Mark one or more messages in a chat as read
AI agents use mark_message_as_read to create or update resources in Mcp Ap2 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Ap2 environment.
This tool modifies data (message read status) in a reversible manner. It does not retrieve data without side effects (Read), execute arbitrary code (Execute), delete/destroy data (Destructive), or move money (Financial). The severity is low because marking messages as read has minimal blast radius—the operation is non-destructive and easily reversible (messages can be marked unread or the status reset).
From the tool's definition The tool 'mark_message_as_read' performs an action that modifies state—specifically, updating the read status of messages. The description states it 'Mark[s] one or more messages in a chat as read,' which is a state-changing operation.
Documented attack patterns abuse exactly the kind of access mark_message_as_read gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Ap2, and nothing reaches the server without passing your rules. This is the rule we recommend for mark_message_as_read:
{
"version": "1",
"default": "deny",
"tools": {
"mark_message_as_read": {
"limits": [
{
"counter": "mark_message_as_read_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}mark_message_as_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.
Free to start. No card required.
Mark one or more messages in a chat as read. It is categorised as a Write tool in the Mcp Ap2 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Ap2 MCP server in PolicyLayer and add a rule for mark_message_as_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 Mcp Ap2. Nothing to install.
mark_message_as_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 mark_message_as_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 mark_message_as_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.
mark_message_as_read is provided by the Mcp Ap2 MCP server (@codespar/mcp-ap2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Ap2, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
1300 Mcp Ap2 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.