Back to cookbook

AI Prompt to Score and Prioritize Sales Leads Using HubSpot's MCP Server

0 views Updated

Make this prompt yours

Share

This AI prompt for HubSpot's MCP server is built for sales and marketing teams who want to turn a crowded HubSpot pipeline into a ranked list of leads worth calling first. Instead of manually scanning contact records and deal stages, you connect an AI assistant like Claude or ChatGPT to HubSpot through its MCP integration, hand it your scoring criteria, and let it pull live contact properties, deal stage, email engagement, and recent activity to produce a prioritized shortlist with a clear rationale for each ranking.

The prompt works by giving the model a fixed, explainable scoring rubric — firmographic fit, engagement recency, deal value, and buying-stage signals — and instructing it to call HubSpot's MCP tools to retrieve the underlying records rather than guessing from memory. This keeps the output grounded in actual CRM data instead of plausible-sounding fabrications, and it produces a format sales reps can act on immediately: a ranked table with score, reasoning, and a recommended next action per lead.

Because this prompt mixes a structured rubric with live tool calls, it's worth tightening before it runs against your real pipeline. If you want a Business-mode pass that sharpens the scoring criteria and output format before you point it at HubSpot, the Prompt Optimizer is a reasonable next step.

Prompt template

Make this prompt yours

prompt-template
445 tokens
ROLE You are a sales operations analyst with access to HubSpot through an MCP (Model Context Protocol) connection. You can call HubSpot MCP tools to retrieve contact, company, and deal records. CONTEXT Company: [COMPANY NAME] Target segment: [TARGET SEGMENT, e.g. mid-market SaaS companies] Lead source(s) to review: [LEAD SOURCE, e.g. "contacts created in the last 14 days" or "Marketing Qualified Leads list"] Sales motion: [SALES MOTION, e.g. inside sales, outbound SDR, self-serve trial] SCORING RUBRIC Score each lead from 0-100 using these weighted factors: - Firmographic fit ([WEIGHT 1]%): company size, industry, and tech stack match against [IDEAL CUSTOMER PROFILE] - Engagement recency ([WEIGHT 2]%): email opens/clicks, site visits, and form submissions in the last [TIME WINDOW] - Deal stage and value ([WEIGHT 3]%): current HubSpot deal stage and estimated deal value - Buying-stage signals ([WEIGHT 4]%): explicit intent such as demo requests, pricing page visits, or replies to outreach TASK 1. Use HubSpot MCP tools to retrieve the contact, company, and deal records for the lead source specified above. 2. Apply the scoring rubric to each lead using the actual field values returned by HubSpot, not assumptions. 3. Rank the leads from highest to lowest score. 4. For each of the top [NUMBER OF LEADS] leads, state the score, a one-line reason citing the specific HubSpot data that drove it, and a recommended next action. CONSTRAINTS - Do not assign a score without first retrieving the underlying HubSpot record through an MCP tool call. - If a required field is missing from HubSpot, flag it explicitly instead of guessing a value. - Keep the final list to [NUMBER OF LEADS] leads maximum. OUTPUT FORMAT A ranked table with columns: Rank | Lead Name | Score | Key Reason | Recommended Next Action Followed by a short summary of any leads that had missing or incomplete HubSpot data.

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
193 tokens
ROLE You are a sales operations analyst with access to HubSpot through an MCP connection. CONTEXT Company: Northwind Analytics Target segment: mid-market SaaS companies with 50-500 employees Lead source(s) to review: contacts created in the last 14 days from the "Q4 Webinar" campaign Sales motion: inside sales with a 4-person SDR team SCORING RUBRIC - Firmographic fit (30%): company size and industry match against mid-market B2B SaaS - Engagement recency (25%): email opens/clicks and site visits in the last 14 days - Deal stage and value (25%): current HubSpot deal stage and estimated deal value - Buying-stage signals (20%): demo requests, pricing page visits, or reply activity TASK Retrieve the webinar contacts via HubSpot MCP tools, score each against the rubric, and return the top 10.

When to use it

  • You have more inbound or outbound leads in HubSpot than your sales team can call in a day and need a ranked list.
  • A new rep needs a consistent, repeatable way to judge lead quality instead of relying on gut feel.
  • Marketing just closed a campaign and dumped a batch of new contacts into HubSpot that need triaging by fit and intent.
  • Sales leadership wants a weekly pipeline review that explains why each lead is ranked the way it is, not just a raw score.

Best practices

  • Define your scoring rubric in plain numbers (for example, deal value weighted 30%, engagement recency 25%) before you ask the model to apply it, so results are consistent run to run.
  • Ask the model to cite which HubSpot property or MCP tool call produced each score component, so a rep can verify a ranking in seconds instead of trusting it blindly.
  • Re-run the prompt on a rolling schedule (daily or weekly) rather than once, since engagement recency and deal stage change constantly in an active pipeline.
  • Cap the output at a workable list size (15-25 leads) instead of asking for every contact in the portal, so reps actually act on it instead of skimming past it.

Common mistakes

  • Letting the model invent a lead score from a contact's name or company alone instead of requiring it to pull actual HubSpot deal and engagement data first.
  • Using vague criteria like "good fit" or "high intent" without defining what those mean in measurable HubSpot fields, which produces inconsistent rankings each run.
  • Scoring the entire database at once instead of segmenting by lifecycle stage first, which buries hot deal-stage leads under cold top-of-funnel contacts.
  • Treating the ranked list as final instead of spot-checking a few scores against the actual HubSpot record before handing it to the sales team.

FAQs

What is HubSpot's MCP server and how does it work with AI prompts?

HubSpot's MCP (Model Context Protocol) server lets an AI assistant like Claude or ChatGPT connect directly to your HubSpot portal and call tools that read contact, company, and deal records. Instead of pasting CRM data into a chat, the model retrieves it live through the MCP connection, which keeps lead scores grounded in your actual pipeline instead of guesses.

Can I use this lead-scoring prompt without HubSpot's MCP integration?

Yes, but you would need to paste the relevant contact and deal data into the chat yourself, and the model would lose the ability to pull fresh engagement signals on its own. The MCP connection is what lets the scoring stay current without manual data exports.

How often should I re-run a HubSpot lead-scoring prompt?

Most sales teams get the most value running it daily for active pipelines or weekly for longer sales cycles, since engagement recency and deal stage are the factors that change fastest and most directly affect which leads deserve a call today.

Which Cuelara tool can help me catch gaps in this lead-scoring prompt before I run it against real HubSpot data?

Prompt Debugger — it scans a prompt like this one for vague scoring criteria, missing edge cases (such as leads with incomplete HubSpot data), and logic gaps before you rely on its output to prioritize outreach.

Found this prompt useful? Share it.

Share

More in Marketing & Sales

Marketing & Sales

ChatGPT Prompt to Write a Compelling Elevator Pitch for Your Startup or Business

This ChatGPT prompt is built for founders, salespeople, consultants, and job seekers who need a tight, memorable elevator pitch that explain…

Role: You are a pitch coach who helps people explain their business or idea clearly and persuasively in a short amount of time.

Context:
- Business or idea: [WHAT YOU DO IN ONE SENTENCE]
- Target audience for this pitch: [E.G., INVESTORS, CUSTOMERS, A HIRING MANAGER]
- Problem you solve: [THE SPECIFIC PAIN POINT OR NEED]
- What makes your approach different: [YOUR UNIQUE ANGLE OR ADVANTAGE]
- Setting where this will be delivered: [E.G., INVESTOR MEETING, NETWORKING EVENT, LINKEDIN PROFILE]
- Desired outcome: [WHAT YOU WANT THE LISTENER TO DO NEXT, E.G., SCHEDULE A CALL, TRY THE PRODUCT, REFER SOMEONE]

Constraints:
- Keep sentences short enough to say in one breath.
- Avoid jargon unless the audience specifically expects it.
- Do not include statistics or claims that are not provided above.
- End with a clear, specific call to action, not a vague closing line.

Output format:
1. A 10-second version (one sentence).
2. A 30-second version (3-4 sentences).
3. A 60-second version (a short paragraph with a brief example or proof point).
4. One alternate opening line for each version that could be used instead, in case the first one doesn't fit the room.

Make this prompt yours

Marketing & Sales

ChatGPT Prompt to Write a Product Launch Announcement

A product launch announcement prompt helps marketers, founders, and product managers turn a list of features into a clear, persuasive announ…

ROLE: You are a product marketing copywriter who writes clear, benefit-led launch announcements.

CONTEXT:
- Product or feature name: [PRODUCT_NAME]
- What it does in one sentence: [ONE_SENTENCE_DESCRIPTION]
- Problem it solves / what changes for the user: [CORE_BENEFIT]
- Target audience: [AUDIENCE]
- Launch date or availability: [LAUNCH_DATE]
- Tone: [TONE, e.g. confident and direct / playful / technical]

TASK:
Write a product launch announcement for the channel specified below. Lead with the customer benefit, not the feature mechanics. Address the audience's likely hesitation: [KNOWN_OBJECTION]. End with a clear call to action: [DESIRED_ACTION].

CONSTRAINTS:
- Channel: [CHANNEL, e.g. email / LinkedIn post / blog post intro]
- Length limit: [WORD_OR_CHARACTER_LIMIT]
- Do not use generic phrases like "game-changing" or "revolutionary"
- Keep sentences short enough to scan on mobile

OUTPUT FORMAT:
1. Three headline or subject line options
2. The full announcement body matching the channel and length limit
3. One short alternate version with a different angle (e.g. urgency vs. curiosity)

Make this prompt yours

Marketing & Sales

ChatGPT Prompt to Write a Memorable Brand Tagline or Slogan

This ChatGPT prompt generates a batch of candidate brand taglines for a business, product, or campaign, built for founders, marketers, and s…

Role: You are a brand strategist writing taglines for [COMPANY/PRODUCT NAME].

Context:
- What the business does: [DESCRIBE PRODUCT OR SERVICE]
- Target audience: [DESCRIBE WHO BUYS OR USES IT]
- Key differentiator: [WHAT MAKES THIS BRAND DIFFERENT FROM COMPETITORS]
- Brand tone: [e.g. playful, premium, no-nonsense, warm]

Task:
Generate [NUMBER] tagline options for this brand.

Constraints:
- Keep each tagline under [MAX WORD COUNT] words
- Include a mix of tones: at least a few literal/clear options, a few clever/wordplay options, and a few emotional/aspirational options
- Avoid generic phrases like "quality you can trust" or "taking it to the next level"
- Label each tagline with which tone category it falls into

Output format:
Numbered list grouped by tone category, with each tagline on its own line.

Make this prompt yours