// MCP TOOL REFERENCE

autotask_raw_request

ServerAutotask
CategoryExecute

WHAT IT DOES

What autotask_raw_request does on Autotask

AI agents invoke autotask_raw_request to trigger actions in Autotask. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

THE RISK

High Risk

Why autotask_raw_request needs a policy

This tool allows arbitrary HTTP requests to any Autotask REST endpoint, meaning it can perform reads, writes, deletes, financial operations, or any other action depending on the arguments passed. It is a generic execution escape hatch with no restrictions on method or endpoint, giving it the maximum blast radius across all categories.

From the tool's definition Escape hatch for Autotask REST endpoints not yet wrapped by a typed tool... The path is resolved against the zone-resolved base URL

Documented attack patterns abuse exactly the kind of access autotask_raw_request gives an agent:

POLICY

How to control autotask_raw_request

PolicyLayer is an MCP gateway — it sits between your AI agents and Autotask, and nothing reaches the server without passing your rules. This is the rule we recommend for autotask_raw_request:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "autotask_raw_request": {
      "limits": [
        {
          "counter": "autotask_raw_request_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

autotask_raw_request stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Autotask — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Autotask tools

Financial autotask_create_ticket_charge Create charge on ticket for materials, costs, or expenses. Execute autotask_execute_tool Execute any Autotask tool by name. Use after discovering tools via autotask_list_category_ Write autotask_update_ticket_charge Update an existing ticket charge. Only fields provided will be changed. Write autotask_create_company Create new company record Write autotask_create_company_note Create a new note for a company Write autotask_create_contact Create new contact record Write autotask_create_contract Create a new Contract in Autotask. Field names match the Autotask REST API exactly. status Write autotask_create_contract_service Add a ContractService (service line item) to an existing Contract.

All 91 Autotask tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Autotask → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about autotask_raw_request

What does the autotask_raw_request tool do? +

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<N>.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. It is categorised as a Execute tool in the Autotask MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on autotask_raw_request? +

Register the Autotask MCP server in PolicyLayer and add a rule for autotask_raw_request: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Autotask. Nothing to install.

What risk level is autotask_raw_request? +

autotask_raw_request is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit autotask_raw_request? +

Yes. Add a rate_limit block to the autotask_raw_request rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block autotask_raw_request completely? +

Set action: deny in the PolicyLayer policy for autotask_raw_request. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides autotask_raw_request? +

autotask_raw_request is provided by the Autotask MCP server (wyre-technology/autotask-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Autotask tool call.

Start from Autotask, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

91 Autotask tools catalogued and risk-classified — across an index of 43,000+ MCP servers.