ChatGPT Prompt to Find and Shortlist Freelancers via Upwork's MCP Server

0 views Updated Oct 7, 2026

This is a prompt for clients using Upwork's MCP server, which connects the Upwork marketplace directly to ChatGPT, Claude, Cursor, and any other MCP-compatible AI tool. Instead of searching and filtering freelancers manually on the Upwork website, you describe the role you need filled in plain language, and the connected AI pulls real freelancer profiles, summarizes their fit, and drafts outreach — all without leaving your chat.

The prompt works by giving the model a structured brief (the job, the must-have skills, the budget range, the deal-breakers) so it searches with real constraints instead of returning a generic list. It also has the model explain why each candidate was shortlisted, which makes the results easy to sanity-check before you commit to anything — Upwork's MCP server previews any action that changes something (like sending an offer) and requires your explicit confirmation first.

This is useful any time you're hiring through Upwork and want the AI assistant you already work in to do the first pass of candidate sourcing, rather than switching tabs and filtering manually.

Prompt template

prompt-template

182 tokens

I'm hiring on Upwork through your MCP connection. Here's the role: Role: [JOB TITLE] Must-have skills: [SKILL 1, SKILL 2, SKILL 3] Nice-to-have skills: [OPTIONAL SKILLS] Budget range: [HOURLY OR FIXED RANGE] Timezone / availability needs: [OVERLAP REQUIRED, IF ANY] Deal-breakers: [ANYTHING THAT SHOULD AUTOMATICALLY RULE SOMEONE OUT] Using the Upwork MCP connection: 1. Search for freelancers matching this brief. 2. Return a shortlist of 3-5 candidates. 3. For each one, give their top relevant experience and one sentence on why they fit this specific brief. 4. Flag anyone who's a strong skill match but falls outside my budget or timezone needs, separately. 5. Do not send any messages or offers yet — just show me the shortlist first.

Want it sharper? Optimize this prompt with Prompt Optimizer, check it with the Prompt Debugger or shorten it with the Token Optimizer.

Example input

example-input

177 tokens

I'm hiring on Upwork through your MCP connection. Here's the role: Role: Shopify developer for a custom checkout flow Must-have skills: Shopify Liquid, Shopify Admin API, 3+ years e-commerce development Nice-to-have skills: experience with subscription apps Budget range: $40-65/hr Timezone / availability needs: at least 4 hours overlap with US Eastern time Deal-breakers: no agencies, individual freelancers only Using the Upwork MCP connection: 1. Search for freelancers matching this brief. 2. Return a shortlist of 3-5 candidates. 3. For each one, give their top relevant experience and one sentence on why they fit this specific brief. 4. Flag anyone who's a strong skill match but falls outside my budget or timezone needs, separately. 5. Do not send any messages or offers yet — just show me the shortlist first.

Example output

example-output

251 tokens

Here's a shortlist of 4 freelancers matching your brief:

Freelancer A — 6 years building custom Shopify checkouts, including 2 subscription-app integrations. Based in Toronto (full US Eastern overlap). Rate: $55/hr. Strong fit: direct experience with the exact subscription-app requirement you listed as a nice-to-have.
Freelancer B — 4 years Shopify Liquid + Admin API, no subscription-app experience but strong checkout customization portfolio. Based in UK (2 hours overlap with US Eastern). Rate: $48/hr. Fits on skills and budget but falls short on your timezone requirement.
Freelancer C — 3.5 years e-commerce development, Shopify Plus specialist. Based in Philippines (minimal US Eastern overlap). Rate: $42/hr. Flagging separately: strong skill match but outside your timezone requirement.
Freelancer D — 5 years Shopify development, solo freelancer (not an agency). Based in US Central (full Eastern overlap). Rate: $60/hr. Solid all-around fit, slightly above your budget midpoint but within range.

I haven't sent any messages or offers — let me know which of these you'd like to reach out to first.

When to use it

You're posting a role on Upwork and want AI-assisted candidate sourcing instead of scrolling proposals manually
You need a quick shortlist of 3-5 qualified freelancers with a clear reason each one made the list
You're already working inside ChatGPT, Claude, or Cursor and don't want to switch to the Upwork site to search
You want a consistent, repeatable way to brief the AI so shortlists don't vary wildly between searches

Best practices

Give concrete must-haves (specific tools, years of experience, timezone overlap) instead of vague requirements like "good communicator"
Set a real budget range so the AI filters out freelancers outside it rather than surfacing anyone with the right skill tag
Always review the AI's drafted offer or message before it's sent — Upwork's MCP server requires confirmation for actions like this by design, so use that checkpoint
Ask the AI to show its reasoning for each shortlisted candidate so you can catch a bad match before reaching out

Common mistakes

Giving a one-line job description and expecting a precise shortlist — vague input produces a vague, oversized list
Letting the AI send offers or messages automatically without reviewing the confirmation preview first
Forgetting to specify budget or timezone constraints, which are often the real deciding factors beyond raw skill match
Treating the AI's shortlist as final instead of as a first pass — it still needs a human read of each profile before you commit

FAQs

What is Upwork's MCP server and do I need to install anything?

It's a Model Context Protocol server that connects your Upwork account to AI tools like ChatGPT, Claude, and Cursor. It's free for all Upwork users — you connect it once in your AI tool's MCP/connector settings, then it's available in any conversation.

Can the AI send offers or messages to freelancers on its own?

No — Upwork's MCP server previews any action that changes something, like sending an offer or message, and requires your explicit confirmation before it happens. The prompt above also explicitly tells the AI to stop at the shortlist stage.

Does this work the same way in ChatGPT, Claude, and Cursor?

Yes — the prompt itself doesn't depend on any one tool's syntax. The MCP server exposes the same Upwork actions to whichever AI client you've connected it to.

What if the shortlist the AI returns doesn't match what I actually need?

Make the brief more specific — vague requirements produce vague shortlists. Add concrete must-haves, a real budget range, and explicit deal-breakers, then re-run the search.

Is this only for one-off hires, or can I reuse it for ongoing hiring?

You can reuse the same structured brief format for any role — just swap in the new job title, skills, and budget each time, which keeps your shortlists consistent across multiple hires.

Found this prompt useful? Share it.

More in Productivity

Productivity

ChatGPT Prompt to Turn a Messy Brain Dump Into an Organized Project Plan

This ChatGPT prompt to turn a brain dump into a project plan takes a raw, unordered list of thoughts — the kind you type out in five minutes…

ROLE: You are a project planning assistant that turns unstructured notes into an organized project plan.

CONTEXT:
- Project name: [PROJECT NAME]
- Raw brain dump (unedited): [PASTE YOUR NOTES, BULLET POINTS, OR STREAM-OF-CONSCIOUSNESS TEXT]
- Team members involved, if known: [NAMES OR ROLES]
- Target deadline, if any: [DATE OR TIMEFRAME]

TASK:
1. Read through the raw notes and group related ideas into 3-6 themes or phases
2. For each phase, list the specific tasks that belong to it, pulled from the notes
3. Assign an owner to each task if a name or role was mentioned; otherwise mark it "Unassigned"
4. Flag any item from the notes that was too vague to turn into an actionable task
5. Note any dependency where one task must finish before another can start

CONSTRAINTS:
- Do not invent tasks that weren't implied by the notes
- Do not merge two distinct ideas into one task just to shorten the list

OUTPUT FORMAT:
A phased project plan with phase names as headers, tasks as a checklist under each, and a separate "Needs Clarification" section at the end.

Productivity

Meeting Notes to Action Items

A prompt that converts raw meeting notes or a transcript into the three things people actually need afterwards: what was decided, who does w…

You are an executive assistant. Turn the meeting notes below into a structured summary.

Meeting date: [DATE]
Attendees: [NAMES]

Output sections:
1. Summary (max 4 sentences)
2. Decisions made (bullets)
3. Action items as a table: Owner | Task | Due date
4. Open questions
5. Unassigned items that need an owner

Rules: never invent owners or dates. If missing, write "TBD" and list it in section 5.

Notes:
"""
[PASTE NOTES]
"""

Productivity

ChatGPT Prompt to Write a Weekly Status Update for Your Manager

A weekly status update prompt turns a scattered list of tasks, wins, and blockers into a short, readable report your manager can skim in und…

Role: You are a concise status-report writer helping a [JOB TITLE] summarize their work week for [AUDIENCE, e.g., direct manager, client, cross-functional stakeholders].

Context:
- Reporting period: [DATE RANGE]
- Raw notes on completed work: [LIST COMPLETED TASKS]
- Raw notes on in-progress work: [LIST IN-PROGRESS TASKS WITH % COMPLETE OR STATUS]
- Blockers or risks: [LIST BLOCKERS, OR WRITE "NONE"]
- Upcoming priorities: [LIST NEXT WEEK'S PLANNED WORK]

Constraints:
- Keep the entire report under [WORD LIMIT, e.g., 200] words
- Use plain, non-technical language appropriate for [AUDIENCE]
- Do not invent accomplishments or soften blockers — report status exactly as given
- Flag any blocker that could delay a deadline in its own clearly labeled line

Output format:
1. One-sentence summary of the week
2. "Completed" section as short bullets
3. "In Progress" section as short bullets with status
4. "Blockers/Risks" section (omit if none)
5. "Next Week" section as short bullets