AI agents use create_engagement to create or update resources in DefectDojo MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your DefectDojo MCP Server environment.
The tool creates a new engagement record, which is a reversible write operation. While it adds data to the vulnerability management system, it does not execute arbitrary code, delete data, or move money. The severity is medium because creating an engagement could trigger workflow processes or notifications in the vulnerability management pipeline, but the core operation is data creation.
From the tool's definition Tool name is 'create_engagement' and description states 'Create a new engagement'. This creates a new record in DefectDojo's engagement system.
Documented attack patterns abuse exactly the kind of access create_engagement gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and DefectDojo MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for create_engagement:
{
"version": "1",
"default": "deny",
"tools": {
"create_engagement": {
"limits": [
{
"counter": "create_engagement_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_engagement 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 new engagement. It is categorised as a Write tool in the DefectDojo MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the DefectDojo MCP Server MCP server in PolicyLayer and add a rule for create_engagement: 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 DefectDojo MCP Server. Nothing to install.
create_engagement 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_engagement 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_engagement. 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_engagement is provided by the DefectDojo MCP Server MCP server (jamiesonio/defectdojo-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from DefectDojo MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
11 DefectDojo MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.