Get the correct namespace for a Filament class
AI agents call filament_get_namespace to retrieve information from Filament MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries namespace information, analogous to a lookup or fetch operation. It has no capacity to create, modify, delete, execute arbitrary code, or affect external systems. The worst-case misuse would be retrieving incorrect namespace information, which is informational only and carries no blast radius beyond potentially misleading documentation lookups.
From the tool's definition Tool name and description indicate it 'Get[s] the correct namespace for a Filament class' — a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get the correct namespace for a Filament class. It is categorised as a Read tool in the Filament MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Filament MCP Server MCP server in PolicyLayer and add a rule for filament_get_namespace: 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 Filament MCP Server. Nothing to install.
filament_get_namespace 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 filament_get_namespace 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 filament_get_namespace. 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.
filament_get_namespace is provided by the Filament MCP Server MCP server (serbansorin/filament-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →