messages.mark_read · MCP Fullstack MCP: Risk & Policy

WHAT IT DOES

What messages.mark_read does on MCP Fullstack

AI agents use messages.mark_read to create or update resources in MCP Fullstack — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Fullstack environment.

WHY IT NEEDS A POLICY

Why messages.mark_read needs a policy

Marking a message as read modifies the read/unread state of a message. This is a reversible write operation (it could be marked unread again). It does not delete, execute code, or involve financial transactions. Blast radius is very low as misuse would only affect message read status.

From the tool's definition Mark a message as read

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

messages.mark_read Rate-limited

messages.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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "messages.mark_read": {
      "limits": [
        {
          "counter": "messages.mark_read_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCP Fullstack, so you can run agents against it safely.

FAQ

Questions about messages.mark_read

What does the messages.mark_read tool do? +

Mark a message as read. It is categorised as a Write tool in the MCP Fullstack MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on messages.mark_read? +

Register the MCP Fullstack MCP server in PolicyLayer and add a rule for messages.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 MCP Fullstack. Nothing to install.

What risk level is messages.mark_read? +

messages.mark_read is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit messages.mark_read? +

Yes. Add a rate_limit block to the messages.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.

How do I block messages.mark_read completely? +

Set action: deny in the PolicyLayer policy for messages.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.

What MCP server provides messages.mark_read? +

messages.mark_read is provided by the MCP Fullstack MCP server (jacobfv/mcp-fullstack). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.