How do I define my ICP?
Three ways: pick a built-in template, provide a JSON config with weights per signal, or write a plain-English description of your ideal customer.

@mambalabsdev
Basic information
Scores any company against your ideal customer profile from a template, a weights config, or a plain-English description, returning a 0 to 100 score and tier. Part of the Mamba Labs signal toolkit.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mamba-icp": {
"command": "npx",
"args": [
"-y",
"@mambalabsdev/mcp-icp-fit-scorer"
],
"env": {
"APIFY_TOKEN": "your-apify-token"
}
}
}
}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 requires llm_api_key). Read-only; requires an APIFY_TOKEN and consumes Apify credits per call.
Icp Fit Scorer is an MCP server that scores any company against your ideal customer profile and returns a 0 to 100 score, a tier (A/B/C), and per-signal reasoning. You define your ICP using a template, a JSON weights config, or a plain-English description.
Pass a company domain along with your ICP definition (template, weights config, or plain-English description). The server evaluates the company against your criteria and returns a scored, tiered result with reasoning. Configure it with your Apify token in the server config.
Three ways: pick a built-in template, provide a JSON config with weights per signal, or write a plain-English description of your ideal customer.
Depends on your config. Common signals include company size, industry, tech stack, hiring activity, geography, and funding stage.
Yes. The server runs on Apify infrastructure. You need an Apify token, which you can get from a free Apify account.
Yes. The output is a flat JSON row with score, tier, and reasoning columns.
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott
MCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.

Kaiva Bridge turns your API, database or documents into a managed MCP server for Claude, ChatGPT, Cursor and VS Code. Point it at an OpenAPI or Swagger spec, an API docs link, a cURL command, a Postman collection, a Grap

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.
CronWatch records every run of your scheduled jobs in your own database, and speaks up when one is missed, fails, gets stuck, runs slow or costs too much. CronWatch is free and open-source.
Comments