Loads a .pnt into the open viewer and returns a summary read from clashes.json.
AI agents call viewer_load_package to retrieve information from PyNet Bridge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read operation: it opens a package file in a viewer and queries data from clashes.json to return a summary. There is no modification, deletion, execution of arbitrary code, or side effects described. The action is informational and reversible (loading a file for viewing does not alter the file or system state).
From the tool's definition Tool description states it 'Loads a .pnt into the open viewer and returns a summary read from clashes.json.' The key verbs are 'Loads' and 'returns a summary read from' — the tool retrieves and displays data from a file without modifying it.
Attacks that exploit this kind of access
Loads a .pnt into the open viewer and returns a summary read from clashes.json. It is categorised as a Read tool in the PyNet Bridge MCP Server, which means it retrieves data without modifying state.
Register the PyNet Bridge MCP server in PolicyLayer and add a rule for viewer_load_package: 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 PyNet Bridge. Nothing to install.
viewer_load_package 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 viewer_load_package 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 viewer_load_package. 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.
viewer_load_package is provided by the PyNet Bridge MCP server (rafael-nunezdearenas/pynetbridge). 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 →