AI agents use upwork_send_message to create or update resources in Upwork MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Upwork MCP Server environment.
Sending messages on Upwork creates new data (message records) and modifies conversation state. While reversible (messages can typically be deleted), this tool could be misused to send unsolicited messages, spam, or misleading communications to clients/freelancers at scale, causing reputational and trust damage.
From the tool's definition Tool name 'upwork_send_message' indicates it sends/creates messages on the Upwork platform. Server description confirms it 'manages messages' and uses 'browser automation.' The empty description limits specificity, but the action is clearly message creation,…
Documented attack patterns abuse exactly the kind of access upwork_send_message gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Upwork MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for upwork_send_message:
{
"version": "1",
"default": "deny",
"tools": {
"upwork_send_message": {
"limits": [
{
"counter": "upwork_send_message_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}upwork_send_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.
Free to start. No card required.
upwork_send_message. It is categorised as a Write tool in the Upwork MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Upwork MCP Server MCP server in PolicyLayer and add a rule for upwork_send_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 Upwork MCP Server. Nothing to install.
upwork_send_message 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 upwork_send_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.
Set action: deny in the PolicyLayer policy for upwork_send_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.
upwork_send_message is provided by the Upwork MCP Server MCP server (vanooo/upwork-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 18 Upwork MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
18 Upwork MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.