mark_message

Mark an inbox item read or unread (read defaults true). Requires handle + secret.

SERVERGateway SOURCEhttps://wingmanprotocol.com/mcp

Medium RISK CLASS

Category Write

Parameters 42 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/com-wingmanprotocol-agent-gateway/mark-message.md

WHAT IT DOES

What mark_message does on Gateway

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

Parameter	Type	Required
`read`	boolean	—
`handle`	string	Yes
`secret`	string	—
`item_id`	string	Yes

Parameters from the server's own tool schema.

RISK

Why mark_message is rated Medium

Marking messages read/unread is a classic Write operation—it modifies inbox state but is fully reversible. The blast radius is minimal: an agent marking the wrong messages as read causes a minor UX inconvenience but no data loss, financial impact, or system compromise. Low severity reflects the narrow scope and reversibility.

From the tool's definition Tool explicitly performs a state change: 'Mark an inbox item read or unread'. This is a reversible modification of data (toggling a read/unread flag), not a destructive deletion, data retrieval, or external execution.

Risk signalsHandles credentials or secrets (secret)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs mark_message safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Gateway, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For mark_message, this is the rule to start with:

mark_message Rate-limited

mark_message 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": {
    "mark_message": {
      "limits": [
        {
          "counter": "mark_message_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Gateway, apply this rule, and every mark_message call is checked against it from then on.

FAQ

Questions about mark_message

What does the mark_message tool do? +

Mark an inbox item read or unread (read defaults true). Requires handle + secret. It is categorised as a Write tool in the Gateway MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does mark_message accept? +

mark_message accepts 4 parameters: read, handle, secret, item_id. Required: handle, item_id. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on mark_message? +

Register the Gateway MCP server in PolicyLayer and add a rule for mark_message: 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 Gateway. Nothing to install.

What risk level is mark_message? +

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

Can I rate-limit mark_message? +

Yes. Add a rate_limit block to the mark_message 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 mark_message completely? +

Set action: deny in the PolicyLayer policy for mark_message. 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 mark_message? +

mark_message is provided by the Gateway MCP server (https://wingmanprotocol.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Gateway, and thousands of servers like it.

This server

All 271 Gateway tools →

Across the catalogue

sms_mark_read on Twilio SMS MCP Server →mark-as-read on Meme MCP Server → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →