For developers

ICP Intelligence docs

For developers and marketing operations teams. The decision: how to call ICP Intelligence from your own code or assistant.

This page covers the MCP address, the REST API behind the web forms and every input field of all 9 tools.

By Shashwat Ghosh, Co-Founder and Fractional CMO, Helix GTM Consulting · Last updated 2 November 2026

Try these prompts

Use ICP Intelligence to do a deep dive on these customers for our spend management software: mid-size manufacturers with 300 to 3,000 employees and large field sales teams, IT services firms with heavy travel spend, distributors with many branches.
Calculate TAM, SAM and SOM with ICP Intelligence: 9,000 potential companies, average contract value $24,000, 25% fit our ICP, year one share target 1%.
Map the buyer group for spend management software with ICP Intelligence. Deal size $24,000 ACV, target company size 300 to 3,000 employees, typical champion Finance Controller.

MCP server

Address: https://icp-intelligence.gtmhelix.com/mcp (Streamable HTTP, stateless, JSON responses). GET returns 405 by design.
Authentication: none. Every tool is marked read only (readOnlyHint: true, destructiveHint: false) and has a title.
Rate limit: 300 requests per minute per IP address. Server: icp-intelligence-mcp version 1.2.26.
Limits: 262,144 bytes per call; text fields up to 4,000 characters, except the document field customer_descriptions (ICP Deep Dive), which takes up to 100,000; one call per request (no batches). A call over a limit is refused before the tool runs.
Local use: npx -y @shashwatgtmalpha/icp-intelligence-mcp runs these tools over stdio (npm can lag behind this site until a new version is published).

REST API (used by the web forms)

Send POST https://icp-intelligence.gtmhelix.com/api/tools/<tool name> with a JSON body {"input": {...}}. The answer is JSON: {"ok": true, "tool": "...", "title": "...", "text": "..."}, where text is the same Markdown the MCP tool returns. The endpoint calls the same server code as the MCP address.

Terminal

curl -s -X POST https://icp-intelligence.gtmhelix.com/api/tools/icp_deep_dive \
  -H "Content-Type: application/json" \
  -d '{"input": {"customer_descriptions": "Mid-size manufacturers with 300 to 3,000 employees and large field sales teams; the finance controller buys and the pain is a slow month-end close. Also IT services firms with heavy travel spend, and distributors with many branches.", "product_category": "spend management software"}}'

Errors: 400 with errors (missing or invalid fields), 404 for an unknown tool, 405 for methods other than POST, 413 above 32,000 bytes, 422 when the tool itself refuses the input (ok is false and error holds the tool's message), 429 when the rate limit is reached, 500 if the tool fails.
Limits: 30 requests per minute per IP address; the whole request up to 32,000 bytes; top level text fields up to 6,000 characters and top level lists up to 50 items.
Forms without JavaScript post application/x-www-form-urlencoded and get an HTML page back.
Inputs and answers are not stored, and the input is not logged (see Privacy).

Release history

History: first released 17 January 2026, on npm and in the MCP Registry. Dates for npm and the MCP Registry come from their public records; later versions come from the commits in the GitHub repository. npm can lag behind this site until a new version is published.

Version	Date	Where
1.0.0	17 January 2026	npm and the MCP Registry
1.1.0	24 September 2026	GitHub, commit 05250b6
1.2.0	26 September 2026	GitHub, commit cbb91d9
1.2.1	26 September 2026	GitHub, commit ff791d3
1.2.2	27 September 2026	GitHub, commit 5c572ed
1.2.3	27 September 2026	GitHub, commit d36107e
1.2.4	27 September 2026	GitHub, commit 11d5332
1.2.5	27 September 2026	GitHub, commit c276b55
1.2.6	28 September 2026	GitHub, commit 8414dcb
1.2.7	28 September 2026	GitHub, commit 8ec007c
1.2.8	29 September 2026	GitHub, commit b6f989d
1.2.9	29 September 2026	GitHub, commit 0561894
1.2.10	29 September 2026	GitHub, commit 4b79099
1.2.11	29 September 2026	GitHub, commit 8ee0c3f
1.2.12	30 September 2026	GitHub, commit 65a8779
1.2.13	30 September 2026	GitHub, commit c376531
1.2.14	30 September 2026	GitHub, commit ca26a26
1.2.15	30 September 2026	GitHub, commit 170d76b
1.2.16	1 October 2026	GitHub, commit 56a76f8
1.2.18	12 October 2026	safety fix only: the instruction echo safeguard; tool list and answers otherwise unchanged
1.2.22	15 October 2026	security update only: MCP SDK 1.31.0 (advisory GHSA-6qxp-vccf-f47h); tool list and answers unchanged
1.2.24	16 October 2026	security update: text you type is shown with a small backslash before characters that could start a link, image, tag or code, so it can never become live markup; tool list unchanged
1.2.25	17 October 2026	quality update: sector knowledge for the nine verticals and their sub industries on all nine tools; new optional inputs company, product_category and business_model; a usage count per tool (no text you type is kept)
1.2.26 (this site)	26 October 2026	fix: buyer_group_analyzer no longer lists a role you named (for example Head of IT) as not in your list; lookalike_signal_generator shows the checklist and subscriptions only for the platforms you ask for; tool list unchanged

Tool reference

Generated from the server's own input schemas, version 1.2.26.

ICP Deep Dive

icp_deep_dive

Helps you decide which customers to go after next. You give your best customers, as a list (industry, size, contract value, sales cycle, tech stack, buying trigger, champion title) or in your own words. You get the patterns they share, with ties named as ties, the budget shown as the contract value range seen in your customers, recommendations, and sector notes when your inputs name a supported sector. It works only from what you give and looks nothing up. See what it does.

Field	Type	Required	Allowed values	Meaning
`customers`	list of objects	no		List of customer objects with available attributes
`customer_descriptions`	string	no		Alternative: Describe your best customers in text format
`product_category`	string	no		What type of product you sell
`company`	string	no		Optional: your company or product name, so the answer can name it
`business_model`	string	no	saas, services, connectivity, transactions, marketplace, hardware_software, investment	Optional: how you charge (software subscription, services, connectivity, per transaction, marketplace, hardware plus software, or investment management). Read from your other inputs when left out

ICP Scoring Model

icp_scoring_model

Helps you decide which leads are worth a seller's time. You give the criteria that matter, how important each one is and, if you know it, what goes with success. You get a lead scoring template: example point weights set by importance level, example points for each value you list, a scorecard and tier bands to adjust, with sector notes when your inputs name a supported sector. Your success pattern is matched to your criteria; it does not set the weights. See what it does.

Field	Type	Required	Meaning
`scoring_criteria`	list of objects	no	Criteria for scoring with importance levels
`success_correlation`	string	no	What correlates with success? (e.g., "deals with VP Sales champion close 2x faster")
`product_category`	string	no	What you sell, as a product category, for example spend management software.
`company`	string	no	Optional: your company or product name, so the answer can name it

Buyer Group Analyzer

buyer_group_analyzer

Helps you decide who else must agree before a deal can close. You give what you sell, the deal size, the company size, your champion and any stakeholders you know. You get a buying group map with your stakeholders placed by their titles (economic buyer, technical evaluator, reviewers, users), each role's concern and message prompts, an influence map and discovery questions, with sector roles and questions when your inputs name a supported sector. Roles from titles are hypotheses to confirm. See what it does.

Field	Type	Required	Allowed values	Meaning
`deal_size`	string	no		ACV range (e.g., "$50K-100K")
`target_company_size`	string	no		Company size (e.g., "500-1000 employees")
`product_category`	string	yes		What you sell
`known_stakeholders`	list of strings	no		Roles you know are involved
`typical_champion`	string	no		Your typical champion role
`company`	string	no		Optional: your company or product name, so the answer can name it
`business_model`	string	no	saas, services, connectivity, transactions, marketplace, hardware_software, investment	Optional: how you charge (software subscription, services, connectivity, per transaction, marketplace, hardware plus software, or investment management). Read from your other inputs when left out

TAM SAM SOM Calculator

tam_sam_som_calculator

Helps you decide how big your market is, counted bottom up. You give how many companies could buy and your annual contract value in dollars, plus your ICP match rate and year 1 share if you have them. You get TAM, SAM and SOM with the arithmetic and assumptions shown and a summary for an investor deck. It is a calculator, not a data source: a rate you leave out is filled with a labelled example, and sector notes are added when your inputs name a supported sector. See what it does.

Field	Type	Required	Meaning
`total_potential_companies`	number (0 or more)	yes	Estimated total companies that could buy (from LinkedIn, industry reports)
`average_contract_value`	number (more than 0)	yes	Your average ACV in dollars
`icp_percentage`	number (0 or more)	no	Percentage of those companies that match your ICP, from 0 to 100. Left out, 30 is used and marked as an example
`year1_market_share_target`	number (0 or more)	no	Realistic Year 1 market share percentage, from 0 to 100 (typically 1-5%). Left out, 3 is used and marked as an example
`data_sources`	string	no	Where you got your numbers (for documentation)
`segment_name`	string	no	Name of the market segment
`product_category`	string	no	Optional: what you sell (for example "spend management software"), used for sector notes. The arithmetic does not use it
`company`	string	no	Optional: your company or product name, so the answer can name it

Lookalike Signal Generator

lookalike_signal_generator

Helps you decide how to find more accounts like your best ones. You give your ICP's company profile, technologies, champion titles and buying triggers, and optionally what you sell and the platforms you use. You get targeting criteria and search queries for each platform, one signal for each trigger, and search keywords from what you sell and the sector. It writes criteria, not data: it finds no companies or contacts. See what it does.

Field	Type	Required	Meaning
`icp_firmographics`	object	no	Firmographic criteria
`icp_technographics`	list of strings	no	Technologies your ICP typically uses
`champion_titles`	list of strings	yes	Job titles of your champions
`buying_triggers`	list of strings	no	Events that trigger buying
`platforms`	list of strings	no	Optional: the sections to include (linkedin, google_ads, 6sense, zoominfo). Left out, every section is included
`product_category`	string	no	Optional: what you sell (for example "spend management software"), used for search keywords and sector notes
`company`	string	no	Optional: your company or product name, so the answer can name it

Account Prioritization

account_prioritization

Helps you decide which accounts to work first. You give your accounts with fit, intent and relationship scores from 0 to 100 and a timing, plus optional weights. You get a ranked list from a weighted score, with a tier for each account, the points its timing earned and the factor that added the most points. See what it does.

Field	Type	Required	Meaning
`accounts`	list of objects	no	List of accounts to prioritize. Each account: name, fit_score (0 to 100), intent_signals (0 to 100), relationship (0 to 100), timing (now, soon, later or unknown)
`prioritization_weights`	object	no	Optional custom weights in percent for fit, intent, relationship and timing. A missing weight uses its default (40, 30, 15, 15); the tool does not check that the weights sum to 100
`product_category`	string	no	Optional: what you sell (for example "spend management software"), used for sector notes. The arithmetic does not use it
`company`	string	no	Optional: your company or product name, so the answer can name it

ICP Gap Analysis

icp_gap_analysis

Helps you decide whether you are selling to the customers you meant to. You give your current customer base, your ideal customer profile and, if you have them, current and target metrics. You get what the ideal profile has that the current base lacks, metric gaps from your own figures, causes to check and actions that fit your business model, with sector notes when your inputs name a supported sector. See what it does.

Field	Type	Required	Allowed values	Meaning
`current_customers`	string	yes		Description of your current customer base
`ideal_icp`	string	yes		Description of your ideal customer profile
`current_metrics`	object	no		Current performance metrics
`target_metrics`	object	no		Target performance metrics
`product_category`	string	no		Optional: what you sell, used for sector notes
`company`	string	no		Optional: your company or product name, so the answer can name it
`business_model`	string	no	saas, services, connectivity, transactions, marketplace, hardware_software, investment	Optional: how you charge (software subscription, services, connectivity, per transaction, marketplace, hardware plus software, or investment management). Read from your other inputs when left out

ICP Evolution Tracker

icp_evolution_tracker

Helps you decide whether your ICP should change after recent wins and losses. You give your current ICP, recent wins, recent losses and market changes. You get a candidate change for each (an addition to test, a disqualifier to test, an implication to check), a draft of the updated ICP, the roles your ICP does not name, the loss reasons to tag and what to pull from your CRM. It does not compute win rates; check each candidate against your CRM. See what it does.

Field	Type	Required	Meaning
`current_icp`	string	yes	Your current ICP definition
`recent_wins`	string	no	Description of recent successful customers
`recent_losses`	string	no	Description of recent lost deals
`market_changes`	string	no	Recent market or competitive changes
`time_period`	string	no	Time period you are reviewing, in your own words (for example "last quarter")
`product_category`	string	no	Optional: what you sell, used for sector notes
`company`	string	no	Optional: your company or product name, so the answer can name it

ICP Interview Synthesizer

icp_interview_synthesizer

Helps you decide what your customer interviews mean for your ICP. You give structured notes, one per interview: the customer, the role, pain points, buying triggers, value realized and key quotes. You get the pain points, objections, buying triggers, value realized and champion roles across the interviews, quotes kept word for word, discovery questions and sector notes. It does not take full transcripts; give only the points and quotes you want analyzed. See what it does.

Field	Type	Required	Meaning
`interview_notes`	list of objects	no	Structured interview notes: one object per interview with the customer (company or segment), the role of the person interviewed and the points and quotes to analyze
`product_category`	string	no	Optional: what you sell, used for sector notes
`company`	string	no	Optional: your company or product name, so the answer can name it

How to read the answer

Both the MCP server and the REST endpoint return the same structured Markdown text for a given input object; the REST endpoint returns an HTTP 400 error listing any missing or invalid fields. Figures calculated from your inputs are shown directly, while any unprovided benchmark, match rate, share, or weight is labelled as an example figure.

What to do next

Founder: Test TAM, SAM, SOM Calculator or ICP Deep Dive via the MCP endpoint or REST API with your actual addressable accounts and contract value.
CEO: Review the input fields for TAM, SAM, SOM Calculator and ICP Gap Analysis so your team supplies real match rates and share assumptions.
CMO: Use the schemas for ICP Deep Dive, Buyer Group Analyzer, and ICP Interview Synthesizer to standardize customer research inputs.
CRO: Check the fields for Account Prioritization and ICP Scoring Model so revenue operations passes complete account lists and scoring criteria.
Demand generation head: Pass your best customers and trigger signals into Lookalike Signal Generator and Buyer Group Analyzer.

Why come back

Come back when you wire ICP Intelligence into an internal workflow, check allowed enum values, or review the latest release notes. The tool applies the same fixed rules every time. It does not call an AI model, and this site does not keep what you enter.

Choose your app

Run a Helix tool in your browser, then take the result to ChatGPT, Claude or Gemini. Connectors work with supported plans in Claude, ChatGPT, Cursor, VS Code and Windsurf. The Helix GTM Suite skills package supports Claude Code, Gemini CLI, Antigravity, Cursor and VS Code, and is available through skills.sh. Each plugin has its own installation steps, below or on its own page.

Connector setup guides · Skills package setup guide · Find the skills on skills.sh