Submit a proposal for an Upwork job. Call get_job_details first to get screening questions.
AI agents use submit_proposal to create or update resources in Upwork — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Upwork environment.
Submitting a proposal creates a new binding communication artifact on Upwork that establishes the freelancer's application for a job contract. While reversible (proposals can typically be withdrawn), this is a Write action because it generates new data records.
From the tool's definition Tool description states 'Submit a proposal for an Upwork job' — this creates a new proposal record on the Upwork platform, a reversible action that modifies data (adds a proposal to the job posting).
Documented attack patterns abuse exactly the kind of access submit_proposal 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 submit_proposal:
{
"version": "1",
"default": "deny",
"tools": {
"submit_proposal": {
"limits": [
{
"counter": "submit_proposal_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}submit_proposal 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.
Submit a proposal for an Upwork job. Call get_job_details first to get screening questions. It is categorised as a Write tool in the Upwork MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Upwork MCP server in PolicyLayer and add a rule for submit_proposal: 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.
submit_proposal 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 submit_proposal 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 submit_proposal. 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.
submit_proposal 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.