Read Upwork messages. Without room_id: lists conversations. With room_id: reads full message history.
AI agents call get_messages to retrieve information from Upwork without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing message data without creating, modifying, deleting, or executing any operations. It is purely informational. Severity is low because while message content may contain sensitive information, reading existing messages is a standard, non-destructive operation with no capacity for financial impact or system alteration.
From the tool's definition Tool name 'get_messages' and description 'Read Upwork messages' explicitly states retrieval functionality. Listing conversations and reading message history are query operations with no side effects.
Documented attack patterns abuse exactly the kind of access get_messages gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Upwork, and nothing reaches the server without passing your rules. This is the rule we recommend for get_messages:
{
"version": "1",
"default": "deny",
"tools": {
"get_messages": {}
}
}get_messages is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Read Upwork messages. Without room_id: lists conversations. With room_id: reads full message history. It is categorised as a Read tool in the Upwork MCP Server, which means it retrieves data without modifying state.
Register the Upwork MCP server in PolicyLayer and add a rule for get_messages: 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 Upwork. Nothing to install.
get_messages is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_messages 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 get_messages. 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.
get_messages is provided by the Upwork MCP server (zcrossoverz/upwork-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Upwork, 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.
11 Upwork tools catalogued and risk-classified — across an index of 43,000+ MCP servers.