Retrieve client information from the Velociraptor server. Args: hostname: Hostname or FQDN of the target endpoint. org_id: Optional Velociraptor org ID for multi-tenant deployments. search_all_orgs: Search across orgs when no org_id is supplied. Returns: A dictionary containing client metadata, i...
AI agents call client_info to retrieve information from Velociraptor MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a lookup/query operation that retrieves existing forensic client information from the Velociraptor server. It has no destructive, financial, or code-execution implications. While it could enable reconnaissance on a compromised LLM, the tool itself only reads and returns metadata with no side effects.
From the tool's definition Tool retrieves client metadata including client_id, hostname, and org information without modifying any data.
Documented attack patterns abuse exactly the kind of access client_info gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Velociraptor MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for client_info:
{
"version": "1",
"default": "deny",
"tools": {
"client_info": {}
}
}client_info 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.
Retrieve client information from the Velociraptor server. Args: hostname: Hostname or FQDN of the target endpoint. org_id: Optional Velociraptor org ID for multi-tenant deployments. search_all_orgs: Search across orgs when no org_id is supplied. Returns: A dictionary containing client metadata, including the client_id, which can be used to target other artifact collections. When search_all_orgs is true, the response may also include OrgId/OrgName. It is categorised as a Read tool in the Velociraptor MCP MCP Server, which means it retrieves data without modifying state.
Register the Velociraptor MCP server in PolicyLayer and add a rule for client_info: 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 Velociraptor MCP. Nothing to install.
client_info 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 client_info 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 client_info. 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.
client_info is provided by the Velociraptor MCP server (mgreen27/mcp-velociraptor). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Velociraptor MCP, 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.
28 Velociraptor MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.