Poll Burp Collaborator for received interactions.
AI agents call collaborator_check to retrieve information from Burp Mcp Plus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the state of Burp Collaborator to check for incoming network interactions (DNS, HTTP callbacks, etc.). It performs data retrieval only and has no capacity to modify, delete, or execute actions. The polling operation is a standard read pattern used in security testing workflows to passively observe whether target systems have made outbound connections. No side effects occur from calling this tool.
From the tool's definition Tool description states 'Poll Burp Collaborator for received interactions' - polling is a read operation that retrieves data without modification or side effects.
Documented attack patterns abuse exactly the kind of access collaborator_check gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Burp Mcp Plus, and nothing reaches the server without passing your rules. This is the rule we recommend for collaborator_check:
{
"version": "1",
"default": "deny",
"tools": {
"collaborator_check": {}
}
}collaborator_check is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Poll Burp Collaborator for received interactions. It is categorised as a Read tool in the Burp Mcp Plus MCP Server, which means it retrieves data without modifying state.
Register the Burp Mcp Plus MCP server in PolicyLayer and add a rule for collaborator_check: 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 Burp Mcp Plus. Nothing to install.
collaborator_check is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the collaborator_check 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 collaborator_check. 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.
collaborator_check is provided by the Burp Mcp Plus MCP server (titaniumtushar/burp-mcp-plus). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Burp Mcp Plus, 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.
20 Burp Mcp Plus tools catalogued and risk-classified — across an index of 43,000+ MCP servers.