Autotask MCP Server (TICnine/autotask-mcp) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 90 tools. No publisher has claimed this listing.

C
Caution
74/100

Autotask MCP Server

Provides AI assistants with direct access to Autotask PSA for MSP operations. Enables natural language interaction for ticket management, time logging, company lookups, project tracking, and billing review through 39 comprehensive tools.

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

TICnine

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
⚠️
Known vulnerabilities in dependencies: 1 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 3 credentials: AUTOTASK_SECRET, X_API_KEY, X_API_SECRET
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes90 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

autotask_test_connection

Test the connection to Autotask API

autotask_search_companies

Search for companies in Autotask. Returns 25 results per page by default. Use page parameter for more results.

autotask_create_company

Create a new company in Autotask

autotask_update_company

Update an existing company in Autotask

autotask_get_company_site_configuration

Get the site configuration record(s) for a company in Autotask. Site configurations contain tenant-defined fields used to track per-company configuration data. Call this first to discover which fields are available before calling autotask_update_company_site_configuration.

autotask_update_company_site_configuration

Update fields on a company site configuration record. The set of available fields is tenant-defined, so callers should first call autotask_get_company_site_configuration to discover the available field names and current values for the company. Pass the site configuration record id (not the company i

autotask_search_contacts

Search for contacts in Autotask. Returns 25 results per page by default. Use page parameter for more results.

autotask_create_contact

Create a new contact in Autotask

autotask_search_tickets

Search for tickets in Autotask. Returns 25 results per page by default. Use page parameter for more results. Use get_ticket_details for full data on a specific ticket.

autotask_get_ticket_details

Get detailed information for a specific ticket by ID. Use this for full ticket data when needed.

autotask_create_ticket

Create a new ticket in Autotask

autotask_update_ticket

Update fields on an existing Autotask ticket. Only supply the fields you want to change.

autotask_get_ticket_charge

Get a specific ticket charge by ID

autotask_search_ticket_charges

Search for charges on a specific ticket. Charges represent materials, costs, or expenses billed against a ticket. Providing ticketId is strongly recommended — unfiltered queries are expensive and capped at 10 results.

autotask_create_ticket_charge

Create a charge (material, cost, or expense) on a ticket. Used to bill clients for parts, travel, or other non-labor costs.

autotask_update_ticket_charge

Update an existing ticket charge. Only fields provided will be changed.

autotask_delete_ticket_charge

Delete a ticket charge by ID. Requires both the parent ticket ID and charge ID.

autotask_create_time_entry

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.

autotask_search_projects

Search for projects in Autotask. Returns 25 results per page by default. Use page parameter for more results.

autotask_create_project

Create a new project in Autotask

autotask_update_project

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.

autotask_search_resources

Search for resources (users) in Autotask. Returns 25 results per page by default. Use page parameter for more results.

autotask_get_ticket_note

Get a specific ticket note by ticket ID and note ID

autotask_search_ticket_notes

Search for notes on a specific ticket

autotask_create_ticket_note

Create a new note for a ticket

autotask_search_ticket_checklist_items

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.

autotask_create_ticket_checklist_item

Add a new checklist item to a ticket.

autotask_update_ticket_checklist_item

Update a checklist item on a ticket — edit text, mark complete/incomplete, or change position.

autotask_delete_ticket_checklist_item

Delete a checklist item from a ticket.

autotask_get_project_note

Get a specific project note by project ID and note ID

autotask_search_project_notes

Search for notes on a specific project

autotask_create_project_note

Create a new note for a project

autotask_get_company_note

Get a specific company note by company ID and note ID

autotask_search_company_notes

Search for notes on a specific company

autotask_create_company_note

Create a new note for a company

autotask_get_ticket_attachment

Get a specific ticket attachment by ticket ID and attachment ID

autotask_search_ticket_attachments

Search for attachments on a specific ticket

autotask_create_ticket_attachment

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

autotask_get_expense_report

Get a specific expense report by ID

autotask_search_expense_reports

Search for expense reports with optional filters

autotask_create_expense_report

Create a new expense report

autotask_create_expense_item

Create an expense item on an existing expense report

autotask_get_quote

Get a specific quote by ID

autotask_search_quotes

Search for quotes with optional filters

autotask_create_quote

Create a new quote

autotask_get_opportunity

Get a specific opportunity by ID

autotask_search_opportunities

Search for opportunities with optional filters

autotask_create_opportunity

Create a new sales opportunity in Autotask

autotask_get_product

Get a specific product by ID

autotask_search_products

Search for products with optional filters

autotask_get_service

Get a specific service by ID

autotask_search_services

Search for services with optional filters

autotask_get_service_bundle

Get a specific service bundle by ID

autotask_search_service_bundles

Search for service bundles with optional filters

autotask_get_quote_item

Get a specific quote item by ID

autotask_search_quote_items

Search for quote items, typically filtered by quote ID

autotask_create_quote_item

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.

autotask_update_quote_item

Update an existing quote item (quantity, price, etc.)

autotask_delete_quote_item

Delete a quote item (line item) from a quote

autotask_search_configuration_items

Search for configuration items in Autotask with optional filters

autotask_search_contracts

Search for contracts in Autotask with optional filters

autotask_search_invoices

Search for invoices in Autotask with optional filters

autotask_get_invoice_details

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.

autotask_search_tasks

Search for tasks in Autotask. Returns 25 results per page by default. Use page parameter for more results.

autotask_create_task

Create a new task in Autotask

autotask_list_phases

List phases for a project in Autotask

autotask_create_phase

Create a new phase in an Autotask project

autotask_list_queues

List all available ticket queues in Autotask. Use this to find queue IDs for filtering tickets by queue.

autotask_list_ticket_statuses

List all available ticket statuses in Autotask. Use this to find status values for filtering or creating tickets.

autotask_list_ticket_priorities

List all available ticket priorities in Autotask. Use this to find priority values for filtering or creating tickets.

autotask_get_field_info

Get field definitions for an Autotask entity type, including picklist values. Useful for discovering valid values for any picklist field.

autotask_search_billing_items

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.

autotask_get_billing_item

Get detailed information for a specific billing item by ID

autotask_search_billing_item_approval_levels

Search for billing item approval levels. These describe multi-level approval records for Autotask time entries, enabling visibility into tiered approval workflows.

autotask_search_time_entries

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.

autotask_search_service_calls

Search for service calls in Autotask. Returns 25 results per page by default. Use page parameter for more results.

autotask_get_service_call

Get detailed information for a specific service call by ID.

autotask_create_service_call

Create a new service call in Autotask

autotask_update_service_call

Update an existing service call in Autotask

autotask_delete_service_call

Delete a service call from Autotask

autotask_search_service_call_tickets

Search for ticket associations on service calls. Use to find which tickets are linked to a service call.

autotask_create_service_call_ticket

Link a ticket to a service call

autotask_delete_service_call_ticket

Unlink a ticket from a service call

autotask_search_service_call_ticket_resources

Search for resource assignments on service call tickets. Use to find which technicians are assigned to a service call.

autotask_create_service_call_ticket_resource

Assign a resource (technician) to a service call ticket

autotask_delete_service_call_ticket_resource

Unassign a resource (technician) from a service call ticket

autotask_list_categories

List available tool categories. Use this to discover what types of Autotask operations are available before loading specific tools.

autotask_list_category_tools

List tools in a specific category with full schemas. Use after autotask_list_categories to see available tools and their parameters.

autotask_execute_tool

Execute any Autotask tool by name. Use after discovering tools via autotask_list_category_tools.

autotask_router

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.

// known CVEs in dependencies1 high

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

high@modelcontextprotocol/sdk@1.25.3GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configAUTH_MODEe =gateway \
configAUTOTASK_API_URLis auto-detected from AUTOTASK_USERNAME via Autotask's
configAUTOTASK_INTEGRATION_CODEe =your-code \
🔐 secretAUTOTASK_SECRETe =your-secret \
configAUTOTASK_USERNAMEe =your-user@company.com \
configLAZY_LOADING
configLOG_FORMATsimple # simple, json
configLOG_LEVELinfo # error, warn, info, debug
configMCP_HTTP_HOST0.0.0.0 # HTTP transport bind address
configMCP_HTTP_PORT8080 # HTTP transport port (only used when MCP_TRANSPORT=http)
configMCP_SERVER_NAMEautotask-mcp
configMCP_SERVER_VERSION
configMCP_TRANSPORT"-e", "=stdio",
🔐 secretX_API_KEY
🔐 secretX_API_SECRET
configX_API_URL
configX_INTEGRATION_CODE
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

90/90 tools missing one or more hints — autotask_test_connection (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); autotask_search_companies (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); autotask_create_company (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +87 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool test coverage

Only 8/90 tools referenced in tests (9%)

Write tests that reference each tool by name so every tool has at least one test.

Production dependencies are patched

0 critical, 1 high severity in production deps — @modelcontextprotocol/sdk@1.25.3 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/ticnine/autotask-mcp?variant=verified)](https://m8ven.ai/mcp/ticnine/autotask-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 4c5d21b50e01f3781c6a71b579c22bc8fcd29c7e
code hash: 5e81d5d39a82ba6209968c5e078768828e1f9c3943c3de9ad0f6a39c29c74731
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client