BackCrew GorillaDesk MCP Server
Enables AI assistants to manage GorillaDesk customer records, users, and company data through natural language interactions. Supports listing, creating, and updating customers, adding notes, and retrieving company and user information.
README
BackCrew GorillaDesk MCP Server
An open-source Model Context Protocol (MCP) server for GorillaDesk, the field service management (FSM) platform used by a number of pest control, lawn care, and cleaning operators. Point Claude, ChatGPT, Cursor, or any other MCP-compatible client at your GorillaDesk account and manage customer records using plain language instead of clicking through the GorillaDesk web app.
Built by BackCrew — the second entry in a series of open MCP servers for the CRMs and FSM platforms that run the pest control industry. First entry: backcrew-mcp for Housecall Pro.
New to MCP? Jump to What is an MCP server, and why does a CRM need one?
Contents
- What is an MCP server, and why does a CRM need one?
- What this server does — and its real limits
- Tool reference
- Setup
- Connecting it to an MCP client
- Usage examples
- Project layout
- Notes on the GorillaDesk API
- Roadmap
- Built by BackCrew
- License
What is an MCP server, and why does a CRM need one?
The Model Context Protocol is an open standard for connecting an LLM to external tools and data. An MCP server exposes a set of typed "tools" (think: functions with a name, a description, and a schema for their arguments); an MCP client — Claude Desktop, Claude Code, ChatGPT, Cursor, etc. — reads that tool list and lets the model call them mid-conversation.
Concretely, once this server is running you can ask your AI assistant 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 calls the right list_customers, add_customer_note, list_users, etc. behind the scenes, instead of you tabbing over to the GorillaDesk dashboard by hand.
What this server does — and its real limits
This is a single Node/TypeScript MCP server (stdio transport) wrapping the GorillaDesk public API, built directly from GorillaDesk's own published OpenAPI spec (https://api.gorilladesk.com/v1/specs — publicly downloadable, no login required).
Be upfront about scope: as of this writing, GorillaDesk's public API is small. It covers 9 operations across 5 resources:
| Domain | Tools |
|---|---|
| Company | get_company |
| Users | list_users, get_user |
| Customers | list_customers, get_customer, create_customer, update_customer |
| Customer Notes | add_customer_note |
| Phone Types | list_phone_types |
That's it. There is currently no public endpoint for jobs, scheduling/appointments, invoicing, estimates, technician routes, materials, or leads-as-a-distinct-resource — even though GorillaDesk the product has all of that. Either the rest of their API sits behind a partner/enterprise tier not reflected in the public docs, or it simply hasn't shipped publicly yet.
We're shipping this repo at its true size rather than padding it with guessed endpoints. If GorillaDesk expands their public API, this server (and this README) will expand with it — see Roadmap.
You don't need a GorillaDesk account to read the code, build it, or see the full tool list. The server starts and responds to tools/list with zero configuration — it only asks for GORILLADESK_API_KEY once a tool actually tries to call the live API.
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.
Setup
Prerequisites
- Node.js 18+
- A GorillaDesk account (only required to call the live API — not to build or explore this repo)
Install
git clone https://github.com/jayson-svg/backcrew-mcp-gorilladesk.git
cd backcrew-mcp-gorilladesk
npm install
npm run build
Get a GorillaDesk API key
- Log into your GorillaDesk account
- Go to Addons → API
- Generate a key
Full details: GorillaDesk API authentication docs.
Configure environment variables
cp .env.example .env
Then edit .env:
GORILLADESK_API_KEY=your_key_here
Connecting it to an MCP client
Claude Desktop / Claude Code
Add this to your MCP client's config (for Claude Desktop, claude_desktop_config.json):
{
"mcpServers": {
"gorilladesk": {
"command": "node",
"args": ["/absolute/path/to/backcrew-mcp-gorilladesk/dist/index.js"],
"env": {
"GORILLADESK_API_KEY": "your_key_here"
}
}
}
}
Restart the client and the GorillaDesk tools should show up alongside any others you have configured.
Any other MCP-compatible client (Cursor, Windsurf, custom agents built on the MCP SDK, etc.) works the same way — this server speaks standard stdio MCP.
Usage examples
Given the current scope, this server is genuinely useful for:
- "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 is not yet useful for job scheduling, invoicing, or estimates — GorillaDesk hasn't published public endpoints for those.
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
429response includesx-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.
Roadmap
This is the second of a planned series of MCP servers, one per major pest control CRM/FSM used in the US and UK. First entry: Housecall Pro (74 tools, full job/invoice/schedule lifecycle). See ROADMAP.md for what's next, including why PestPac is currently blocked (its API docs require a paid, login-gated developer account — no public reference exists).
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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.