Skip to main content

Data engineer building an agent pipeline on Megido

Get the shape of a niche my agent already found, as JSON

The distributions of a niche your agent found in an earlier step, in one machine-readable object.

You: My agent already found the niche SaaS invoicing platforms. Give me its shape as JSON: size, growth, scale and countries.

Megido get_cohortdistributions
Agent: 
{"niche_id": "<id>", "niche": "SaaS invoicing platforms", "size": "50-199", "median_index": 62.7,
 "share_growing": 48,
 "scale": {"<500": 3, "500-3k": 20, "3k-15k": 25, "15k-75k": 17, "75k-1M": 30, "1M+": 5},
 "leading_countries": {"US": 23},
 "revenue_observed": true}
Real data from the corpus, as of August 2026. Growth compares the latest month with the one before.

How your agent answers

  1. get_cohort opened the niche by the id your agent kept from an earlier step and returned its distributions.

Where it stops. There are no sites or names in the object, and no revenue: revenue_observed says that payment was observed, not how much. Ids are issued to each organization, so the example shows <id>.

Ask your agent

You already found the niche [niche]. Give me its shape as JSON: size, growth, scale and countries.

View as Markdown

Ask your agent today

Megido is in early access. Request access, or sign in if you already have an account. If your team is already on Megido, ask its owner for an invitation. Then ask from your AI agent, in the Megido chat, or as a task for Megido's agents.

Request early accessSign in

In Claude Code, add the server, then run /mcp and choose to authenticate:

claude mcp add --transport http megido https://api.megido.io/mcp

Claude, ChatGPT, Cursor, VS Code and other apps, by signing in or with an API key: step by step.