
Maverick MCP Server
An MCP server that enables Amazon Q CLI users to create, query, and manage Maverick sites through natural language commands.
README
Maverick MCP Server
An MCP (Model Context Protocol) server for managing Maverick sites through Amazon Q CLI.
Features
- Create Sites: Create new Maverick sites with comprehensive configuration options
- Query Sites: Search and filter sites using various criteria
- Get Site Details: Retrieve detailed information about specific sites
Installation
- Install the package:
cd /Users/vigneshwaran.rajesh/companyWork/EE-hackathon/maverick-mcp
pip install -e .
pip install -r requirements.txt
- Test the installation:
python3 test_server.py
- Set up environment variables:
export MAVERICK_BASE_URL="https://maverick-staging.appiancloud.com"
export MAVERICK_API_TOKEN="your-api-token-here"
Configuration for Amazon Q CLI
Add to your Q CLI MCP configuration file at ~/.aws/amazonq/mcp.json
:
{
"mcpServers": {
"maverick": {
"command": "python3",
"args": ["/Users/vigneshwaran.rajesh/companyWork/EE-hackathon/maverick-mcp/server.py"],
"env": {
"MAVERICK_BASE_URL": "https://maverick-staging.appiancloud.com",
"MAVERICK_API_TOKEN": "your-actual-api-token-here"
}
}
}
}
Note: Use the full path to your server.py file in the configuration.
Available Tools
1. maverick___create_site
Creates a new Maverick site with specified configuration.
Required Parameters:
subdomain
: The site name/subdomain
Optional Parameters:
installer
: Appian version (e.g., "22.1.235.0")installerLabel
: Installer label (e.g., "22.1-latest")region
: AWS region (e.g., "us-east-1")serverSize
: Server size (e.g., "m5.large")purpose
: Site purpose (development, hackathon, etc.)customerName
: Customer namedryRun
: Validate without creating (boolean)- And many more configuration options...
2. maverick___query_sites
Query sites using various filters and criteria.
Filter Options:
siteList
: Array of site IDspurpose
: Array of purposes to filter byregion
: Array of regions to filter byaccountName
: Array of account namescreatedAfter
: Sites created after specified timecreatedBefore
: Sites created before specified timemodifiedAfter
: Sites modified after specified timestatus
: Site status (Active, Shutdown, etc.)labelName
+labelValue
: Filter by labelsstartIndex
: Pagination start (default: 1)batchSize
: Results per page (default: 20)
3. maverick___get_site_by_id
Get detailed information about a specific site.
Parameters:
identifier
: Site ID (numeric) or site name/subdomain
4. maverick___manage_site
Perform various actions on existing Maverick sites.
Required Parameters:
identifier
: Site ID (numeric) or site name/subdomainaction
: Action to perform
Supported Actions:
start
: Start a stopped siterestart
: Restart a running sitestop
: Stop a running site (data persists)force-stop
: Force stop (bypasses standard checks)force-restart
: Force restart (force stop + start)delete
: Permanently delete a siterevert
: Revert site to a specific snapshoton-demand-backup
: Take an on-demand backupedit
: Edit site configurationclone
: Create a copy of the sitemove
: Move site to different regionresize
: Increase site volume size
Action-Specific Parameters:
- Edit:
installer
,serverSize
,purpose
,siteProperties
, etc. - Revert:
restoreSpec
(withsiteID
andcreatedAt
) - Clone:
reason
,requestorFirstName
,requestorLastName
,requestorEmail
,supportCase
- Move:
region
,email
(optional) - Resize:
volumeSize
5. maverick___get_site_resize_status
Check the status of an ongoing site resize operation.
Parameters:
siteId
: Site ID to check resize status for
Usage Examples
Create a Simple Site
Create a new Maverick site with subdomain "my-test-site"
Create an Advanced Site
Create a Maverick site with subdomain "hackathon-site", purpose "hackathon", customer "Appian Engineering", server size "m5.large", and region "us-east-1"
Query Sites by Purpose
Find all Maverick sites with purpose "development"
Query Sites by Region
Show me all sites in us-east-1 and us-west-2 regions
Query Recent Sites
Find all sites created after 01/01/2024
Get Specific Site
Get details for Maverick site with ID 1004544
Query with Pagination
Show me the first 10 active sites
Site Management Actions
Start Maverick site with ID 1004544
Stop site "my-test-site" gracefully
Restart site 1004544 with force restart
Delete site "old-test-site" permanently
Take an on-demand backup of site 1004544
Edit Site Configuration
Edit site 1004544 to change server size to "m5.xlarge" and purpose to "hackathon"
Update site "my-site" to use installer label "23.1-latest"
Clone Site
Clone site 1004544 for debugging with reason "Reproduce customer issue" and support case "CN-1234"
Move and Resize Sites
Move site 1004544 to region "us-west-2"
Resize site 1004544 volume to 100 GB
Check resize status for site 1004544
Testing
Run the test script to verify everything is working:
python3 test_server.py
This will test all three tools and show you what to expect.
Response Format
The server provides formatted, human-readable responses with:
- ✅ Success indicators
- ❌ Error indicators
- 📊 Structured site information with emojis for easy reading
- Pagination information when applicable
- Total count of matching results
Error Handling
The server handles various error scenarios:
- Missing API tokens
- Validation errors (400)
- Not found errors (404)
- Server errors (500)
- Network timeouts
- Invalid parameters
Files in this Project
server.py
- Main MCP server implementation with all 5 toolsrequirements.txt
- Python dependenciessetup.py
- Package configurationtest_server.py
- Test script to verify all functionalitytest_auth.py
- Authentication testing scriptq-config-example.json
- Example Q CLI configurationREADME.md
- This documentation
Next Steps
- Get your Maverick API token from your Maverick instance
- Set the environment variables with your actual token
- Add the MCP server configuration to
~/.aws/amazonq/mcp.json
- Restart Amazon Q CLI and test with:
q chat
- Try the example commands to verify everything works
Development
To extend the server with additional Maverick APIs:
- Add new tool definitions to
handle_list_tools()
- Add corresponding handlers to
handle_call_tool()
- Implement the API call functions
- Update this README with the new functionality
Environment Variables
MAVERICK_BASE_URL
: Base URL for Maverick API (default: staging)MAVERICK_API_TOKEN
: Authentication token for Maverick API (required)
Note: The server uses the appian-api-key
header for authentication, which is one of the supported methods in Maverick API. Other supported methods include:
appian-api-key
header (used by this server)Authorization: Bearer
header- Basic Authentication with null username
- Basic Authentication with null password
Authentication Setup
To get your API token:
- Configure object security for a service account in your Maverick instance
- Generate an API key for that service account
- Set the
MAVERICK_API_TOKEN
environment variable with your key
Example:
export MAVERICK_API_TOKEN="your-actual-api-key-here"
Dependencies
mcp>=1.10.0
: Model Context Protocol libraryhttpx>=0.25.0
: Async HTTP client- Python 3.8+
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.