DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to connect an agent to the growth.engineer catalog with Growth Engineer

Add the read-only MCP server so an agent can search workflows, tools and companies.

Who it is forA marketer or founder who wants their agent to look up go-to-market plays without copying docs by hand.

The problemVendor docs are written for people, and growth plays often live in private notes an agent cannot read.

The outcomeThe agent can search the catalog and fetch any workflow, tool or company file through the growth.engineer MCP server.

What you need first

  • An AI agent that can add an MCP server or paste in a text file, such as Claude, Claude Code, ChatGPT, Codex or Cursor
  • Accounts and credentials for any vendor tool a workflow uses, since each company file names the credential it needs
  • For contributing: a GitHub account, Node 22+ and pnpm 11 (corepack enable installs the pinned version)

Steps

  1. In Claude, open Settings, choose Connectors, click Add, then Add custom connector.
  2. Name it growth.engineer, paste https://www.growth.engineer/mcp and click Add.
  3. For Claude Code, run claude mcp add --transport http growth-engineer --scope user https://www.growth.engineer/mcp.
  4. For Codex, run codex mcp add growth-engineer --url https://www.growth.engineer/mcp.
  5. Ask the agent to search the catalog for a goal, such as funding signals, and to open the matching workflow with get.

Prompt for your agent

Use the growth-engineer MCP server at https://www.growth.engineer/mcp to search for workflows about <goal>. Return the title and key of each match and open the first one with get. Check that the returned file has a title, inputs and steps before you report back.

Caveat. The server is read-only for search and get, but the submit_feedback tool sends your text to the maintainers, so do not include private data in feedback.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page