ghl-api-mcp
MCP server for GoHighLevel documentation, enabling agents to search docs, list endpoints, and fetch focused API details without loading large files.
README
ghl-api-mcp
ghl-api-mcp is an MCP stdio server for GoHighLevel documentation. It lets agents search docs, list endpoints, and fetch focused API details without loading large markdown files into prompt context.
This repo does not include a runnable GoHighLevel OAuth/SSO sample app; it contains documentation and the MCP docs server that indexes that documentation.
What It Does
The server indexes markdown files under docs/ and exposes MCP tools for:
list_docssearch_docslist_endpointsget_endpoint_detailsget_sectionget_documentreload_docs
The current corpus includes API review docs, implementation guides, and operational notes such as OAuth/SSO integration details and rate-limit guidance. To see exactly what is loaded, run list_docs.
list_docs labels each file as either a reference or guide. Use get_document when an agent needs the full body of a longer procedural document instead of a single extracted section.
For search_docs, list_endpoints, get_endpoint_details, and get_section, you can pass an optional whitelabel_domain like api.example.com or https://api.example.com. Returned endpoint URLs and embedded example URLs will be rewritten to that domain.
Requirements
- Node.js
>=20for local usage - Docker, if you want to run the containerized version
Quick Start
Local
npm install
npm start
Or run the CLI entrypoint directly:
npm install
./bin/ghl-api-mcp.js
Important: this is a stdio MCP server. When you run it successfully, it stays attached and waits for client requests. It is not an HTTP server and does not open a port.
Docker
docker build -t ghl-api-mcp .
docker run --rm -i ghl-api-mcp
MCP Client Configuration
Local Repo Checkout
Use this when the repository already exists on disk:
{
"mcpServers": {
"ghl-docs": {
"command": "node",
"args": ["/absolute/path/to/ghl-api-mcp/src/server.js"]
}
}
}
Local Repo Checkout With External Docs Directory
{
"mcpServers": {
"ghl-docs": {
"command": "node",
"args": ["/absolute/path/to/ghl-api-mcp/src/server.js"],
"env": {
"GHL_DOCS_DIR": "/absolute/path/to/docs"
}
}
}
}
Docker
{
"mcpServers": {
"ghl-docs": {
"command": "docker",
"args": ["run", "--rm", "-i", "ghl-api-mcp"]
}
}
}
Docker With External Docs Directory
{
"mcpServers": {
"ghl-docs": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-v",
"/absolute/path/to/docs:/docs:ro",
"-e",
"GHL_DOCS_DIR=/docs",
"ghl-api-mcp"
]
}
}
}
Document Loading
- Any
.mdfile underdocs/is indexed automatically - If the server is already running, call
reload_docsafter changing docs on disk - If you add docs to the repo and run via Docker without a mounted docs directory, rebuild the image so the container includes the new files
Development
npm install
npm test
Scraping Workflow
Use the browser-backed scraper when a GHL doc links to richer ClickUp content:
npm run scrape:page -- \
--url https://marketplace.gohighlevel.com/docs/ghl/contacts/search-contacts-advanced \
--output docs/generated/search-contacts-advanced.md
Browser selection order:
- Chrome
- Chrome Canary
- Zen
You can override the browser with --browser, --executablePath, or PUPPETEER_EXECUTABLE_PATH.
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.