Name: Icp Fit Scorer
Author: Mamba Labs

Icp Fit Scorer MCP

Scores a company against your ICP with weighted signals. Returns score, tier, and breakdown.

Grade A Local · stdio API key 2 tools v1.2.1 · 6 Oct 2026

No reviews yet by Mamba Labsnpm 2,971 Runs on your machine, nothing hosted

96/100

trust score

downloads a day

local

runs on your machine

335

downloads in 30d

What it does

MCP server for ICP Fit Scorer. Scores a company against your ideal customer profile with weighted signals via Apify. Returns a 0 to 100 score, a tier, and a per-signal breakdown. Clay-ready output.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --env 'APIFY_TOKEN=${APIFY_TOKEN}' --transport stdio icp-fit-scorer-mcp '--' npx -y @mambalabsdev/mcp-icp-fit-scorer

# 2 — ask your agent for something these tools do
#   score_icp_fit, list_icp_templates

It needs APIFY_TOKEN: this reads it from your environment, so export it first.

Icp Fit Scorer costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publisher

Mamba Labs57 servers

7 categories · publishing since 2026

All 57 servers

Installation

Where are you running it?

Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Icp Fit Scorer as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.

Claude Codedeclared by this listing

This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads APIFY_TOKEN (Apify API token from https://console.apify.com/account/integrations) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx APIFY_TOKEN … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.

claude mcp add --scope user --env 'APIFY_TOKEN=${APIFY_TOKEN}' --transport stdio icp-fit-scorer-mcp '--' npx -y @mambalabsdev/mcp-icp-fit-scorer

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.

What it asks of you

It reaches a system of yours, so it needs your own credential rather than the publisher’s: APIFY_TOKEN — Apify API token from https://console.apify.com/account/integrations. You set it in your own client’s config, on your machine — this marketplace never holds it.

What it writes

One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.

What you approve

2 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Score a company against your ideal customer profile (ICP) using weighted signals. Returns a 0 to 100 icp_score, an A to D icp_tier, and a per-signal breakdown as a flat, Clay-ready JSON row. Define your ICP with a prebuilt template, a JSON scoring_config, or a plain-English icp_description (which…

Parameter	Type	Required	Notes
company_domain	string	yes	The primary domain of the company to score. Example: clay.com
company_name	string	no	Optional display name of the company.
template	string	no	Name of a prebuilt scoring config, one of the six the actor ships: full_signal, saas_outbound, b2b_services, fintech, smb_local, enterprise. Alternative to scoring_config or icp_description. Call list
scoring_config	object	no	JSON object of scoring weights. Alternative to template or icp_description.
icp_description	string	no	Plain-English description of your target ICP. Requires llm_api_key. Alternative to template or scoring_config.
llm_api_key	string	no	Your OpenAI or Anthropic API key. Required only when using icp_description.
llm_provider	string	no	LLM provider to use with icp_description: openai or anthropic.
fetch_signals	boolean	no	If true, the actor fetches hiring and tech-stack signals for the company automatically before scoring.
include_explanation	boolean	no	If true, adds a score_explanation string to the output describing how the score was derived.
tier_thresholds	object	no	Optional. Minimum score for each tier as { "tier_a": number, "tier_b": number, "tier_c": number }. Scores at or above tier_a are A, tier_b are B, tier_c are C, else D. Defaults to 80 / 60 / 40.
funded_within_days	integer	no	Optional. How recent a funding round must be to count for the recently_funded signal, in days. Defaults to 540 (18 months).
min_score_to_output	integer	no	If set, rows scoring below this threshold are skipped from output (not pushed to dataset). Skipped rows are logged only.
previous_score	integer	no	Previous ICP score for this company. If provided, output includes score_change and score_trend fields.
gtm_hiring_signal	string	no	Whether the company is actively hiring for GTM/sales roles. Accepts a boolean-like string ("true"/"false"). Sent as a string for Clay compatibility and coerced to boolean at runtime.
gtm_role_count	string	no	Number of open GTM/sales roles. Scores via the gtm_role_count_strong signal when at or above min_gtm_roles (default 2). Accepts a numeric string (e.g. "8"). Sent as a string for Clay compatibility and
uses_hubspot	string	no	Whether the company uses HubSpot. Accepts a boolean-like string ("true"/"false"). Sent as a string for Clay compatibility and coerced to boolean at runtime.
uses_salesforce	string	no	Whether the company uses Salesforce. Accepts a boolean-like string ("true"/"false"). Sent as a string for Clay compatibility and coerced to boolean at runtime.
uses_clay	string	no	Whether the company uses Clay. Accepts a boolean-like string ("true"/"false"). Sent as a string for Clay compatibility and coerced to boolean at runtime.
crm_detected	string	no	Whether any CRM was detected. Accepts a boolean-like string ("true"/"false") or any non-empty CRM name (e.g. "Salesforce"). Sent as a string for Clay compatibility and coerced to boolean at runtime. A
seq_tool_detected	string	no	Whether a sales sequencing tool (Outreach, SalesLoft, Apollo, Lemlist) was detected. Accepts a boolean-like string ("true"/"false") or any non-empty tool name (e.g. "Outreach"). Sent as a string for C

List the prebuilt ICP scoring templates score_icp_fit accepts in its template input, with the actor's own note on how they differ. Answers locally from the server: no Apify run, no token needed, and no charge. Use it before score_icp_fit when you have no scoring_config or icp_description of your…

No parameter schema on file.

Free

$0 forever

Every tool, no call limit
No card, and mcprush charges nothing for it
Source published under MIT
Runs on your machine — nothing of it reaches our gateway
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install Icp Fit Scorer or to call it, at any volume.

ATrust score 96 / 100

Release 1.2.1 · scanned 14 Oct 2026

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score96

Findings1 threat · 1 capability

Capabilitymoderate

Coveragesource

Verificationrepo

Surface digest2cb69cb23085c729e6ce18d423d4babcc62bede7b241291888d8bba7d6d49b10

Score vectorthreat 100 → client 96

Term	Level	What it prices	Points
capability-exposure	moderate	capability blast radius (moderate) — client exposure if the model is manipulated	−3
verification-discount	repo	publisher verification (public source) — no provenance, but the source is public and inspectable	−1
coverage-honesty	source	inspection depth (source) — how much of the target the scan could see	−0

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

Tool surfaceread

Implementation sourceread

Package metadataread

Live transportnot available

Tools were statically extracted from the published source (2 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.

Tool	Capability tags	Why the tag was assigned
score_icp_fit	untrusted-inputexternal-sink	untrusted-input: declares openWorldHint: true (interacts with entities outside the server); external-sink: handler sends an HTTP POST (fetch(https://api.apify.com/v2/acts/${actorPath}/runs?timeout=${ACTOR_RUN_TIMEOUT_SECS}) at build/index.js:74
list_icp_templates	no tags

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

flow-1

Untrusted input can drive an external action even though no sensitive source is exposed.

Supply chain and provenance

Integrityfirst-seen

Surface digest2cb69cb23085c729

Scanned2026-10-14

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.