This record as markdown: /tools/delltrak-wamcp/wa-mark-read.md
What wa_mark_read does on WA MCP
AI agents use wa_mark_read to create or update resources in WA MCP, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your WA MCP environment.
Why wa_mark_read is rated Medium
Marking messages as read modifies chat metadata and message state, which is a write operation. While reversible (messages can be marked unread), it changes data state and could be misused to hide evidence of message reading or manipulate communication records.
From the tool's definition Tool name 'wa_mark_read' and description 'Mark specific messages as read in a chat' indicate modification of message state/metadata. This is a reversible write operation that changes the read status of messages.
Attacks that exploit this kind of access
The rule that runs wa_mark_read safely
PolicyLayer is an MCP gateway: it sits between your AI agents and WA MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For wa_mark_read, this is the rule to start with:
wa_mark_read 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 WA MCP, apply this rule, and every wa_mark_read call is checked against it from then on.
Questions about wa_mark_read
Mark specific messages as read in a chat. It is categorised as a Write tool in the WA MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the WA MCP server in PolicyLayer and add a rule for wa_mark_read: 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 WA MCP. Nothing to install.
wa_mark_read 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 wa_mark_read 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 wa_mark_read. 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.
wa_mark_read is provided by the WA MCP server (delltrak/wamcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on WA, and thousands of servers like it.
This server
Across the catalogue