Pull or clone the community adapter repository
AI agents use site_update to create or update resources in Ma Browser — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ma Browser environment.
Pulling or cloning repositories creates or modifies data (local repository state) in a reversible manner. While the browser server context suggests potential for arbitrary website access, the specific tool description indicates version control operations on a repository.
From the tool's definition Tool description states 'Pull or clone the community adapter repository' — operations that create local copies or update repositories.
Attacks that exploit this kind of access
Pull or clone the community adapter repository. It is categorised as a Write tool in the Ma Browser MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ma Browser MCP server in PolicyLayer and add a rule for site_update: 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 Ma Browser. Nothing to install.
site_update 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 site_update 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 site_update. 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.
site_update is provided by the Ma Browser MCP server (zzhan111/multi-agents-browser). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
site_update is one line of Ma Browser's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →