mcp-icp-fit-scorer
This server scores a company against your Ideal Customer Profile (ICP) using weighted signals, returning a 0–100 icp_score, an A–D icp_tier, a lead_tag, and a per-signal breakdown across hiring, tech stack, headcount, funding, and industry.
Define your ICP three ways:
Use a prebuilt template (e.g.,
b2b_saas) for quick setupProvide a custom JSON scoring config with your own signal weights
Write a plain-English description (requires an OpenAI or Anthropic API key)
Key features:
Requires a company domain as input; optionally accepts a display name
Enable
fetch_signalsto automatically retrieve hiring and tech-stack data before scoringEnable
include_explanationto get a natural-language breakdown of the scoreReturns flat, Clay-ready JSON for easy integration into CRMs or AI agent workflows
Allows using OpenAI's API (e.g., GPT models) to interpret plain-English Ideal Customer Profile descriptions and convert them into scoring configurations.
ICP Fit Scorer MCP Server
An MCP server that scores a company against your ideal customer profile. It wraps the Mamba Labs ICP Fit Scorer actor on Apify and returns a Clay-ready flat JSON row to any MCP client.
What it does
Give it a company domain and a definition of your ICP, and it scores the company on weighted signals, returning a 0 to 100 score, an A to D tier, and a per-signal breakdown. Define your ICP three ways: a prebuilt template, a JSON scoring config, or a plain-English description (which uses your own LLM key). Turn on fetch_signals and the actor will gather hiring and tech-stack signals for you before scoring. One flat row, ready for Clay, a CRM, or an AI agent workflow. All of the scoring runs on Apify. This package is a thin client that calls the actor and hands back the result.
Quick start
You need Node.js 18 or newer and an Apify account with an API token.
Add this to your Claude Desktop config:
{
"mcpServers": {
"mamba-icp-scorer": {
"command": "npx",
"args": ["-y", "@mambalabsdev/mcp-icp-fit-scorer"],
"env": {
"APIFY_TOKEN": "your-apify-token"
}
}
}
}Get your token at https://console.apify.com/account/integrations, paste it in, and restart Claude Desktop. The score_icp_fit tool will be available.
Prerequisites
Node.js 18 or newer
An Apify account with an API token
Example prompts
"Score clay.com against the b2b_saas template and fetch its signals."
"How well does stripe.com fit an ICP of mid-market fintech companies? Explain the score."
"Score figma.com with my scoring config and include the per-signal breakdown."
"Rate openai.com against this ICP description: enterprise AI teams hiring for go-to-market."
Inputs
company_domain(required): the primary domain of the company to score. Example:clay.comcompany_name(optional): display name of the company.template(optional): name of a prebuilt scoring config.scoring_config(optional): a JSON object of scoring weights.icp_description(optional): plain-English ICP description. Requiresllm_api_key.llm_api_key(optional): your OpenAI or Anthropic key, used only withicp_description.llm_provider(optional):openaioranthropic.fetch_signals(optional): let the actor gather hiring and tech-stack signals automatically.include_explanation(optional): add ascore_explanationstring to the output.
Define your ICP with exactly one of template, scoring_config, or icp_description.
This server exposes the single-company scoring path. The actor also supports batch inputs (a dataset or CSV of companies) and a results webhook. For those, run the actor directly on Apify.
Output
The tool returns the actor's flat JSON row for the scored company, including icp_score (0 to 100), icp_tier (A to D), the per-signal breakdown, and an optional explanation. See the Apify Store page for the full output schema.
Example output
{
"company_domain": "ramp.com",
"icp_score": 87,
"icp_tier": "A",
"lead_tag": "priority",
"score_hiring": 25,
"score_tech_stack": 22,
"score_headcount": 20,
"score_funding": 20,
"score_industry": 0,
"run_date": "2026-05-28"
}Features
User-defined JSON scoring config with custom weights
Returns icp_score (0 to 100), icp_tier (A to D), and lead_tag
Per-signal point breakdown: hiring, tech stack, headcount, funding, industry
Replaces 6+ manual formula columns in Clay
Full actor documentation
This server is a thin client and holds no scoring logic. For the complete input and output reference, pricing, and run history, see the Apify Store page:
https://apify.com/mambalabs/icp-fit-scorer
Mamba Labs GTM Suite
This is one of six actors in the Mamba Labs GTM Suite, covering hiring signals, tech stack detection, signal aggregation, job board keyword scanning, LinkedIn URL resolution, and ICP scoring. See them all at https://apify.com/mambalabs.
Related Mamba Labs MCP servers
The rest of the Mamba Labs GTM toolkit, each as its own MCP server:
License
MIT
Built by Mamba Labs. https://apify.com/mambalabs
Maintenance
Tools
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mambalabsdev/mcp-icp-fit-scorer'
If you have feedback or need assistance with the MCP directory API, please join our Discord server