impact-mcp
This server provides read-only B2B positioning tools for applying the IMPACT framework, from buyer-role hypotheses through competitive mapping, value positioning, market selection, messaging, channel execution, and full audits.
Get the IMPACT method step by step, filtered by phase and sector.
Identify champion, economic buyer, influencer, reviewer, user, and anti-champion hypotheses.
Map competitors, status quo, doing nothing, strengths/weaknesses, and discovery questions.
Pinpoint believable value statements, proof points, audience/channel versions, and test questions.
Anchor a beachhead segment with segment ranking, TAM/SAM/SOM sizing, expansion path, and ICP hypothesis.
Craft core positioning statements, message hierarchy, objection handling, and message tests.
Translate positioning into website, LinkedIn, email, sales deck, and demo copy.
Run a full positioning audit with input completeness scores, proof review, 30-day plan, and measures.
Build a segment-specific message via a staged map-to-message workshop with proof-gap handling and confirmation receipt.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@impact-mcp Identify champions for a project management tool for remote teams."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
IMPACT MCP v2.2.28
By Helix GTM Consulting (https://gtmhelix.com), built by Shashwat Ghosh, Co-Founder and Fractional CMO.
Hypothesis-Driven B2B Positioning Engine: 8 tools implementing the IMPACT framework for strategic positioning and go-to-market messaging.
Use it hosted (no install)
Add https://impact.gtmhelix.com/mcp to Claude or ChatGPT as a custom connector, or to Codex or Gemini CLI as an MCP server. It needs no sign-in and always runs the newest version (2.2.28). The same tools run as a free web app with a form per tool at https://impact.gtmhelix.com/, and the setup steps are at https://impact.gtmhelix.com/connect/.
The npm package below is an older version (2.0.0 on npm on 27 September 2026) until the next npm release. Use it only if you need a local stdio server.
Related MCP server: Andru
Quick Start
# Run directly with npx
npx -y @shashwatgtmalpha/impact-mcpClaude Desktop Configuration
Add to your claude_desktop_config.json:
{
"mcpServers": {
"impact-mcp": {
"command": "npx",
"args": ["-y", "@shashwatgtmalpha/impact-mcp"]
}
}
}The IMPACT Framework
IMPACT is a hypothesis-driven positioning methodology for B2B companies:
Phase | Focus | Tool |
Identify | Champions & Buyer Personas |
|
Map | Alternatives & Competitive Landscape |
|
Pinpoint | Value Proposition & Differentiation |
|
Anchor | Market Selection & Beachhead |
|
Craft | Messaging & Positioning Statement |
|
Translate | Channel-Specific Execution |
|
Tools and inputs
Tool names and input formats were checked against tools/list of impact-mcp 2.2.28 on 17 November 2026. Query tools/list for current descriptions.
# | Tool | Title | What it does |
1 |
| IMPACT Framework Guide | Helps you decide which positioning steps to run, and in what order. You give nothing, or one IMPACT step to focus on and your sector. You get the IMPACT positioning method step by step (identify champions, map alternatives, pinpoint value, anchor in a market, craft the message, translate it to execution), with a template or checklist for each step; a focus step returns that step only, and your sector adds its buyer roles, measures and proof points. |
2 |
| Identify Champions | Helps you decide who inside the buyer will push for you. You give what your product does and the problem it solves, plus optional company name, target company type, price point and sector. You get hypotheses for the champion, the economic buyer, the technical influencer, commercial and control reviewers and daily users, warning signs of an anti champion, a path to develop the champion and what to give them. These are roles to test, not named people. |
3 |
| Map Alternatives | Helps you decide what buyers compare you with, and where you can lead. You give your product and its category, plus optional competitors, their weaknesses and your strengths. You get one card for each competitor you name, the status quo and doing nothing, where you can lead and discovery questions, with your sector's questions and objections. It uses only what you give and says what would sharpen the map. |
4 |
| Pinpoint Value | Helps you decide what you can claim that buyers will believe. You give your target customer, the main outcome they get and what you do that others do not, plus optional product name, category, customer results and business model. You get value statements in three versions, a value matrix for your own figures, proof points ranked from customer results to social proof, versions for different audiences and channels, and questions to test the value. |
5 |
| Anchor Market | Helps you decide which market segment to win first. You give what your product does and the segments you are weighing, plus optional customers, pain, deal size and company counts. You get a beachhead choice: your segments ranked from your own customers, pain and deal size when you give all three (the answer says which method it used), otherwise scored on keywords in their names; a TAM, SAM and SOM calculation from only the figures you give; a three year expansion path and an ICP hypothesis for the chosen segment. It never chooses a segment you did not name. |
6 |
| Craft Message | Helps you decide what your core message is, and how to test it. You give your target customer, the key benefit and what sets you apart, plus optional product name, customer need, category, main competitor and business model. You get a positioning statement (full and one sentence), a message hierarchy from tagline to three supporting pillars, versions for different audiences, objection handling and ways to test the message. It writes from your own words, in whole sentences. |
7 |
| Translate Execution | Helps you decide how your positioning should read in each channel. You give a positioning statement, your target customer and the key benefit, plus optional channels, product name and business model. You get copy to edit: a website hero, a LinkedIn tagline and post drafts, a three email cold sequence, a sales deck outline and a 15 minute demo script, with calls to action that fit your business model and the order to work the channels in. |
8 |
| IMPACT Full Audit | Helps you decide whether your positioning is working and what to fix first. You give what your product does, your target customer and the problem you solve, plus optional company name, differentiation, competitors, current positioning, customer feedback and business model. You get a positioning audit: an input completeness score for each IMPACT step, the proof you already have, your current positioning checked in words, a recommended positioning with tagline options, a 30 day action plan and the measures to track. The score measures how complete your inputs are, not how strong your positioning is. |
Inputs of each tool
1. IMPACT Framework Guide (impact_get_framework)
Input | Required | Type | Description |
| No | one of: | Optional: specific phase to focus on (identify/map/pinpoint/anchor/craft/translate) |
| No | one of: | Your company's own industry (not your customers'). When given, it decides the sector notes; when left out, the tool reads it from your words and stays neutral if they are unclear. |
2. Identify Champions (impact_identify_champions)
Input | Required | Type | Description |
| Yes | string | What your product does (1-2 sentences) |
| Yes | string | The core problem you solve |
| No | string | Your company name |
| No | string | Type of companies you target (e.g., "Series B SaaS", "Enterprise manufacturing") |
| No | string | Optional: ACV range (e.g., "$50K-100K") |
| No | one of: | Your company's own industry (not your customers'). When given, it decides the sector notes; when left out, the tool reads it from your words and stays neutral if they are unclear. |
3. Map Alternatives (impact_map_alternatives)
Input | Required | Type | Description |
| Yes | string | What your product does |
| Yes | string | Your product category (e.g., "Sales engagement", "Data platform") |
| No | array of string | List of competitor names |
| No | string | Optional: Known competitor weaknesses or customer complaints |
| No | string | Optional: What you do better than competitors |
| No | one of: | Your company's own industry (not your customers'). When given, it decides the sector notes; when left out, the tool reads it from your words and stays neutral if they are unclear. |
4. Pinpoint Value (impact_pinpoint_value)
Input | Required | Type | Description |
| Yes | string | Who you serve (e.g., "B2B sales teams") |
| Yes | string | The main result customers achieve |
| Yes | string | What you do that others cannot/don't |
| No | string | Your product/company name |
| No | string | Product category |
| No | string | Optional: Any customer results data (e.g., "40% faster, 3x pipeline") |
| No | one of: | Your company's own industry (not your customers'). When given, it decides the sector notes; when left out, the tool reads it from your words and stays neutral if they are unclear. |
5. Anchor Market (impact_anchor_market)
Input | Required | Type | Description |
| Yes | string | What your product does |
| No | array of string | The market segments you are weighing, in your own words (for example Mid-market fintech, Enterprise banks, Small retail chains). Needed for a recommendation: without segments no segment is chosen, and the answer explains how to find yours |
| No | string | Optional: Description of your current/best customers. Shown in the output; not used in the scoring |
| No | string | Optional: Your ACV as one amount (e.g., "$50,000", "$50K" or "$1.5M"); a range is refused |
| No | string | Optional: Typical sales cycle length. Shown in the output; not used in the scoring |
| No | one of: | Your company's own industry (not your customers'). When given, it decides the sector notes; when left out, the tool reads it from your words and stays neutral if they are unclear. |
6. Craft Message (impact_craft_message)
Input | Required | Type | Description |
| Yes | string | Target customer description |
| Yes | string | Primary benefit/reason to buy |
| Yes | string | Your unique differentiation |
| No | string | Your product name |
| No | string | The need they have, written as an action (for example "lose revenue to missed appointments") |
| No | string | Your product category, written as a noun phrase (for example "analytics platform") |
| No | string | Primary alternative/competitor |
| No | one of: | Your company's own industry (not your customers'). When given, it decides the sector notes; when left out, the tool reads it from your words and stays neutral if they are unclear. |
7. Translate Execution (impact_translate_execution)
Input | Required | Type | Description |
| Yes | string | Your core positioning statement |
| Yes | string | Target customer profile |
| Yes | string | Primary benefit, written as an action (for example "cut no-shows") |
| No | array of string | Accepted but not used yet: the output always covers website, LinkedIn, email, sales deck and demo |
| No | string | Your product name |
| No | one of: | Your company's own industry (not your customers'). When given, it decides the sector notes; when left out, the tool reads it from your words and stays neutral if they are unclear. |
8. IMPACT Full Audit (impact_full_audit)
Input | Required | Type | Description |
| Yes | string | What your product does |
| Yes | string | Who you serve |
| Yes | string | The problem you solve |
| No | string | Your company name |
| No | string | What makes you unique |
| No | array of string | Main competitors |
| No | string | Optional: Your current positioning statement or tagline |
| No | string | Optional: What customers say about you |
| No | one of: | Your company's own industry (not your customers'). When given, it decides the sector notes; when left out, the tool reads it from your words and stays neutral if they are unclear. |
Who Is This For?
Primary Users
Role | Key Tools | Use Cases |
Founders/CEOs |
| Market selection, value articulation |
CMOs/VPs Marketing |
| Positioning health assessment |
Product Marketing |
| Messaging, channel adaptation |
Sales Leaders |
| Competitive positioning |
GTM Consultants | All tools | Full positioning engagements |
Job-to-Tool Mapping
Job To Be Done | Recommended Tool |
"I need to understand the IMPACT methodology" |
|
"I need to define our ideal buyer champion" |
|
"I need to map our competitive landscape" |
|
"I need to articulate our unique value" |
|
"I need to select our beachhead market" |
|
"I need to create our positioning statement" |
|
"I need to adapt messaging for different channels" |
|
"I need a full positioning audit" |
|
Recommended Agent Skills
This MCP is included in these user-focused Agent bundles:
Agent Bundle | Tools Count | Best For |
Founder GTM Copilot | 10 tools | Founders, early-stage CEOs |
Product Marketing Engine | 12 tools | PMMs, product marketers |
GTM Consultant Suite | 12 tools | Fractional CMOs, advisors |
SDR Toolkit | 8 tools | SDRs, BDRs |
Related MCPs
MCP | Focus | Tools | Link |
CRAFT GTM | GTM strategy | 8 | |
CRAFT Content | Content creation | 8 | |
ICP Intelligence | ICP & targeting | 9 | |
Revenue Enablement | Sales execution | 12 |
About the IMPACT Framework
The IMPACT framework was developed by Shashwat Ghosh based on 24+ years in B2B and 10+ years of fractional experience. It addresses the common failure mode of B2B positioning: starting with features instead of market hypotheses.
Key Principles:
Hypothesis-driven: Test assumptions before committing
Outside-in: Start with customer, not product
Iterative: Refine based on market feedback
Execution-focused: Bridge strategy to implementation
Author
Shashwat Ghosh, Co-Founder and Fractional CMO, Helix GTM Consulting, with 24+ years in B2B and 10+ years of fractional experience
License
MIT License: see LICENSE for details.
Part of the Helix GTM Consulting MCP suite: rule-based B2B go-to-market tools (no AI model runs inside them)
Hosted connector (Streamable HTTP)
The same tools are also available as a hosted MCP server, so they work in Claude on the web, desktop and mobile without installing anything.
Server URL:
https://impact.gtmhelix.com/mcpTransport: Streamable HTTP (stateless, JSON responses). Authentication: none.
Setup guide: https://impact.gtmhelix.com/connect/
In Claude: Customize, then Connectors, then Add custom connector, and paste the server URL.
In Claude Code:
claude mcp add --transport http impact https://impact.gtmhelix.com/mcp
The npm package (stdio) and the hosted server run the same createServer() code in src/index.ts.
The tool reference (https://impact.gtmhelix.com/docs/) is generated from the code. Where it differs from the parameter tables earlier in this README, the tool reference is correct.
Privacy Policy
Full policy: https://impact.gtmhelix.com/privacy/ (also in PRIVACY.md).
Data collection: the hosted server receives only the tool name and the inputs of each tool call. The npm package runs on your computer and sends nothing to us.
Use and storage: inputs are used only to build that call's reply. Inputs and answers are not stored: no database, no files, no cache, no logging of inputs or outputs by our code. Each call adds one anonymous usage record (date and time, site and tool name, app kind, web form or assistant); see the privacy page.
Third-party sharing: none by us. Netlify hosts the server and processes requests under its own policy (https://www.netlify.com/privacy/). Fonts are served from this site, so loading a page contacts no one else.
Retention: we keep no tool inputs or outputs. Netlify keeps its own platform logs under its policy.
Contact: shashwat@gtmhelix.com
Build our message for this segment
impact_build_segment_message runs in chat with a mandatory pause. The map call starts the existing champion and alternatives tools independently. It leads with proof gaps and questions about the current approach, then returns both maps and a review receipt. The buyer confirms the champion, the target customer wording and the alternative. Chat carries that same brief and receipt into the message call; the server stores no brief.
The message call uses the existing value and message tools. An optional agreed claim from the ChatGPT Positioning Workshop is the starting point. Without a real customer result with source and measurement period, the buyer lines stay labelled unproved hypotheses, figures are held out, and only discovery questions are offered next. With a result supplied, the sales kit is also offered. The tool still asks the buyer to check that trigger, measure and mechanism concern the same thing, test the category word and take the draft to five buyers.
The display-only view is derived from the shared Helix results view and served at ui://helix/results/chains/v1.html. Choices send a message to chat; the widget does not call tools or calculate. Text-only hosts receive the complete same answer. The tool page is /tools/build-segment-message/ and has no form. To regenerate the additive view after a display change, run python scripts/build-chain-view.py, then npm run build. The font licences sit beside the bundled fonts.
Available Tools
9 toolsimpact_anchor_marketAnchor MarketARead-onlyInspect
Helps you decide which market segment to win first. You give what your product does and the segments you are weighing, plus optional customers, pain, deal size and company counts. You get a beachhead choice: your segments ranked from your own customers, pain and deal size when you give all three (the answer says which method it used), otherwise scored on keywords in their names; a TAM, SAM and SOM calculation from only the figures you give; a three year expansion path and an ICP hypothesis for the chosen segment. It never chooses a segment you did not name. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing required fields or invalid values return an error naming what to supply or correct. Use this instead of tam_sam_som_calculator when you need to choose among supplied market segments before sizing the chosen one.
Inputs: product_description (required), sales_cycle, your_sector, customer_pain, +6 more.
impact_build_segment_messageBuild our message for this segmentARead-onlyInspect
Helps you decide how to build a message for one segment when sellers do not use it or buyers keep their current approach. Needs the product, segment, champion problem, alternatives, outcome, capability and proof. Returns proof gaps and current approach questions, champion and alternatives maps for human choices, then a message and proof plan after a pause. Optional agreed workshop claim is the starting point. Without a real customer result, buyer lines are unproved hypotheses and the next step is discovery questions. Chat carries the brief between calls. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing or invalid stage or brief fields return field-specific errors. The message stage requires the matching review receipt and confirmed choices. Missing real proof keeps buyer lines as unproved hypotheses. Use this instead of impact_craft_message when you need a staged segment workshop with confirmed champion and alternative choices.
Inputs: brief (required), stage (required), choices, review_receipt.
impact_craft_messageCraft MessageARead-onlyInspect
Helps you decide what your core message is, and how to test it. You give your target customer, the key benefit and what sets you apart, plus optional product name, customer need, category, main competitor and business model. You get a positioning statement (full and one sentence), a message hierarchy from tagline to three supporting pillars, versions for different audiences, objection handling and ways to test the message. It writes from your own words, in whole sentences. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing required fields or invalid values return an error naming what to supply or correct. Use this instead of impact_translate_execution when you need the core positioning statement and message hierarchy.
Inputs: key_benefit (required), differentiation (required), target_customer (required), competitor, +5 more.
impact_full_auditIMPACT Full AuditARead-onlyInspect
Helps you decide whether your positioning is working and what to fix first. You give what your product does, your target customer and the problem you solve, plus optional company name, differentiation, competitors, current positioning, customer feedback and business model. You get a positioning audit: an input completeness score for each IMPACT step, the proof you already have, your current positioning checked in words, a recommended positioning with tagline options, a 30 day action plan and the measures to track. The score measures how complete your inputs are, not how strong your positioning is. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing required fields or invalid values return an error naming what to supply or correct. Use this instead of impact_craft_message when you need a full positioning review across all six IMPACT steps.
Inputs: problem_solved (required), target_customer (required), product_description (required), competitors, +6 more.
impact_get_frameworkIMPACT Framework GuideARead-onlyInspect
Helps you decide which positioning steps to run, and in what order. You give nothing, or one IMPACT step to focus on and your sector. You get the IMPACT positioning method step by step (identify champions, map alternatives, pinpoint value, anchor in a market, craft the message, translate it to execution), with a template or checklist for each step; a focus step returns that step only, and your sector adds its buyer roles, measures and proof points. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. No input returns all six steps. Invalid focus_phase or sector choices return an error naming the allowed values. Use this instead of impact_full_audit when you need the IMPACT method and templates before applying it to a product.
Inputs: sector, focus_phase, your_sector.
impact_identify_championsIdentify ChampionsARead-onlyInspect
Helps you decide who inside the buyer will push for you. You give what your product does and the problem it solves, plus optional company name, target company type, price point and sector. You get hypotheses for the champion, the economic buyer, the technical influencer, commercial and control reviewers and daily users, warning signs of an anti champion, a path to develop the champion and what to give them. These are roles to test, not named people. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing required fields or invalid values return an error naming what to supply or correct. Use this instead of buyer_group_analyzer when you need champion-role hypotheses from a product and problem.
Inputs: problem_solved (required), product_description (required), price_point, your_sector, +2 more.
impact_map_alternativesMap AlternativesARead-onlyInspect
Helps you decide what buyers compare you with, and where you can lead. You give your product and its category, plus optional competitors, their weaknesses and your strengths. You get one card for each competitor you name, the status quo and doing nothing, where you can lead and discovery questions, with your sector's questions and objections. It uses only what you give and says what would sharpen the map. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing required fields or invalid values return an error naming what to supply or correct. Use this instead of competitive_intel when you need positioning against competitors, the current approach and doing nothing.
Inputs: category (required), your_product (required), competitors, your_sector, +2 more.
impact_pinpoint_valuePinpoint ValueARead-onlyInspect
Helps you decide what you can claim that buyers will believe. You give your target customer, the main outcome they get and what you do that others do not, plus optional product name, category, customer results and business model. You get value statements in three versions, a value matrix for your own figures, proof points ranked from customer results to social proof, versions for different audiences and channels, and questions to test the value. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing required fields or invalid values return an error naming what to supply or correct. Use this instead of impact_craft_message when you need outcome and proof statements before writing the core message.
Inputs: key_outcome (required), target_customer (required), unique_capability (required), category, +4 more.
impact_translate_executionTranslate ExecutionARead-onlyInspect
Helps you decide how your positioning should read in each channel. You give a positioning statement, your target customer and the key benefit, plus optional channels, product name and business model. You get copy to edit: a website hero, a LinkedIn tagline and post drafts, a three email cold sequence, a sales deck outline and a 15 minute demo script, with calls to action that fit your business model and the order to work the channels in. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing required fields or invalid values return an error naming what to supply or correct. Use this instead of impact_craft_message when you already have positioning and need channel-specific copy.
Inputs: key_benefit (required), target_customer (required), positioning_statement (required), channels, +3 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 9 tools
The six IMPACT step tools (champions, alternatives, value, anchor, message, execution) map cleanly to distinct method steps, but impact_full_audit, impact_craft_message, and impact_build_segment_message substantially overlap in output (positioning statement/message). The descriptions acknowledge this by adding 'use this instead of X' routing hints, which helps but shows real boundary friction.
All tools share the impact_ prefix and snake_case, and most follow a verb_noun shape (get_framework, identify_champions, map_alternatives, pinpoint_value, anchor_market, craft_message, translate_execution, build_segment_message). impact_full_audit deviates by omitting a leading verb, a minor inconsistency in an otherwise predictable scheme.
Nine tools is well within the ideal range and each corresponds to a concrete stage of the IMPACT method or a cross-cutting audit/framework lookup. Nothing feels padded or missing at the count level.
The surface covers framework retrieval, all six positioning steps, a full audit, and a staged segment workshop, which is strong lifecycle coverage for a positioning methodology. Minor gaps: messaging testing/validation is only embedded inside craft_message, and there is no standalone way to store or revise positioning across calls, though the read-only stateless design appears intentional.
Maintenance
Related MCP Connectors
CRAFT GTM: 8 go to market strategy tools by Helix GTM Consulting
Tools for Go-to-market teams creating sales materials, product demos, and deal rooms for customers.
Revenue Engine for scoped diagnosis, action planning, execution, and Figure-Eight value evidence.
CRAFT Content: 8 B2B content tools by Helix GTM Consulting
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceBusiness intelligence toolkit that analyzes competitors, scores websites, builds customer personas, and conducts market research using real-time competitive data. 8 tools including SWOT analysis, pricing analysis, and local market intelligence.MIT
- AlicenseAqualityBmaintenanceRevenue intelligence for complex B2B growth. Your agent builds the assets technical founders sell with, and prepares them for real buyer conversations.34398 npm2MIT
IMPACT Framework MCP ServerDeprecated
AlicenseAqualityFmaintenanceProvides B2B positioning and messaging tools based on the IMPACT Framework, enabling analysis of champions, competitors, and value propositions to craft compelling messages and execute strategic audits.836 npmMIT- AlicenseAqualityBmaintenanceEnables deep ICP analysis with 9 tools for ideal customer profiling, market sizing, buyer mapping, and account prioritization.9307 npm3MIT