draft_proposal

Draft a customized Upwork proposal based on a job description. Picks the best template (MCP/AI Agent/Discord/General) and writes a custom opening referencing the specific job.

SERVERJobs SOURCE0xcybin/jobs-mcp

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade A, identity unverified Pull the record →

WHAT IT DOES

What draft_proposal does on Jobs

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

RISK

Why draft_proposal is rated Medium

This tool generates/creates a proposal document (a write operation), but it appears to only draft content locally without submitting or sending it anywhere. The output is a tailored text proposal. No irreversible actions, financial transactions, or code execution are involved. Severity is low since misuse would at most produce an inappropriate draft proposal.

From the tool's definition Draft a customized Upwork proposal based on a job description. Picks the best template and writes a custom opening referencing the specific job.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs draft_proposal safely

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

draft_proposal Rate-limited

draft_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "draft_proposal": {
      "limits": [
        {
          "counter": "draft_proposal_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 Jobs, apply this rule, and every draft_proposal call is checked against it from then on.

FAQ

Questions about draft_proposal

What does the draft_proposal tool do? +

Draft a customized Upwork proposal based on a job description. Picks the best template (MCP/AI Agent/Discord/General) and writes a custom opening referencing the specific job. It is categorised as a Write tool in the Jobs MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on draft_proposal? +

Register the Jobs MCP server in PolicyLayer and add a rule for draft_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 Jobs. Nothing to install.

What risk level is draft_proposal? +

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

Can I rate-limit draft_proposal? +

Yes. Add a rate_limit block to the draft_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.

How do I block draft_proposal completely? +

Set action: deny in the PolicyLayer policy for draft_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.

What MCP server provides draft_proposal? +

draft_proposal is provided by the Jobs MCP server (0xcybin/jobs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Jobs, and thousands of servers like it.

This server

All 8 Jobs tools →

Across the catalogue

create-draft on Meme MCP Server →mail_create_draft on Apple Apps MCP → The MCP Attack Database →

Guides

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