Back to cookbook

Claude Prompt to Draft a Tailored Upwork Proposal via MCP

1 views Updated

Make this prompt yours

Share

This is a prompt for freelancers using Upwork's MCP server to draft tailored proposals directly inside Claude, ChatGPT, or Cursor instead of writing each one from scratch on the Upwork site. Through the MCP connection, the AI can pull the actual job post you're applying to and your own profile details, then write a proposal that responds to the specific brief rather than a generic template.

The prompt forces the AI to reference at least one concrete detail from the job post itself โ€” a requirement, a tool mentioned, a problem the client described โ€” which is what separates a proposal that reads as tailored from one that's obviously copy-pasted. Generic proposals are the single biggest reason freelancers get ignored, so this structure exists specifically to avoid that.

Upwork's MCP server also lets freelancers receive job alerts and read client messages through the same connection, so this prompt fits into a broader AI-assisted workflow: get notified of a matching job, draft a tailored proposal immediately, and keep momentum without switching tools.

Prompt template

Make this prompt yours

prompt-template
151 tokens
I'm applying to this Upwork job through your MCP connection. Here's the job post: [PASTE FULL JOB POST TEXT HERE] Here's relevant background from my profile/portfolio: [YOUR RELEVANT SKILLS, PAST PROJECTS, OR RESULTS โ€” BE SPECIFIC] Write a proposal that: 1. Opens by referencing a specific detail or problem from the job post โ€” not a generic greeting. 2. Connects one or two pieces of my real experience directly to what they're asking for. 3. Suggests a concrete first step or question that shows I've actually read the brief. 4. Closes with a clear, low-pressure call to action. 5. Stays under [WORD LIMIT] words. Don't invent any experience I haven't listed above.

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
227 tokens
I'm applying to this Upwork job through your MCP connection. Here's the job post: "Looking for a freelance copywriter to rewrite our SaaS onboarding emails. We have 5 emails that currently get a 12% open rate and almost no click-through. Need someone who understands B2B SaaS tone and can turn these into a sequence that actually drives trial-to-paid conversion." Here's relevant background from my profile/portfolio: I've written onboarding email sequences for 3 B2B SaaS clients, one of which took trial-to-paid conversion from 8% to 19% over two months. I specialize in conversational-but-professional tone for technical products. Write a proposal that: 1. Opens by referencing a specific detail or problem from the job post โ€” not a generic greeting. 2. Connects one or two pieces of my real experience directly to what they're asking for. 3. Suggests a concrete first step or question that shows I've actually read the brief. 4. Closes with a clear, low-pressure call to action. 5. Stays under 150 words. Don't invent any experience I haven't listed above.

Example output

example-output
178 tokens

A 12% open rate on onboarding emails usually points to subject lines and timing more than content โ€” but a near-zero click-through on top of that tells me the emails themselves aren't making the trial-to-paid case clearly.

I recently rewrote a 5-email onboarding sequence for a B2B SaaS client and took their trial-to-paid conversion from 8% to 19% over two months, mainly by restructuring each email around one specific action instead of general feature overviews.

Before diving in, I'd want to know: do you have any data on where in the 5-email sequence users tend to drop off? That would shape whether I focus on email 1-2 (activation) or 3-5 (conversion push).

Happy to share the before/after metrics from that project if useful. Let me know if you'd like to hop on a quick call this week.

When to use it

  • You're applying to a specific Upwork job post and want a proposal that references the actual brief, not a generic template
  • You want to respond quickly to new job alerts without sacrificing quality on each proposal
  • You're testing different proposal angles for similar jobs and want a consistent starting structure to adapt
  • You want the AI to pull from your real profile and portfolio instead of inventing experience you don't have

Best practices

  • Always paste in the actual job post text so the AI has real details to reference, not just a job title
  • Tell the AI to pull only from your real portfolio and past work โ€” don't let it invent experience you don't have
  • Ask for a proposal that opens with the client's specific problem, not a generic greeting or your own bio
  • Review and personalize the draft before sending โ€” it's a strong starting point, not a final submission

Common mistakes

  • Reusing the exact same proposal text across multiple jobs โ€” clients can tell, and it's the top reason proposals get skipped
  • Letting the AI invent skills or past projects you haven't actually done, which creates a mismatch once you're hired
  • Writing a proposal that talks about your experience in general instead of answering the specific problem in the job post
  • Making the proposal too long โ€” most clients skim, so a tailored, concise response beats an exhaustive one

FAQs

Can the AI access my real Upwork profile and portfolio through MCP?

Yes โ€” Upwork's MCP server gives the connected AI access to your profile data, so it can reference your actual history rather than making something up, as long as you point it to pull from your real profile and portfolio.

Will a tailored proposal actually get more responses than a template?

Clients consistently report that generic, copy-pasted proposals are the main reason they skip applicants. A proposal that references a specific detail from the job post signals you actually read it, which is what this prompt is built to produce.

Can I use this same prompt in ChatGPT or Cursor instead of Claude?

Yes โ€” the prompt and the Upwork MCP connection both work across any MCP-compatible AI tool, including ChatGPT and Cursor, not just Claude.

What if I don't have much relevant past experience for a specific job?

Be honest about what you do have and let the AI connect it logically, rather than asking it to invent experience โ€” proposals that overclaim tend to fall apart once a client asks a follow-up question.

Does Upwork's MCP server submit the proposal automatically?

No โ€” actions that change something, including submitting a proposal, are previewed and require your explicit confirmation first, so you always get a chance to review and edit the draft.

Found this prompt useful? Share it.

Share

More in Content Creation & Copywriting

Content Creation & Copywriting

ChatGPT Prompt to Write a Compelling About Us Page for a Business Website

This About Us page prompt helps founders, marketers, and small business owners turn a scattered company history into a page that actually buโ€ฆ

ROLE: You are an experienced brand copywriter who writes About pages that build trust fast.

CONTEXT:
- Business name: [BUSINESS NAME]
- Industry: [INDUSTRY]
- Founding story (key facts only): [2-4 REAL FACTS ABOUT HOW AND WHY THE BUSINESS STARTED]
- Who the business serves: [TARGET CUSTOMER]
- What makes it different: [DIFFERENTIATOR OR UNIQUE APPROACH]
- Desired tone: [TONE, e.g. warm and direct / playful and confident]
- Point of view: [FIRST PERSON SINGULAR / FIRST PERSON PLURAL / THIRD PERSON]

CONSTRAINTS:
- Use only the facts provided above; do not invent dates, numbers, or achievements
- Keep the page between [MIN WORDS] and [MAX WORDS] words
- Avoid generic phrases like "passionate about excellence" or "customer-first mindset"
- End with a clear call to action tied to [DESIRED NEXT STEP]

OUTPUT FORMAT:
1. A headline (under 10 words)
2. An opening paragraph that names the problem the customer faces
3. A middle section introducing the founder/team and the differentiator
4. A closing paragraph with the call to action

Write the About Us page now using only the information given above.

Make this prompt yours

Content Creation & Copywriting

ChatGPT Prompt for Writing Landing Page Headlines and Copy

This ChatGPT prompt for landing page copy helps marketers, founders, and freelance copywriters turn a bare product description into a full lโ€ฆ

Role: You are a direct-response copywriter who writes clear, benefit-led landing page copy.

Context:
- Product or service: [WHAT YOU'RE SELLING]
- Target audience: [WHO THIS PAGE IS FOR]
- Primary benefit or outcome: [THE ONE THING CUSTOMERS CARE ABOUT MOST]
- Supporting features: [2-4 FEATURES OR PROOF POINTS]
- Tone: [E.G. CONFIDENT, FRIENDLY, TECHNICAL, PLAYFUL]
- Desired action: [E.G. START FREE TRIAL, BOOK A DEMO, BUY NOW]

Constraints:
- Do not use generic phrases like "unlock your potential" or "take it to the next level"
- Every headline must reference a specific, concrete outcome
- Keep the subheadline under 20 words
- Use only the features and claims provided above; do not invent statistics or testimonials

Output format:
1. Five headline options, each on its own line
2. One subheadline for the strongest headline
3. Three to five benefit bullets, each starting with the outcome, not the feature
4. One call-to-action button label and one supporting line of microcopy beneath it

Make this prompt yours

Content Creation & Copywriting

ChatGPT Prompt to Write a Customer Case Study That Converts

A customer case study prompt gives ChatGPT the structure it needs to turn a client's raw results into a persuasive success story, instead ofโ€ฆ

ROLE: You are a B2B case study writer who turns customer results into persuasive, specific success stories.

CONTEXT:
- Customer/company: [CUSTOMER NAME AND INDUSTRY]
- Problem they had before working with us: [SPECIFIC PROBLEM OR PAIN POINT]
- What we did / product or service used: [SOLUTION DESCRIPTION]
- Results, with real numbers: [METRICS, PERCENTAGES, DOLLAR AMOUNTS, TIMEFRAMES]
- Customer quote (if available): [DIRECT QUOTE OR 'NONE PROVIDED']
- Target reader: [E.G. COLD PROSPECT, WARM LEAD, EXISTING CUSTOMER CONSIDERING UPSELL]

CONSTRAINTS:
- Do not invent metrics, quotes, or details not provided above.
- Lead with the problem, not company background.
- Use plain, concrete language โ€” avoid words like 'leverage,' 'synergy,' or 'robust.'
- Keep the solution section focused on what changed for the customer, not a feature list.

OUTPUT FORMAT:
1. Headline (under 12 words, outcome-focused)
2. Subhead (one sentence, names the customer and the result)
3. Problem section (2-3 sentences)
4. Solution section (2-3 sentences)
5. Results section (bulleted metrics, 3-5 bullets)
6. Closing pull-quote (use the provided quote, or write 'NEEDS CUSTOMER QUOTE' if none was given)
7. One-sentence call to action

Make this prompt yours