Autotask MCP Server
Autotask MCP Server gives MCP-compatible AI assistants direct, tool-based access to an Autotask PSA environment for MSP workflows.
Search, create, and update companies, contacts, tickets, projects, tasks, phases, resources, and configuration items.
Work with ticket details, notes, attachments, charges, checklist items, audit history, and time entries.
Manage financial and sales data including billing items, invoices, expense reports/items, quotes/quote items, opportunities, products, services, and service bundles.
Manage contracts and contract service lines, including expiring-contract reporting.
Handle service calls, ticket associations, and technician assignments.
Discover picklists/field values, queues, statuses, priorities, categories, and use a router or raw REST escape hatch for unsupported endpoints.
Support local stdio and remote HTTP transports, credential/impersonation modes, caching, rate-limit handling, and interactive ticket cards in MCP Apps hosts.
Offers containerized deployment options for the Autotask MCP server with production and development configurations
Provides a Node.js implementation for accessing Autotask PSA data, with support for companies, contacts, tickets, and time entries management
Enables structured access to Kaseya Autotask PSA data and operations, including companies, contacts, tickets, time entries with comprehensive CRUD operations and advanced search capabilities
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., "@Autotask MCP Server show me open tickets for Acme Corp from this week"
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.
Autotask MCP Server
Give your AI assistant direct access to Autotask. Search tickets, create time entries, look up companies, manage projects — all through natural language. No more copy-pasting between browser tabs and chat windows.
This is a Model Context Protocol (MCP) server that connects Claude (or any MCP-compatible AI) to your Autotask PSA environment. Your AI assistant gets 101 tools covering the operations MSP teams use daily: ticket triage, time logging, company lookups, project management, billing review, and more.
If you run an MSP on Autotask and you're tired of the context-switching tax, this is for you.
Part of the MSP Claude Plugins ecosystem — a growing suite of AI integrations for the MSP stack including Datto RMM, IT Glue, HaloPSA, ConnectWise Automate, NinjaOne, Huntress, and more. Built by MSPs, for MSPs.
One-Click Deployment
Note — no GitHub Packages token required. Unlike most WYRE MCP servers,
autotask-mcpdoes not depend on a private@wyre-ai/*package on GitHub Packages. Its only WYRE dependency is theautotask-nodeSDK, declared as a git dependency on the publicWYRE-AI/autotask-noderepo, whichnpm installresolves anonymously. The DigitalOcean one-click deploy therefore works without anyNODE_AUTH_TOKEN/GITHUB_TOKENbuild variable.
Related MCP server: ConnectWise API Gateway MCP Server
Quick Start
Claude Desktop — download, open, done:
Download
autotask-mcp.mcpbfrom the latest releaseOpen the file (double-click or drag into Claude Desktop)
Enter your Autotask credentials when prompted (Username, Secret, Integration Code)
No terminal, no JSON editing, no Node.js install required.
Claude Code (CLI):
claude mcp add autotask-mcp \
-e AUTOTASK_USERNAME=your-user@company.com \
-e AUTOTASK_SECRET=your-secret \
-e AUTOTASK_INTEGRATION_CODE=your-code \
-- npx -y github:WYRE-AI/autotask-mcpSee Installation for Docker and from-source methods.
Features
🔌 MCP Protocol Compliance: Full support for MCP resources and tools
🎴 Interactive Ticket Card (MCP Apps):
autotask_get_ticket_detailsrenders as an interactive card in MCP Apps hosts (Claude Desktop/web) with an in-card "Add note" round-trip; neutral theme by default, brandable viaMCP_BRAND_*env vars. In every host, the text the assistant reads carries the full ticket: description, contact, linked configuration item, custom fields (UDFs), recent notes and the complete record as JSON🛠️ Comprehensive API Coverage: 101 tools spanning companies, contacts, tickets, projects, billing items, time entries, notes, attachments, and more
🔍 Advanced Search: Powerful search capabilities with filters across all entities
📝 CRUD Operations: Create, read, update operations for core Autotask entities
🔄 ID-to-Name Mapping: Automatic resolution of company and resource IDs to human-readable names
⚡ Intelligent Caching: Smart caching system for improved performance and reduced API calls
🔒 Secure Authentication: Enterprise-grade API security with Autotask credentials
🌐 Dual Transport: Supports both stdio (local) and HTTP Streamable (remote/Docker) transports
📦 MCPB Packaging: One-click installation via MCP Bundle for desktop clients
🐳 Docker Ready: Containerized deployment with HTTP transport and health checks
📊 Structured Logging: Comprehensive logging with configurable levels and formats
🧪 Test Coverage: Comprehensive test suite with 80%+ coverage
Table of Contents
Installation
Option 1: MCPB Bundle (Claude Desktop)
The simplest method — no terminal, no JSON editing, no Node.js install required.
Download
autotask-mcp.mcpbfrom the latest releaseOpen the file (double-click or drag into Claude Desktop)
Enter your Autotask credentials when prompted (Username, Secret, Integration Code)
For Claude Code (CLI), one command:
claude mcp add autotask-mcp \
-e AUTOTASK_USERNAME=your-user@company.com \
-e AUTOTASK_SECRET=your-secret \
-e AUTOTASK_INTEGRATION_CODE=your-code \
-- npx -y github:WYRE-AI/autotask-mcpOption 2: Docker
Local (stdio — for Claude Desktop or Claude Code):
{
"mcpServers": {
"autotask": {
"command": "docker",
"args": [
"run", "--rm", "-i",
"-e", "MCP_TRANSPORT=stdio",
"-e", "AUTOTASK_USERNAME=your-user@company.com",
"-e", "AUTOTASK_SECRET=your-secret",
"-e", "AUTOTASK_INTEGRATION_CODE=your-code",
"--entrypoint", "node",
"ghcr.io/wyre-ai/autotask-mcp:latest",
"dist/entry.js"
]
}
}
}Remote (HTTP Streamable — for server deployments):
docker run -d \
--name autotask-mcp \
-p 127.0.0.1:8080:8080 \
-e CONDUIT_S2S_SECRET="your-real-s2s-secret" \
-e AUTOTASK_USERNAME="your-user@company.com" \
-e AUTOTASK_SECRET="your-secret" \
-e AUTOTASK_INTEGRATION_CODE="your-code" \
--restart unless-stopped \
ghcr.io/wyre-ai/autotask-mcp:latest
# Verify (health does not require X-Gateway-S2S)
curl http://127.0.0.1:8080/healthThe HTTP server refuses to start when CONDUIT_S2S_SECRET is empty or a known placeholder. Clients connect to http://127.0.0.1:8080/mcp using MCP Streamable HTTP transport and must send X-Gateway-S2S. See X-Gateway-S2S signing.
Gateway Mode (for MCP Gateway deployments):
When deploying behind an MCP Gateway that injects credentials via HTTP headers. This container has no static Autotask credentials:
docker run -d \
--name autotask-mcp \
-p 127.0.0.1:8080:8080 \
-e CONDUIT_S2S_SECRET="your-real-s2s-secret" \
-e AUTH_MODE=gateway \
--restart unless-stopped \
ghcr.io/wyre-ai/autotask-mcp:latestThe gateway injects credentials via headers:
X-Gateway-S2S: service-to-service proof (required on/mcp)X-API-Key: Autotask usernameX-API-Secret: Autotask secretX-Integration-Code: Autotask integration codeX-Impersonation-Resource-Id: (optional) Autotask resource ID to act on behalf of
A /mcp request missing any of the three Autotask headers returns 401 and does not fall back to AUTOTASK_* in the environment. See Gateway Mode for details.
Option 3: From Source (Development)
git clone https://github.com/WYRE-AI/autotask-mcp.git
cd autotask-mcp
npm ci && npm run buildThen point your MCP client at dist/entry.js:
{
"mcpServers": {
"autotask": {
"command": "node",
"args": ["/path/to/autotask-mcp/dist/entry.js"],
"env": {
"AUTOTASK_USERNAME": "your-user@company.com",
"AUTOTASK_SECRET": "your-secret",
"AUTOTASK_INTEGRATION_CODE": "your-code"
}
}
}
}Prerequisites
Valid Autotask API credentials (API user email, secret, integration code)
MCP-compatible client (Claude Desktop, Claude Code, etc.)
Docker (for Option 2) or Node.js 18+ (for Option 3)
Configuration
Environment Variables
Create a .env file with your configuration:
# Required Autotask API credentials (Local Mode)
AUTOTASK_USERNAME=your-api-user@example.com
AUTOTASK_SECRET=your-secret-key
AUTOTASK_INTEGRATION_CODE=your-integration-code
# Optional configuration
# AUTOTASK_API_URL is auto-detected from AUTOTASK_USERNAME via Autotask's
# unauthenticated zoneInformation endpoint on first connect. Only set this
# explicitly to override auto-detection (e.g. for an on-prem proxy).
# AUTOTASK_API_URL=https://webservices2.autotask.net/atservicesrest/
# Attribute notes and other supported writes to this Autotask resource (env mode)
# AUTOTASK_IMPERSONATION_RESOURCE_ID=29682886
MCP_SERVER_NAME=autotask-mcp
# Authentication mode
AUTH_MODE=env # env (local), gateway (hosted)
# Required to start HTTP. Empty and known placeholders are rejected.
# Never commit a real value. stdio does not use this.
CONDUIT_S2S_SECRET=
# Local HTTP only. Exactly "1" skips X-Gateway-S2S and forces 127.0.0.1.
# MCP_ALLOW_INSECURE_DEV=1
# Transport (stdio for local/desktop, http for remote/Docker)
MCP_TRANSPORT=stdio # stdio, http
MCP_HTTP_PORT=8080 # HTTP transport port (only used when MCP_TRANSPORT=http)
# Honored when CONDUIT_S2S_SECRET is set. Without a usable secret the bind is 127.0.0.1.
MCP_HTTP_HOST=0.0.0.0 # HTTP transport bind address
# Logging
LOG_LEVEL=info # error, warn, info, debug
LOG_FORMAT=simple # simple, json
# Search-result name enrichment
# Max concurrent Autotask API calls used to resolve company/resource names on
# search results. Kept low to stay under Autotask's per-integration
# concurrent-thread limit (raising it risks HTTP 429 "thread threshold").
AUTOTASK_ENHANCE_CONCURRENCY=3
# Max Autotask REST calls in flight per tenant. Further calls queue instead of
# tripping the concurrent-thread limit (HTTP 429 "thread threshold").
AUTOTASK_MAX_INFLIGHT=3
# Environment
NODE_ENV=productionGateway Mode
When deployed behind an MCP Gateway (e.g., mcp.wyre.ai), the server operates in gateway mode where credentials are injected via HTTP headers on each request.
Enable Gateway Mode:
AUTH_MODE=gateway
MCP_TRANSPORT=http
CONDUIT_S2S_SECRET=<gateway-provisioned secret>Every /mcp request must include a valid X-Gateway-S2S header and the three Autotask credential headers. A request missing any credential header returns 401. The server does not fall back to AUTOTASK_USERNAME, AUTOTASK_SECRET, or AUTOTASK_INTEGRATION_CODE in the process environment.
Expected Headers:
Header | Description |
| Service-to-service proof. |
| Autotask API username (email) |
| Autotask API secret key |
| Autotask integration code |
| (Optional) Custom Autotask API URL |
| (Optional) Verified email of the Conduit user making the call. Honored only on Node HTTP with a usable |
| (Optional) |
| (Optional) Autotask resource ID to act on behalf of. Forwarded to Autotask as its |
Impersonation
Autotask attributes writes to another resource when a request carries the ImpersonationResourceId header. The server sends it on every Autotask call when a resource is set; Autotask applies it only to entities and actions that support impersonation and ignores it elsewhere. The supported list (see Entities that support impersonation) includes the note entities this server writes (TicketNote, ProjectNote, CompanyNote), plus TimeEntry, Ticket, Projects, Company, Contact, ServiceCall, Opportunity and Quote. Autotask records the impersonated resource as the creator and fills the read-only impersonatorCreatorResourceID; setting that field in a body does nothing.
Autotask's requirements:
The API-only user's security level must allow impersonation on the entity type.
The impersonated resource's security level must allow it to be impersonated ("Allow impersonation of resources with this security level").
Both must have permission to add or edit the entity.
Where the resource ID comes from:
Mode | Source | Fallback |
|
| None. Resource IDs are tenant-specific, so an env default is never applied to gateway requests. |
|
|
|
|
| None. The Worker route has no |
|
| None |
A per-request value builds a fresh service for that request only, so it never carries over to another request. Values that aren't positive integers are ignored with a warning. If Autotask rejects an impersonated call, the error says which resource was being impersonated and the call is not retried as the API user.
Acting-user impersonation
Default off. Note on v2.40.0: v2.40.0 turned acting-user impersonation on for every gateway request. On tenants whose Autotask API user isn't allowed to impersonate, every ticket note then failed with HTTP 500 "The logged in Resource does not have the adequate permissions to create this entity type.", and that response wasn't retried. v2.41.1 made the feature opt-in and retries that 500 once as the API user, and v2.42.0 added the per-connection opt-in header. Don't run v2.40.0.
Ways to impersonate, from highest precedence:
Source | Scope | Behavior on refusal |
Explicit resource ID: | Every call on that request or server | Strict: the call fails, and is never retried as the API user |
Acting-user email ( | Writes only | Best-effort: falls back to the API user as described below |
Neither | Every call runs as the API user (the default) |
Opt-in: this is off unless the sidecar runs with AUTOTASK_IMPERSONATE_ACTING_USER=true (or 1) for every tenant, or the request carries X-Autotask-Impersonate-Acting-User: on (also true/1) for that connection. Conduit sets that header from the Autotask connection's "Post writes as the signed-in person" setting. Both are honored only after X-Gateway-S2S verifies. When off, the email header is ignored and writes run as the tenant's API user.
In gateway mode, Conduit sends the acting user's verified email in X-Conduit-Acting-User-Email, and the sidecar attributes that person's writes to their own Autotask resource:
On the first write of a request (POST create, PATCH, PUT or DELETE; never a GET or a
/queryread), the sidecar queries activeResourcesbyemailwith the tenant's own API credentials, as the API user.Exactly one active resource with that exact email (case-insensitive) is a match. The write carries
ImpersonationResourceId: <id>.No match, more than one active match, or only inactive matches mean the write runs as the API user, as it did before.
If Autotask refuses the impersonation, attribution for that user and operation (method and entity route) is switched off for 6 hours (
AUTOTASK_IMPERSONATION_REJECTED_TTL_MS). Other operations keep impersonating. What happens to the refused write depends on the response:A 403, or another 4xx (except 429) that mentions impersonation: the write is retried once as the API user. A rejected 4xx request was not applied, so the retry can't double-write.
A structured 500 saying the logged-in resource "does not have the adequate permissions to create this entity type": the write is retried once as the API user. This is Autotask's permission check, so nothing was written. It's what Autotask returns when the API user's security level doesn't allow impersonation (see the v2.40.0 note below).
Any other 500 whose structured
errorslist mentions impersonation: the write is not retried, because Autotask doesn't guarantee that a 500 wasn't applied. The call fails with a hint, and the next attempt runs as the API user.Gateway 5xx responses and unstructured 500s are not treated as refusals at all.
Usually a refusal means the tenant hasn't enabled impersonation in the security levels (see Impersonation).
Lookups are cached per tenant (API username) and email: matches for 15 minutes, misses for 5 minutes, lookup errors for 1 minute. You can tune this with AUTOTASK_IMPERSONATION_CACHE_TTL_MS and AUTOTASK_IMPERSONATION_MISS_TTL_MS. Cache keys are SHA-256 hashes, so raw emails are never stored. Lookup outcomes are logged at debug level, without the email.
Both headers (X-Conduit-Acting-User-Email and X-Autotask-Impersonate-Acting-User) are trusted only because Conduit is the only caller that can pass X-Gateway-S2S. Conduit sets the email from the user's verified login and the opt-in from the connection's stored setting, and strips any client-supplied copy. The sidecar ignores it on the Cloudflare Worker (no S2S check) and on an insecure-dev listener. An explicit X-Impersonation-Resource-Id always wins and keeps its strict behavior: it applies to every call, and a rejection fails the call.
X-Gateway-S2S signing
MCP_TRANSPORT=http refuses to start unless CONDUIT_S2S_SECRET is a real secret. Empty values and known placeholders are rejected, including changeme, placeholder, your-s2s-secret, secret, password, test, and any value that is only an unresolved ${...} template. The process logs an error and exits non-zero. It never prints the secret.
MCP_ALLOW_INSECURE_DEV=1 is the local-only escape hatch. The process logs a warning, does not check X-Gateway-S2S, and listens on 127.0.0.1 only. A non-loopback MCP_HTTP_HOST (including 0.0.0.0, localhost, and ::1) is ignored in that mode and the override is logged.
Without a usable secret the bind address defaults to 127.0.0.1. A configured secret honors MCP_HTTP_HOST (default 0.0.0.0 when that variable is unset, which is what the container image sets). Publish the host port on loopback unless a proxy sits in front.
/health stays unauthenticated and does not read credentials. The stdio transport does not use CONDUIT_S2S_SECRET.
With a usable secret, every /mcp request must include:
X-Gateway-S2S: t=<unix seconds>,v1=<lowercase hex>v1 is HMAC-SHA256, hex-encoded, of the ASCII string t=<unix seconds> (the same t= prefix that starts the header), keyed with CONDUIT_S2S_SECRET. The timestamp must be within 300 seconds of the server clock. A missing or invalid header returns HTTP 401. The secret is never written to logs or the response body.
# t is the current unix time. v1 is HMAC-SHA256 of the literal "t=$t".
t=$(date +%s)
v1=$(printf 't=%s' "$t" | openssl dgst -sha256 -hmac "$CONDUIT_S2S_SECRET" | awk '{print $NF}')
curl -sS http://127.0.0.1:8080/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-H "X-Gateway-S2S: t=${t},v1=${v1}" \
-H "X-API-Key: api-user@example.com" \
-H "X-API-Secret: the-api-secret" \
-H "X-Integration-Code: the-integration-code" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'In AUTH_MODE=env, /mcp still requires a valid X-Gateway-S2S header. Autotask credentials then come from AUTOTASK_*. In AUTH_MODE=gateway, the three X-API-* headers above are required as well and are the only credential source for that request.
Health Check Response (Gateway Mode):
{
"status": "ok",
"transport": "http",
"authMode": "gateway",
"timestamp": "2026-02-05T10:00:00.000Z"
}For detailed migration instructions, see the Migration Guide.
💡 Pro Tip: Copy the above content to a .env file in your project root.
Autotask API Setup
Create API User: In Autotask, create a dedicated API user with appropriate permissions
Generate Secret: Generate an API secret for the user
Integration Code: Obtain your integration code from Autotask
Permissions: Ensure the API user has read/write access to required entities
For detailed setup instructions, see the Autotask API documentation.
Usage
Command Line
# Start the MCP server (stdio transport, for piping to an MCP client)
node dist/entry.js
# HTTP refuses to start until CONDUIT_S2S_SECRET is a real secret
CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" MCP_TRANSPORT=http node dist/index.js
# Local HTTP only, without a service-to-service secret (always binds 127.0.0.1)
MCP_ALLOW_INSECURE_DEV=1 MCP_TRANSPORT=http node dist/index.jsMCP Client Configuration
See Installation for all setup methods.
API Reference
Resources
Resources provide read-only access to Autotask data:
autotask://companies- List all companiesautotask://companies/{id}- Get specific companyautotask://contacts- List all contactsautotask://contacts/{id}- Get specific contactautotask://tickets- List all ticketsautotask://tickets/{id}- Get specific ticketautotask://time-entries- List time entries
Tools
The server provides 101 tools for interacting with Autotask:
Company Operations
autotask_search_companies- Search companies with filtersautotask_create_company- Create new companyautotask_update_company- Update existing company
Contact Operations
autotask_search_contacts- Search contacts with filtersautotask_create_contact- Create new contact
Ticket Operations
autotask_search_tickets- Search tickets with filtersautotask_get_ticket_details- Get a ticket by ID: description, status/priority/queue, company, contact, assignee, dates, linked configuration item, resolution, custom fields (UDFs), recent notes and the full record (fullDetails: truefor untruncated text and all UDFs)autotask_create_ticket- Create new ticket
Time Entry Operations
autotask_create_time_entry- Log time entryautotask_search_time_entries- Search time entries with filters (resource, ticket, task, date range); each entry includessummaryNotesandinternalNotes
Billing Items (Approve and Post Workflow)
autotask_search_billing_items- Search approved and posted billing itemsautotask_get_billing_item- Get specific billing item by IDautotask_search_billing_item_approval_levels- Search multi-level approval records for time entries
Project Operations
autotask_search_projects- Search projects with filtersautotask_create_project- Create new project
Resource Operations
autotask_search_resources- Search resources (technicians/users)
Note Operations
autotask_get_ticket_note/autotask_search_ticket_notes/autotask_create_ticket_noteautotask_get_project_note/autotask_search_project_notes/autotask_create_project_noteautotask_get_company_note/autotask_search_company_notes/autotask_create_company_note
Attachment Operations
autotask_get_ticket_attachment- Get ticket attachmentautotask_search_ticket_attachments- Search ticket attachmentsautotask_get_ticket_note_attachment- Get an attachment on a ticket note (e.g. a pasted screenshot)autotask_search_ticket_note_attachments- Search attachments on a ticket note
Financial Operations
autotask_get_expense_report/autotask_search_expense_reports/autotask_create_expense_reportautotask_get_quote/autotask_search_quotes/autotask_create_quoteautotask_get_opportunity/autotask_search_opportunities/autotask_create_opportunityautotask_update_opportunity- Update an opportunity (stage, status, revenue/cost lines, UDFs)autotask_search_invoices- Search invoices
Contract Operations
autotask_search_contracts- Search contracts (name, company, status, type, end-date range)autotask_get_contract- Get a single contract by IDautotask_list_expiring_contracts- Expiring/expired contracts report (next N days, per company or org-wide)autotask_create_contract/autotask_create_contracts_bulk- Create contract shells, one or manyautotask_update_contract- Update a contract (e.g. extend/renew end date)autotask_create_contract_service/autotask_update_contract_service- Manage contract service lines
Configuration Items
autotask_search_configuration_items- Search configuration items (assets)
Task Operations
autotask_search_tasks- Search project tasksautotask_create_task- Create project task
Utility Operations
autotask_test_connection- Test API connectivity
Example Tool Usage
// Search for companies
{
"name": "autotask_search_companies",
"arguments": {
"searchTerm": "Acme Corp",
"isActive": true,
"pageSize": 10
}
}
// Create a new ticket
{
"name": "autotask_create_ticket",
"arguments": {
"companyID": 12345,
"title": "Server maintenance request",
"description": "Need to perform monthly server maintenance",
"priority": 2,
"status": 1
}
}ID-to-Name Mapping
The Autotask MCP server includes intelligent ID-to-name mapping that automatically resolves company and resource IDs to human-readable names, making API responses much more useful for AI assistants and human users.
Automatic Enhancement
All search and detail tools automatically include an _enhanced field with resolved names:
{
"id": 12345,
"title": "Sample Ticket",
"companyID": 678,
"assignedResourceID": 90,
"_enhanced": {
"companyName": "Acme Corporation",
"assignedResourceName": "John Smith"
}
}How It Works
ID-to-name mapping is applied automatically to all search and detail tool results. No additional tools are needed — the _enhanced field is added transparently to every response that contains company or resource IDs.
Performance Features
Smart Caching: Names are cached for 30 minutes to reduce API calls
Bulk Operations: Efficient batch lookups for multiple IDs
Graceful Fallback: Returns "Unknown Company (123)" if lookup fails
Parallel Processing: Multiple mappings resolved simultaneously
Testing Mapping
Test the mapping functionality:
npm run test:mappingFor detailed mapping documentation, see docs/mapping.md.
HTTP Transport
The server supports the MCP Streamable HTTP transport for remote deployments (e.g., Docker, cloud hosting). Set MCP_TRANSPORT=http to enable it.
# Start with HTTP transport (exits unless CONDUIT_S2S_SECRET is a real secret)
CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" MCP_TRANSPORT=http MCP_HTTP_PORT=8080 node dist/index.jsThe HTTP transport exposes:
POST /mcp— MCP Streamable HTTP endpoint. RequiresX-Gateway-S2SwhenCONDUIT_S2S_SECRETis set. See X-Gateway-S2S signing.GET /health— Unauthenticated health check (returns{"status":"ok"}). Does not read credentials.
Clients must send requests to /mcp with Accept: application/json, text/event-stream headers per the MCP Streamable HTTP specification.
Docker Deployment
The Docker image uses HTTP transport by default (port 8080) with a built-in health check.
Using Pre-built Image from GitHub Container Registry
The Docker image defaults to HTTP transport on port 8080 — suitable for remote/server deployments where clients connect over the network.
# Pull the latest image
docker pull ghcr.io/wyre-ai/autotask-mcp:latest
# Run container with HTTP transport (default). The image binds 0.0.0.0 inside
# the container; publish on loopback and pass the S2S secret.
docker run -d \
--name autotask-mcp \
-p 127.0.0.1:8080:8080 \
-e CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" \
-e AUTOTASK_USERNAME="your-api-user@example.com" \
-e AUTOTASK_SECRET="your-secret-key" \
-e AUTOTASK_INTEGRATION_CODE="your-integration-code" \
--restart unless-stopped \
ghcr.io/wyre-ai/autotask-mcp:latest
# Verify it's running (health does not require X-Gateway-S2S)
curl http://127.0.0.1:8080/healthCompose will not start when CONDUIT_S2S_SECRET is unset. The checked-in gateway service sets AUTH_MODE=gateway, publishes 127.0.0.1:8080:8080, and does not inject AUTOTASK_*:
CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" docker compose upFor stdio usage with Claude Desktop, see Installation Option 2.
Quick Start (From Source)
# Clone repository
git clone https://github.com/WYRE-AI/autotask-mcp.git
cd autotask-mcp
# Create environment file
cp .env.example .env
# Edit .env with your credentials
# Start with docker-compose
docker compose up -dProduction Deployment
# Build production image locally
docker build -t autotask-mcp:latest .
# Run container
docker run -d \
--name autotask-mcp \
--env-file .env \
--restart unless-stopped \
autotask-mcp:latestDevelopment Mode
# Start development environment with hot reload
docker compose --profile dev up autotask-mcp-devDevelopment
Setup
git clone https://github.com/WYRE-AI/autotask-mcp.git
cd autotask-mcp
npm installAvailable Scripts
npm run dev # Start development server with hot reload
npm run build # Build for production
npm run test # Run test suite
npm run test:watch # Run tests in watch mode
npm run test:coverage # Run tests with coverage
npm run lint # Run ESLint
npm run lint:fix # Fix ESLint issuesProject Structure
autotask-mcp/
├── src/
│ ├── handlers/ # MCP request handlers
│ ├── mcp/ # MCP server implementation
│ ├── services/ # Autotask service layer
│ ├── types/ # TypeScript type definitions
│ ├── utils/ # Utility functions (config, logger, cache)
│ ├── entry.ts # Entry point (stdout guard + .env loader)
│ └── index.ts # Server bootstrap (config, logger, server init)
├── tests/ # Test files
├── scripts/ # Build and packaging scripts
│ └── pack-mcpb.js # MCPB bundle creation
├── manifest.json # MCPB manifest for desktop distribution
├── Dockerfile # Container definition (HTTP transport)
├── docker-compose.yml # Multi-service orchestration
└── package.json # Project configurationTesting
Running Tests
# Run all tests
npm test
# Run with coverage
npm run test:coverage
# Run in watch mode
npm run test:watch
# Run specific test file
npm test -- tests/autotask-service.test.tsTest Categories
Unit Tests: Service layer and utility functions
Integration Tests: MCP protocol compliance
API Tests: Autotask API integration (requires credentials)
Coverage Requirements
Minimum 80% coverage for all metrics
100% coverage for critical paths (authentication, data handling)
Configuration Reference
Environment Variables
Variable | Required | Default | Description |
| ✅ | - | Autotask API username (email) |
| ✅ | - | Autotask API secret key |
| ✅ | - | Autotask integration code |
| ❌ | Auto-detected | Autotask API endpoint URL |
| ❌ | unset (off) | Gateway mode. |
| ❌ |
| How long an acting-user email → resource match is cached (per tenant and email). |
| ❌ |
| How long a no-match, ambiguous or inactive lookup is cached. |
| ❌ |
| How long acting-user impersonation stays off for a user and operation after Autotask refuses it. |
| ❌ | unset | Env mode only. Default Autotask resource ID to impersonate, sent as Autotask's |
| ❌ |
| MCP server name |
| ❌ |
| Transport type ( |
| ❌ |
| HTTP transport port |
| ❌ |
| HTTP bind address. A configured |
| Yes for HTTP | — | Service-to-service secret for |
| ❌ | unset | Set to exactly |
| ❌ |
| Logging level |
| ❌ |
| Log output format |
| ❌ |
| Max concurrent Autotask API calls used to resolve company/resource names on search results. Kept low to stay under Autotask's concurrent-thread limit. |
| ❌ |
| Max Autotask REST calls in flight per tenant. Further calls queue in the HTTP client instead of tripping the concurrent-thread limit. |
| ❌ |
| Node.js environment |
Logging Levels
error: Only error messageswarn: Warnings and errorsinfo: General information, warnings, and errorsdebug: Detailed debugging information
Log Formats
simple: Human-readable console outputjson: Structured JSON output (recommended for production)
Rate Limits
Autotask enforces per-integration-code API thresholds on a rolling 1-hour window:
~10,000 req/hr (soft) — warning email, sporadic
HTTP 429responses~20,000 req/hr (hard) — sustained
HTTP 429until the window rolls
LLM-driven workflows fan out easily — "status report on all open projects with notes" can issue hundreds of requests across a few minutes. The server tries to make this safer:
429 responses are surfaced as structured errors. Tool results carry
error_type: "rate_limited"and aretry_after_secondsfield parsed from Autotask'sRetry-Afterheader. The error message explicitly tells the LLM not to retry and to ask the user to scope the query — this prevents repeated retries from extending the cooldown.Concurrent-thread 429s are queued, not cooled down for a minute. Autotask also returns HTTP 429 when an integration exceeds its thread threshold (the body mentions "thread threshold"). That is a burst problem, separate from the hourly quota. The HTTP client allows
AUTOTASK_MAX_INFLIGHTcalls in flight per tenant (default 3) and queues the rest. A thread-threshold 429 on an idempotent call (GET,DELETE, orPOST /{Entity}/query) is retried with a short backoff and does not arm the 60s cooldown. Hourly-threshold 429s still arm it. Create/update calls are not retried automatically.Fan-out tool descriptions include rate-limit tips. Tools that are commonly looped over (
autotask_search_ticket_notes,autotask_search_project_notes,autotask_search_company_notes,autotask_search_time_entries,autotask_search_ticket_attachments,autotask_search_ticket_note_attachments) include a hint reminding the LLM to scope the parent record list before iterating.
Raising the limit
Per-integration thresholds can be increased in Autotask:
Autotask Admin → Resources/Users (HR) → Resources
Edit the dedicated API user → Workflow Rules → API Tracking Identifier
Adjust the threshold for the integration code your MCP server uses
This is the right answer when a single integration code is shared between Claude/Copilot/etc. and other tooling. For LLM-heavy workloads, dedicate a separate API user (and integration code) so a fan-out from one client doesn't starve others.
Patterns that help
Always scope by date range when searching notes, time entries, attachments. Even a 30-day window can drop call count by an order of magnitude.
Cache parent lookups. If you're iterating over 100 tickets, fetch the ticket list once and reuse it across follow-up queries; don't re-search per child.
Use
autotask_get_field_infoto discover picklist values once per session rather than refetching them per call.
If you're seeing threshold warnings from Autotask but the server seems fine, the LLM driver is probably issuing fan-out patterns. Tighten the prompt to scope before iterating.
Troubleshooting
Common Issues
Authentication Errors
Error: Missing required Autotask credentialsSolution: Ensure all required environment variables are set correctly.
Connection Timeouts
Error: Connection to Autotask API failedSolutions:
Check network connectivity
Verify API endpoint URL
Confirm API user has proper permissions
Permission Denied
Error: User does not have permission to access this resourceSolution: Review Autotask API user permissions and security level settings.
Debug Mode
Enable debug logging for detailed troubleshooting:
LOG_LEVEL=debug npm startHealth Checks
Test server connectivity:
# Run test suite
npm run test
# For HTTP transport, check the health endpoint
curl http://localhost:8080/health
# Returns: {"status":"ok"}
# Test API connection with debug logging
LOG_LEVEL=debug npm startAutotask API Rate Limits
Problem: 429 Too Many Requests or "thread limit exceeded" errors when Claude queries aggressively
Autotask enforces 3 concurrent threads per endpoint per API tracking identifier. When an LLM issues multiple tool calls simultaneously (e.g., searching tickets, companies, and contacts at once), requests can pile up and hit this limit.
Built-in mitigation: The HTTP client caps in-flight requests per tenant (AUTOTASK_MAX_INFLIGHT, default 3) and queues the rest, so a parallel burst waits for a free slot instead of tripping the thread threshold. You may notice slower responses under heavy load. A thread-threshold 429 on an idempotent call is retried briefly; the hourly request threshold still surfaces as a structured rate-limit error and a short tenant cooldown.
Critical for team/multi-user deployments: If multiple users or the MCP Gateway share the same API credentials, they compete for the same 3-thread budget. This can cause noticeable slowdowns and, in severe cases, queued requests that time out.
Solution — one API key per team: Create a dedicated Autotask API user per team or integration. Each user has an independent integrationCode with its own thread budget:
Admin > Resources (Users) > Resources/Users → Add Resource
Set Security Level to API User
Note the username, secret, and integration code
Set
AUTOTASK_USERNAME,AUTOTASK_SECRET, andAUTOTASK_INTEGRATION_CODEper team
Support Team → AUTOTASK_INTEGRATION_CODE=SUPPORT_TEAM_CODE (3 threads)
Projects Team → AUTOTASK_INTEGRATION_CODE=PROJECTS_TEAM_CODE (3 threads, independent)Additionally, Autotask limits 10,000 total requests per hour across all integrations hitting your tenant. If you hit this limit, all integrations will start receiving 429s — another reason to use targeted queries with appropriate filters.
MCP Client Issues
Problem: MCP server not appearing in Claude Desktop Solutions:
Check configuration file syntax (valid JSON)
Verify file path in the configuration
Ensure environment variables are set correctly
Restart Claude Desktop completely
Problem: "Invalid JSON-RPC message: [dotenv@...] injecting env" / Server disconnected
Cause: The autotask-node library calls dotenv.config() at module load time. dotenv v17+ writes status messages via console.log to stdout, which corrupts the MCP stdio JSON-RPC channel.
Solution: Ensure you're using dist/entry.js (not dist/index.js) as the entry point. The entry wrapper redirects console.log to stderr before any libraries load.
Problem: Slow responses Solutions:
Check network connectivity to Autotask API
Enable debug logging (
LOG_LEVEL=debug) to identify bottlenecksThe server caches company/resource names for 30 minutes automatically
Security Best Practices
Store credentials in environment variables, not directly in config files
Limit Autotask API user permissions to the minimum required
Rotate API credentials regularly
For Docker deployments, use secrets management rather than plain environment variables
Contributing
Fork the repository
Create a feature branch (
git checkout -b feature/amazing-feature)Commit your changes (
git commit -m 'Add amazing feature')Push to the branch (
git push origin feature/amazing-feature)Open a Pull Request
Development Guidelines
Follow TypeScript best practices
Maintain test coverage above 80%
Use conventional commit messages
Update documentation for API changes
Add tests for new features
License
This project is licensed under the Apache License 2.0. See the LICENSE file for details.
Contributor License Agreement
By submitting a pull request, you agree to the terms of our Contributor License Agreement. This ensures that contributions can be properly licensed and that you have the right to submit the code.
Contributors
Avatar | Name | Contributions |
Maintainer | ||
CLI bin fix |
Support
Acknowledgments
Model Context Protocol by Anthropic
Autotask REST API by Kaseya
autotask-node library
Built by WYRE Technology — part of the MSP Claude Plugins ecosystem
Available Tools
98 toolsautotask_create_companyC
Create new company record
Inputs: companyName (required), companyType (required), city, phone, +5 more.
autotask_create_company_noteB
Create a new note for a company
Inputs: companyId (required), description (required), title, actionType.
autotask_create_contactC
Create new contact record
Inputs: lastName (required), companyID (required), firstName (required), phone, +2 more.
autotask_create_contractA
Create a new Contract in Autotask. Field names match the Autotask REST API exactly. status: 1=In Effect, 0=Inactive. Dates are ISO format (YYYY-MM-DD).
Inputs: endDate (required), companyID (required), startDate (required), contractName (required), +27 more.
autotask_create_contract_serviceA
Add a ContractService (service line item) to an existing Contract.
Inputs: serviceID (required), unitPrice (required), contractID (required), unitCost, +4 more.
autotask_create_expense_itemB
Create an expense item on an existing expense report
Inputs: amount (required), description (required), expenseDate (required), expenseCategory (required), +6 more.
autotask_create_expense_reportC
Create a new expense report
Inputs: name (required), submitterId (required), weekEndingDate (required), description.
autotask_create_opportunityB
Create a new sales opportunity in Autotask
Inputs: stage (required), title (required), status (required), companyId (required), +11 more.
autotask_create_phaseC
Create a new phase in an Autotask project
Inputs: title (required), projectID (required), dueDate, startDate, +2 more.
autotask_create_projectC
Create a new project in Autotask
Inputs: status (required), companyID (required), projectName (required), projectType (required), +5 more.
autotask_create_project_noteC
Create a new note for a project
Inputs: projectId (required), description (required), title, publish, +2 more.
autotask_create_quoteB
Create a new quote
Inputs: companyId (required), name, contactId, description, +3 more.
autotask_create_quote_itemA
Create a line item on a quote. Set exactly ONE item reference (serviceID, productID, or serviceBundleID). Required: quoteId, quantity. Defaults: unitDiscount=0, lineDiscount=0, percentageDiscount=0, isOptional=false.
Inputs: quoteId (required), quantity (required), name, unitCost, +11 more.
autotask_create_service_callC
Create a new service call in Autotask. Service calls are used to schedule and plan work on tickets.
Inputs: description (required), endDateTime (required), startDateTime (required), status, +3 more.
autotask_create_service_call_ticketB
Link a ticket to a service call. This associates the ticket with the service call for scheduling purposes.
Inputs: ticketID (required), serviceCallID (required).
autotask_create_service_call_ticket_resourceB
Assign a resource (technician) to a service call ticket.
Inputs: resourceID (required), serviceCallTicketID (required), roleID.
autotask_create_taskC
Create a new task in Autotask
Inputs: title (required), status (required), projectID (required), taskType, +5 more.
autotask_create_ticketC
Create new ticket record
Inputs: title (required), companyID (required), description (required), source, +17 more.
autotask_create_ticket_attachmentA
Upload a file attachment to an existing ticket. The file content must be passed as a base64-encoded string in the data field (MCP is JSON-RPC, so binary bytes must be base64-encoded). Autotask enforces a 3 MB hard limit on ticket attachments; this tool validates the decoded size before calling the API and returns a clear error if the limit is exceeded. Example: { ticketId: 12345, title: "screenshot.png", data: "iVBORw0KGgoAAAANSUhEUgAA..." }
Inputs: data (required), title (required), ticketId (required), publish, +2 more.
autotask_create_ticket_chargeA
Create charge on ticket for materials, costs, or expenses.
Inputs: name (required), ticketID (required), chargeType (required), status, +8 more.
autotask_create_ticket_checklist_itemB
Add a new checklist item to a ticket.
Inputs: itemName (required), ticketId (required), position, isCompleted.
autotask_create_ticket_noteA
Create a new note for a ticket
Inputs: publish (required), noteType (required), ticketId (required), description (required), +1 more.
autotask_create_time_entryA
Create a time entry in Autotask. Can be tied to a ticket, task, or project, OR created as "Regular Time" (no parent) for meetings, admin work, etc. For Regular Time, specify a category like "Internal Meeting", "Office Management", "Training", etc.
Inputs: dateWorked (required), hoursWorked (required), summaryNotes (required), taskID, +8 more.
autotask_delete_quote_itemADestructive
⚠ DESTRUCTIVE — IRREVERSIBLE. Permanently deletes a quote item (line item) from a quote. This action cannot be undone. Confirm with the user before invoking.
Inputs: quoteId (required), quoteItemId (required).
autotask_delete_service_callADestructive
⚠ DESTRUCTIVE — IRREVERSIBLE. Permanently deletes a service call and all associated data. This action cannot be undone. Confirm with the user before invoking.
Inputs: serviceCallId (required).
autotask_delete_service_call_ticketADestructive
⚠ DESTRUCTIVE — IRREVERSIBLE. Permanently removes a ticket association from a service call. This action cannot be undone. Confirm with the user before invoking.
Inputs: serviceCallTicketId (required).
autotask_delete_service_call_ticket_resourceADestructive
⚠ DESTRUCTIVE — IRREVERSIBLE. Permanently removes a resource assignment from a service call ticket. This action cannot be undone. Confirm with the user before invoking.
Inputs: serviceCallTicketResourceId (required).
autotask_delete_ticket_chargeADestructive
⚠ DESTRUCTIVE — IRREVERSIBLE. Permanently deletes a ticket charge record and all associated billing data. This action cannot be undone. Confirm with the user before invoking.
Inputs: chargeId (required), ticketId (required).
autotask_delete_ticket_checklist_itemADestructive
⚠ DESTRUCTIVE — IRREVERSIBLE. Permanently deletes a checklist item from a ticket. This action cannot be undone. Confirm with the user before invoking.
Inputs: itemId (required), ticketId (required).
autotask_execute_toolB
Execute any Autotask tool by name. Use after discovering tools via autotask_list_category_tools.
Inputs: toolName (required), arguments.
autotask_get_billing_itemB
Get detailed information for a specific billing item by ID
Inputs: billingItemId (required).
autotask_get_company_noteB
Get a specific company note by company ID and note ID
Inputs: noteId (required), companyId (required).
autotask_get_company_site_configurationA
Get company site configuration records. Call first to discover available fields.
Inputs: companyId (required).
autotask_get_expense_reportA
Get a specific expense report by ID
Inputs: reportId (required).
autotask_get_field_infoA
Get field definitions for an Autotask entity type, including picklist values. Useful for discovering valid values for any picklist field.
Inputs: entityType (required), fieldName.
autotask_get_invoice_detailsA
Get a single Autotask invoice with its nested line items (billing items posted to the invoice). Use for finance workflows that need to see exactly what an invoice contains.
Inputs: invoiceId (required).
autotask_get_opportunityA
Get a specific opportunity by ID
Inputs: opportunityId (required).
autotask_get_productA
Get a specific product by ID
Inputs: productId (required).
autotask_get_project_noteA
Get a specific project note by project ID and note ID
Inputs: noteId (required), projectId (required).
autotask_get_quoteB
Get a specific quote by ID
Inputs: quoteId (required).
autotask_get_quote_itemA
Get a specific quote item by ID
Inputs: quoteItemId (required).
autotask_get_serviceA
Get a specific service by ID
Inputs: serviceId (required).
autotask_get_service_bundleB
Get a specific service bundle by ID
Inputs: serviceBundleId (required).
autotask_get_service_callB
Get a specific service call by ID
Inputs: serviceCallId (required).
autotask_get_ticket_attachmentA
Get a ticket attachment. With includeData=false (default) returns metadata only — fast, suitable for browsing. With includeData=true returns the base64 binary content via the top-level /TicketAttachments/{id} endpoint (the child endpoint never populates data). The attachment is verified to belong to the given ticketId. Oversized binaries are stripped from the response with a dataOmittedReason field — Autotask attachments can be up to 3 MB, which is ~4 MB as base64 and may exceed the MCP client tool-result limit (~1 MB).
Inputs: ticketId (required), attachmentId (required), includeData, maxInlineBase64Bytes.
autotask_get_ticket_chargeB
Get a specific ticket charge by ID
Inputs: chargeId (required).
autotask_get_ticket_detailsB
Get full ticket details including notes, time entries, and custom fields.
Inputs: ticketID (required), fullDetails.
autotask_get_ticket_historyA
Get a single ticket history entry by ID. Each entry records one audited change to a ticket field (who, when, before/after).
Inputs: historyId (required).
autotask_get_ticket_noteA
Get a specific ticket note by ticket ID and note ID
Inputs: noteId (required), ticketId (required).
autotask_list_categoriesA
List available tool categories. Use this to discover what types of Autotask operations are available before loading specific tools.
Inputs: no named parameters.
autotask_list_category_toolsA
List tools in a specific category with full schemas. Use after autotask_list_categories to see available tools and their parameters.
Inputs: category (required).
autotask_list_phasesB
List phases for a project in Autotask
Inputs: projectID (required), pageSize.
autotask_list_queuesA
List all available ticket queues in Autotask. Use this to find queue IDs for filtering tickets by queue.
Inputs: no named parameters.
autotask_list_ticket_prioritiesA
List all available ticket priorities in Autotask. Use this to find priority values for filtering or creating tickets.
Inputs: no named parameters.
autotask_list_ticket_statusesA
List all available ticket statuses in Autotask. Use this to find status values for filtering or creating tickets.
Inputs: no named parameters.
autotask_raw_requestA
Escape hatch for Autotask REST endpoints not yet wrapped by a typed tool. Use sparingly — typed tools are preferred for safety. The existing Content-Type, Accept, ApiIntegrationcode, UserName, Secret headers are added automatically. The path is resolved against the zone-resolved base URL (https://webservices.autotask.net/ATServicesRest/v1.0). Pass queryParams as a flat object of string/number/boolean values; they will be URL-encoded and appended to the path.
Inputs: path (required), method (required), body, queryParams.
autotask_routerA
Intelligent tool router - describe what you want to do and get the right tool suggestion with pre-filled parameters. Use this when unsure which tool to call.
Inputs: intent (required).
autotask_search_billing_item_approval_levelsB
Search for billing item approval levels. These describe multi-level approval records for Autotask time entries, enabling visibility into tiered approval workflows.
Inputs: page, pageSize, timeEntryId, approvalLevel, +3 more.
autotask_search_billing_itemsA
Search for billing items in Autotask. Billing items represent approved and posted billable items from the "Approve and Post" workflow. Returns 25 results per page by default.
Inputs: page, dateTo, dateFrom, pageSize, +8 more.
autotask_search_companiesB
Search companies by name or status. Max 200/page.
Inputs: page, isActive, pageSize, searchTerm.
autotask_search_company_notesA
Search for notes on a specific company. Iterating across many companies trips Autotask's API threshold — scope the parent list first.
Inputs: companyId (required), pageSize.
autotask_search_configuration_itemsC
Search for configuration items in Autotask with optional filters
Inputs: isActive, pageSize, companyID, productID, +3 more.
autotask_search_contactsA
Search contacts by name, email, or company. Max 200/page.
Inputs: page, isActive, pageSize, companyID, +1 more.
autotask_search_contractsC
Search for contracts in Autotask with optional filters
Inputs: status, pageSize, companyID, searchTerm.
autotask_search_expense_reportsC
Search for expense reports with optional filters
Inputs: status, pageSize, submitterId.
autotask_search_invoicesC
Search for invoices in Autotask with optional filters
Inputs: isVoided, pageSize, companyID, invoiceNumber.
autotask_search_opportunitiesC
Search for opportunities with optional filters
Inputs: status, pageSize, companyId, searchTerm.
autotask_search_productsC
Search for products with optional filters
Inputs: isActive, pageSize, searchTerm.
autotask_search_project_notesA
Search for notes on a specific project. Fan-out across many projects trips Autotask's API threshold (see issue #69) — scope the parent list (status, company, date range) first.
Inputs: projectId (required), pageSize.
autotask_search_projectsC
Search for projects in Autotask. Returns 25 results per page by default. Use page parameter for more results.
Inputs: page, status, pageSize, companyID, +2 more.
autotask_search_quote_itemsA
Search for quote items, typically filtered by quote ID
Inputs: quoteId, pageSize, searchTerm.
autotask_search_quotesC
Search for quotes with optional filters
Inputs: pageSize, companyId, contactId, searchTerm, +1 more.
autotask_search_resourcesA
Search for resources (users) in Autotask. Returns 25 results per page by default. Use page parameter for more results.
Inputs: page, isActive, pageSize, searchTerm, +1 more.
autotask_search_service_bundlesC
Search for service bundles with optional filters
Inputs: isActive, pageSize, searchTerm.
autotask_search_service_callsB
Search for service calls in Autotask. Filter by company, status, or date range.
Inputs: status, pageSize, companyId, startAfter, +1 more.
autotask_search_service_call_ticket_resourcesB
Search for resource (technician) assignments on service call tickets.
Inputs: pageSize, resourceId, serviceCallTicketId.
autotask_search_service_call_ticketsA
Search for ticket associations on service calls. Use this to find which tickets are linked to a service call, or which service calls contain a specific ticket.
Inputs: pageSize, ticketId, serviceCallId.
autotask_search_servicesC
Search for services with optional filters
Inputs: isActive, pageSize, searchTerm.
autotask_search_tasksA
Search for tasks in Autotask. Returns 25 results per page by default. Use page parameter for more results.
Inputs: page, status, pageSize, projectID, +2 more.
autotask_search_ticket_attachmentsA
Search for attachments on a specific ticket. Each parent triggers a separate query — scope the parent ticket list before iterating.
Inputs: ticketId (required), pageSize.
autotask_search_ticket_chargesA
Search ticket charges (materials, costs, expenses). Provide ticketId for best performance. Max 10 if unfiltered.
Inputs: pageSize, ticketId.
autotask_search_ticket_checklist_itemsA
List all checklist items on a ticket, including their completion status. Checklist items are a sub-resource of a ticket and cannot be queried without a ticket ID.
Inputs: ticketId (required).
autotask_search_ticket_historyA
Get the audit trail of field changes for a ticket (status transitions, assignment changes, priority edits, etc.). Use this to answer questions like "when did this ticket move from In Progress to Waiting Customer" or "who changed the priority". Returns entries ordered by Autotask; sort/filter client-side if needed.
Inputs: ticketId (required), pageSize.
autotask_search_ticket_notesA
Search for notes on a specific ticket. Iterating across many tickets trips Autotask's per-integration API threshold — scope the parent list first.
Inputs: ticketId (required), pageSize.
autotask_search_ticketsB
Search tickets by company, queue, status, priority. Use autotask_get_ticket_details for full data. Max 500/page.
Inputs: page, status, queueID, pageSize, +9 more.
autotask_search_time_entriesA
Search for time entries in Autotask. Returns 25 results per page by default. Time entries can be filtered by resource, ticket, project, task, date range, or approval status. Use approvalStatus="unapproved" to find entries not yet posted. Common fan-out target — scope by date range first to avoid Autotask's API threshold.
Inputs: page, taskId, billable, pageSize, +6 more.
autotask_test_connectionB
Test Autotask API connection
Inputs: no named parameters.
autotask_update_companyA
Update company record. invoiceTemplateID sets payment terms (103=Due on Receipt, 104=NET 30). Billing address fields separate from regular address.
Inputs: id (required), city, phone, state, +28 more.
autotask_update_company_site_configurationA
Update company site configuration. Fields are tenant-defined; call get first.
Inputs: id (required), updates (required).
autotask_update_contactB
Update contact record. Only provided fields are changed.
Inputs: id (required), city, phone, state, +12 more.
autotask_update_contractA
Update an existing Contract in Autotask (PATCH). Pass only fields you want to change; everything except id is optional. status: 1=In Effect, 0=Inactive.
Inputs: id (required), status, endDate, setupFee, +28 more.
autotask_update_contract_serviceA
Update an existing ContractService line on a Contract. Pass only fields you want to change.
Inputs: id (required), contractID (required), unitCost, serviceID, +5 more.
autotask_update_projectA
Update an existing project in Autotask. Only the fields you provide will be updated. Common use case: set status=5 to mark a project Complete.
Inputs: projectId (required), status, description, endDateTime, +8 more.
autotask_update_quote_itemA
Update an existing quote item (quantity, price, etc.)
Inputs: quoteItemId (required), quantity, unitPrice, isOptional, +4 more.
autotask_update_service_callA
Update an existing service call. Use this to change status, times, or description. To complete/close a service call, set complete: true or update the status.
Inputs: serviceCallId (required), status, complete, description, +2 more.
autotask_update_ticketA
Update ticket record. Only provided fields are changed.
Inputs: ticketId (required), title, status, priority, +7 more.
autotask_update_ticket_chargeA
Update an existing ticket charge. Only fields provided will be changed.
Inputs: chargeId (required), name, status, unitCost, +4 more.
autotask_update_ticket_checklist_itemB
Update a checklist item on a ticket — edit text, mark complete/incomplete, or change position.
Inputs: itemId (required), ticketId (required), itemName, position, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 98 tools
Tools are mostly entity-scoped (get_/search_/create_/update_/delete_), but the sheer volume and some near-duplicates (e.g., get_ticket_details vs search_ticket_history, service_call_ticket association vs service_call CRUD) can confuse. The meta tool list_categories is also odd in a flat toolset.
Naming is predominantly consistent with an autotask_<verb>_<entity> pattern. Minor inconsistencies: list_* vs search_* (list_phases, list_categories) and get_ticket_details vs get_ticket_history where 'details' is vague.
98 tools is far beyond the practical limit for MCP usability. Even for a broad PSA platform, the count will overwhelm context windows and decision-making. Several tools are narrowly scoped (e.g., search_service_call_tickets) and could be merged or split more judiciously.
The surface covers many core entities (tickets, companies, projects, service calls, quotes, billing), but significant gaps exist: no update/delete for notes or attachments, no update/delete for tasks or projects, no search/get for service calls (only create/delete/link), and opportunities/products/contracts are read-only.
Maintenance
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
The HubSpot MCP Server acts as a bridge that enables AI assistants and Large Language Models to securely interact with HubSpot CRM data through natural conversation, without requiring users to understand complex API structures. It provides read-only access to standard CRM objects (contacts, companies, deals, tickets, products, invoices, and more) and their associations, secured via OAuth 2.0, allowing AI agents to perform tasks like summarizing deals, fetching company updates, and looking up record changes.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
The Cortex MCP server provides read-only access to real-time engineering context from the Cortex developer portal, allowing AI coding assistants to answer natural language questions about your organization's catalog (microservices, libraries, domains, teams, infrastructure), scorecards (engineering standards and best practices), initiatives (goals and deadlines), and Engineering Intelligence metrics. It includes tools for querying documentation, tracking personal entities, and accessing AI-assisted insights across the entire Cortex ecosystem.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server enabling AI agents to access and manipulate ServiceNow data through natural language interactions, allowing users to search for records, update them, and manage scripts.47MIT
- FlicenseNot gradedqualityCmaintenanceA Model Context Protocol server that provides a comprehensive interface for interacting with the ConnectWise Manage API, simplifying API discovery, execution, and management for both developers and AI assistants.7 npm19-
- AlicenseBqualityDmaintenanceA Model Context Protocol server providing AI assistants with comprehensive project, task, and subtask management capabilities with project-specific storage.2944 npm88MIT
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that enables AI assistants and development tools to interact with ServiceNow instances, providing comprehensive API coverage for incident management, change management, CMDB, and other ServiceNow modules.3MIT