AI agents use publish_reader_bundle to create or update resources in Pdf Card — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pdf Card environment.
The 'publish' action most likely creates or distributes a bundle (Write category), potentially with side effects like uploading to a server or creating persistent outputs. Without a description, confidence is reduced and severity is assessed as medium since the blast radius depends on where/how widely the bundle is published and whether it's reversible.
From the tool's definition Tool name 'publish_reader_bundle' combined with server context of card-based HTML readers suggests creating or deploying bundled reader output.
Attacks that exploit this kind of access
publish_reader_bundle. It is categorised as a Write tool in the Pdf Card MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pdf Card MCP server in PolicyLayer and add a rule for publish_reader_bundle: 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 Pdf Card. Nothing to install.
publish_reader_bundle 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 publish_reader_bundle 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 publish_reader_bundle. 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.
publish_reader_bundle is provided by the Pdf Card MCP server (velyan/pdf-card-mcp). 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 →