HaloPSA MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@HaloPSA MCP Server show me the 10 most recent open tickets"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
HaloPSA MCP Server
An MCP (Model Context Protocol) server that provides access to HaloPSA's reporting and REST APIs, allowing AI assistants to query and analyze HaloPSA data intelligently.
Features
🔐 Secure OAuth2 authentication with HaloPSA API
📊 Execute SQL queries against HaloPSA database
🔍 Intelligent schema search and query suggestions
📋 Complete database schema with 800+ tables
🤖 AI-friendly query building assistance
🌐 Full API exploration with swagger schema access
📖 Browse and search API endpoints with pagination
🔧 Direct API calls to any HaloPSA endpoint
Installation
NPM
Install the package from npm:
npm install -g @adamhancock/halopsa-mcpDocker
Pull and run the Docker image:
docker run -e HALOPSA_URL=https://your-instance.halopsa.com \
-e HALOPSA_CLIENT_ID=your-client-id \
-e HALOPSA_CLIENT_SECRET=your-client-secret \
-e HALOPSA_TENANT=your-tenant \
ghcr.io/adamhancock/halopsa-mcp:latestUsage with Claude Desktop
Using NPM Package
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"halopsa": {
"command": "npx",
"args": ["@adamhancock/halopsa-mcp"],
"env": {
"HALOPSA_URL": "https://your-instance.halopsa.com",
"HALOPSA_CLIENT_ID": "your-client-id",
"HALOPSA_CLIENT_SECRET": "your-client-secret",
"HALOPSA_TENANT": "your-tenant"
}
}
}
}Using Docker
Add to your Claude Desktop configuration:
{
"mcpServers": {
"halopsa": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e", "HALOPSA_URL=https://your-instance.halopsa.com",
"-e", "HALOPSA_CLIENT_ID=your-client-id",
"-e", "HALOPSA_CLIENT_SECRET=your-client-secret",
"-e", "HALOPSA_TENANT=your-tenant",
"ghcr.io/adamhancock/halopsa-mcp:latest"
]
}
}
}Available Tools
Database Query Tools
halopsa_list_tables
List all available tables in the HaloPSA database:
{
filter: "fault" // Optional: filter tables by name
}halopsa_list_columns
List columns for a specific table:
{
tableName: "FAULTS", // Required: table name
columnFilter: "email" // Optional: filter columns by name
}halopsa_query
Execute SQL queries against the HaloPSA database:
{
sql: "SELECT * FROM FAULTS WHERE Status = 1 LIMIT 10"
}halopsa_table_info
Get detailed information about a specific table including all columns, data types, and relationships:
{
tableName: "FAULTS"
}halopsa_build_query
Build SQL queries programmatically with a helper:
{
tableName: "FAULTS",
columns: ["Faultid", "username", "Symptom"], // Optional: defaults to all columns
conditions: { "Status": 1 }, // Optional: WHERE conditions
orderBy: "datereported DESC", // Optional: ORDER BY clause
limit: 10 // Optional: LIMIT clause
}API Exploration Tools
halopsa_list_api_endpoints
List all API endpoints with basic information. Supports pagination:
{
category: "Tickets", // Optional: filter by category
limit: 100, // Optional: max results (default: 100)
skip: 0 // Optional: skip for pagination
}halopsa_get_api_endpoint_details
Get complete details for specific API endpoints including parameters and schemas:
{
pathPattern: "ticket", // Required: pattern to match endpoints
summaryOnly: false, // Optional: return only basic info
includeSchemas: true, // Optional: include request/response schemas
maxEndpoints: 10, // Optional: max endpoints to return
includeExamples: false // Optional: include examples
}halopsa_search_api_endpoints
Search for API endpoints by keywords. Supports pagination:
{
query: "create ticket", // Required: search query
limit: 50, // Optional: max results (default: 50)
skip: 0 // Optional: skip for pagination
}halopsa_get_api_schemas
Get API schemas/models from the swagger definition. Supports pagination:
{
schemaPattern: "Ticket", // Optional: filter schemas by name
limit: 50, // Optional: max schemas to return
skip: 0, // Optional: skip for pagination
listNames: false // Optional: include all matching schema names
}halopsa_api_call
Make authenticated API calls to any HaloPSA endpoint:
{
path: "/api/Ticket", // Required: API endpoint path
method: "GET", // Optional: HTTP method (default: GET)
body: {}, // Optional: request body for POST/PUT/PATCH
queryParams: {} // Optional: URL query parameters
}Common Queries
Open Tickets
SELECT Faultid, username, Symptom, Status, datereported
FROM FAULTS
WHERE Status IN (1, 2, 3)
ORDER BY datereported DESCUser List
SELECT uusername, uemail, usite, uextn
FROM USERS
WHERE uinactive = 0Request Types
SELECT RTid as RequestTypeId, rtdesc as RequestTypeName
FROM REQUESTTYPE
WHERE RTVisible = 1Development
Run in Development Mode
pnpm run devTest Connection
node dist/index.jsSchema Information
The MCP includes a complete HaloPSA database schema with:
818 tables
Key tables include:
FAULTS (622 columns) - Tickets/Requests
USERS (213 columns) - User information
SITE (115 columns) - Client/Site data
ACTIONS (196 columns) - Ticket actions
REQUESTTYPE (332 columns) - Ticket types
Security Notes
Never commit
.envfilesStore credentials securely
Use read-only API credentials when possible
Rotate API keys regularly
License
ISC
Available Tools
10 toolshalopsa_api_callA
Make authenticated API calls to any HaloPSA endpoint. Use this after finding the right endpoint with schema tools.
Inputs: path (required), method, body, queryParams.
halopsa_build_queryB
Build a basic SQL query for HaloPSA with a helper that ensures proper syntax. Useful for constructing simple SELECT queries with WHERE conditions, ORDER BY, and LIMIT clauses without writing raw SQL.
Inputs: tableName (required), columns, conditions, orderBy, +1 more.
halopsa_get_api_endpoint_detailsA
Get complete details for specific API endpoints including parameters, request/response schemas, and examples. Use after finding endpoints with halopsa_list_api_endpoints.
Inputs: pathPattern (required), summaryOnly, includeSchemas, maxEndpoints, +1 more.
halopsa_get_api_schemasB
Get API schemas/models from the swagger definition. Shows the structure of request/response objects used by the API endpoints. Supports pagination.
Inputs: schemaPattern, limit, skip, listNames.
halopsa_list_api_endpointsA
List all API endpoints with their paths, methods, and summaries. Use this first to discover available endpoints, then use halopsa_get_api_endpoint_details for full details. Supports pagination.
Inputs: category, limit, skip.
halopsa_list_columnsA
List columns for a specific table in the HaloPSA database using information_schema.columns. Returns detailed column information including data types, max length, and nullable status.
Inputs: tableName (required), columnFilter.
halopsa_list_tablesA
List all available tables in the HaloPSA database by querying sys.tables. Returns a complete list of all tables that can be queried. Use this to discover what data is available before writing queries.
Inputs: filter.
halopsa_queryA
Execute a SQL query against HaloPSA reporting API. Use this to retrieve data from any HaloPSA table including tickets (FAULTS), users (USERS), sites (SITE), actions (ACTIONS), request types (REQUESTTYPE), and more. Returns the full report response with data rows, column metadata, and available filters.
Inputs: sql (required), loadReportOnly.
halopsa_search_api_endpointsA
Search for API endpoints by keywords. Returns matching endpoints with basic info. Use halopsa_get_api_endpoint_details for full details of specific endpoints. Supports pagination.
Inputs: query (required), limit, skip.
halopsa_table_infoA
Get detailed information about a specific HaloPSA table including all columns, data types, nullable fields, and relationship suggestions. Use this to understand table structure before writing queries.
Inputs: tableName (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
The tools have some overlap that could cause confusion, particularly between halopsa_list_tables/halopsa_list_columns/halopsa_table_info for database exploration and halopsa_list_api_endpoints/halopsa_search_api_endpoints/halopsa_get_api_endpoint_details for API discovery. However, the descriptions help clarify their specific purposes, preventing complete ambiguity.
All tools follow a consistent halopsa_verb_noun naming pattern with clear, descriptive names. The structure is uniform throughout the set, making it easy to predict tool purposes and maintain readability.
With 10 tools, the count is well-scoped for a server focused on database and API interaction for HaloPSA. Each tool serves a distinct role in the workflow, from discovery to execution, without feeling excessive or insufficient.
The toolset covers essential workflows for database querying and API interaction, including discovery, schema inspection, and execution. Minor gaps exist, such as no direct tools for data modification (e.g., insert/update) or advanced API operations beyond calls, but agents can work around these using the provided tools.
Related MCP Connectors
Query your team's drift, vulnerability, and upgrade data from any AI assistant. OAuth 2.1, 51 tools.
Helpdesk tickets from your AI: find, reply, take, hold, complete — within your own role. OAuth.
Connect any AI assistant to Odoo 16–19 via OAuth 2.0 + PKCE. 400 free calls, no local install.
Connect AI assistants to JustRoadmap to list, read and update workspaces, roadmaps, lanes and items. OAuth sign-in with read-only or read-and-change access per workspace. No delete tools.