to that customer's account saying the gate code changed, and notify Mike"

• "List our technicians and who has admin access"

It's not useful yet for job scheduling, invoicing, or estimates; GorillaDesk hasn't opened up public endpoints for those.

Testing it safely

Given there's no dial to turn down yet, a few habits matter more here than in the rest of this series:

1. Get a feel for it on read-only-style questions first: just don't ask it to create or update anything until you trust how it interprets your requests.

2. The first time you do let it write something, test on a clearly fake customer. Make a test customer named something obvious like "ZZZ Test Customer: Do Not Use" and see how that goes before pointing it at a real one.

3. Never share your API key: not in chat, not in a screenshot, not in a support ticket. Treat it like a password, because it functions like one.

4. If you want to pull the plug entirely, just delete the key from your .env file (or remove the gorilladesk block from Claude's settings). There's no in-between "read only" mode to fall back to yet, so all-off is the fastest safety net.

For developers

Everything below this point assumes a coding background.

Tool reference

Run the server and call tools/list from any MCP client to see exact input/output schemas; every tool's description includes the HTTP method and path it maps to (e.g. Maps to GET /customers/{customerId}.). Source lives under src/tools/, one file per resource.

Why there's no tier/profile system here (yet)

Every other repo in this series reads a <PLATFORM>_MCP_MODE/<PLATFORM>_MCP_PROFILE pair of environment variables and only registers tools up to the allowed tier (genuinely absent from tools/list, not just hidden). This repo predates that pattern, and given the API surface here is only 9 operations with no delete/void/destructive actions among them, the safety payoff of adding tiers is smaller than on the bigger repos. If GorillaDesk's public API grows, this repo should adopt the same tier system the rest of the series uses. See ROADMAP.md.

Project layout

src/
  index.ts          Server entrypoint (registers every tool group and starts stdio transport)
  client.ts          Minimal fetch-based GorillaDesk API client (auth headers, error handling)
  toolkit.ts          Shared helper that wires a Zod input schema + handler into an MCP tool
  tools/
    company.ts
    users.ts
    customers.ts
    phoneTypes.ts

Notes on the GorillaDesk API

• Base URL: https://api.gorilladesk.com/v1

• Auth header: Authorization: Bearer <api_key>

• Public OpenAPI spec: https://api.gorilladesk.com/v1/specs (YAML, no auth required to fetch)

• Rate limits apply per endpoint group; a 429 response includes x-rate-limit-reset

This server was built by reading GorillaDesk's own published OpenAPI spec directly, not by guessing or by reverse-engineering another project. If GorillaDesk publishes more endpoints, open an issue or PR and we'll extend this server to match.

What's next

This is one of a planned series of MCP servers, one per major pest control CRM/FSM used in the US and UK. See ROADMAP.md for the rest of the series, what's next for this repo, and the tiered safety system the bigger repos already have.

Built by BackCrew

This repo is free, open source, and meant to be genuinely useful on its own: clone it, read it, run it, fork it for your own stack.

It's also a demo of the kind of work BackCrew does: we build integrations, automations, and AI tooling for pest control and field service businesses. If you'd rather not stand this up and maintain it yourself (or you want it extended the moment GorillaDesk expands their API, wired into your own internal systems, or built for another CRM entirely), that's a done-for-you engagement we take on.

Want this done for you? Reach out: jayson@backcrew.co

No pressure either way: the code above works standalone.

License

MIT