This record as markdown: /tools/ruflo/post-browse.md
What post-browse does on Ruflo
AI agents use post-browse to create or update resources in Ruflo, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ruflo environment.
Why post-browse is rated Medium
This tool creates or modifies records of browser automation outcomes, which is a reversible write operation. It doesn't execute browser commands itself (that would be Execute), doesn't delete data (Destructive), and doesn't move money (Financial). The 'learning' system context suggests it stores telemetry or feedback data.
From the tool's definition Tool name 'post-browse' and description 'Record browser automation outcome for learning' indicates the tool writes/persists data about browser automation results to a learning system or database.
Attacks that exploit this kind of access
The rule that runs post-browse safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Ruflo, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For post-browse, this is the rule to start with:
post-browse stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Ruflo, apply this rule, and every post-browse call is checked against it from then on.
Questions about post-browse
Record browser automation outcome for learning. It is categorised as a Write tool in the Ruflo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ruflo MCP server in PolicyLayer and add a rule for post-browse: 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 Ruflo. Nothing to install.
post-browse 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 post-browse 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 post-browse. 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.
post-browse is provided by the Ruflo MCP server (ruvnet/ruflo). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Ruflo, and thousands of servers like it.
This server
Across the catalogue