Create a testing task with full access to original work
AI agents use create_testing_task to create or update resources in Agent MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agent MCP environment.
The tool primarily creates a new testing task (Write), which is a reversible data creation action. The phrase 'full access to original work' raises the severity slightly as it implies the created task may have wide-ranging read or modification privileges, but the core action is task creation. No evidence of code execution, deletion, or financial operations.
From the tool's definition "Create a testing task" — creates a new task entity; "with full access to original work" suggests broad read permissions on existing artifacts
Documented attack patterns abuse exactly the kind of access create_testing_task gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Agent MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for create_testing_task:
{
"version": "1",
"default": "deny",
"tools": {
"create_testing_task": {
"limits": [
{
"counter": "create_testing_task_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_testing_task stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Create a testing task with full access to original work. It is categorised as a Write tool in the Agent MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Agent MCP server in PolicyLayer and add a rule for create_testing_task: 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 Agent MCP. Nothing to install.
create_testing_task is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_testing_task 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.
Set action: deny in the PolicyLayer policy for create_testing_task. 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.
create_testing_task is provided by the Agent MCP server (rinadelph/agent-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 Agent MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
6 Agent MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.