AI agents use sendChatMessage to create or update resources in Maige 3d — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Maige 3d environment.
This tool creates new chat message data that appears in the 3D scene's UI overlay. It modifies the chat state by adding a message, but this is fully reversible (messages can be cleared or replaced). It has no destructive effects, does not execute code or commands, and does not affect the 3D scene objects themselves. The blast radius of misuse is minimal—unwanted chat messages are annoying but inconsequential.
From the tool's definition The tool 'sendChatMessage' displays a message in an in-world chat overlay. The description indicates it creates/adds a message to a chat system ('Display a message'), which is a reversible write operation.
Attacks that exploit this kind of access
Display a message in the in-world chat overlay visible to the user inside the 3D view. It is categorised as a Write tool in the Maige 3d MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Maige 3d MCP server in PolicyLayer and add a rule for sendChatMessage: 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 Maige 3d. Nothing to install.
sendChatMessage 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 sendChatMessage 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 sendChatMessage. 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.
sendChatMessage is provided by the Maige 3d MCP server (m-ai-gexr/mcp-webgpu). 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 →