Skip to content
Back to search

growth-engineer

Open-source catalog of go-to-market tools and workflows, written as markdown files any agent can run. Includes a read-only MCP server.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/GetBrew/growth-engineer with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/GetBrew/growth-engineer'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/getbrew--growth-engineer/badge.svg)](/listings/getbrew--growth-engineer)

HTML

<a href="/listings/getbrew--growth-engineer"><img src="/api/listings/getbrew--growth-engineer/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 243 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <div align="center">
  2. <img src="https://cdn.growth.engineer/assets/2026/09/growth-engineer-home-e4cdffcb.webp" alt="The growth.engineer home page, with the card that connects Claude to the MCP server">
  3. <h1>growth.engineer</h1>
  4. **Go-to-market tools and workflows, written as files any agent can run.**
  5. An open-source catalog of go-to-market companies, the functions an agent can
  6. call on each one, and workflows that chain those functions into a result.
  7. Every entry is a markdown file in this repository.
  8. <p>
  9. <a href="https://www.growth.engineer"><b>growth.engineer</b></a> &nbsp;·&nbsp;
  10. <a href="#connect-your-agent">Connect your agent</a> &nbsp;·&nbsp;
  11. <a href="#contribute">Contribute</a> &nbsp;·&nbsp;
  12. <a href="#local-development">Develop</a>
  13. </p>
  14. <p>
  15. <a href="https://www.growth.engineer"><img alt="Live site" src="https://img.shields.io/website?url=https%3A%2F%2Fwww.growth.engineer&style=flat-square&label=growth.engineer&up_message=live&up_color=2ea44f"></a>
  16. <a href="https://github.com/GetBrew/growth-engineer/actions/workflows/ci.yml"><img alt="CI" src="https://img.shields.io/github/actions/workflow/status/GetBrew/growth-engineer/ci.yml?branch=main&style=flat-square&label=CI"></a>
  17. <img alt="MCP server with a read-only catalog" src="https://img.shields.io/badge/MCP-read--only_catalog-111?style=flat-square">
  18. <img alt="Built with Next.js" src="https://img.shields.io/badge/built_with-Next.js-111?style=flat-square&logo=nextdotjs&logoColor=white">
  19. <a href="LICENSE"><img alt="License: MIT" src="https://img.shields.io/badge/license-MIT-111?style=flat-square"></a>
  20. <a href="https://github.com/GetBrew/growth-engineer/stargazers"><img alt="GitHub stars" src="https://img.shields.io/github/stars/GetBrew/growth-engineer?style=flat-square"></a>
  21. </p>
  22. </div>
  23. ---
  24. ## What is this?
  25. Handing a go-to-market tool to an agent means digging through docs written for
  26. people: which key to create, which endpoint to call, whether there is an MCP
  27. server, what a call costs. And a growth play that works usually lives in
  28. someone's notes, where no agent can run it.
  29. growth.engineer writes both down as markdown files an agent can follow:
  30. | Entry | Example key | What the file holds |
  31. | --- | --- | --- |
  32. | **Company** | `apollo` | Who the company is and how an agent reaches it: MCP server, CLI or API, and the credential each one needs. |
  33. | **Tool** | `apollo/enrich-person` | One function an agent can call: the exact MCP tool, CLI command or API endpoint, and the docs page that names it. |
  34. | **Workflow** | `funding-signal-outbound` | Up to ten steps across tools that reach a result: the one motion it serves, the outcome the user gets, the inputs to ask for, how to set up each tool, and the steps. |
  35. Paste a workflow file into Claude, ChatGPT, Cursor or any other agent and it
  36. can run the play. The file tells the agent to ask before it sends a message,
  37. spends money or changes data.
  38. Facts come from each vendor's own documentation, and every tool links the page
  39. that documents its call.
  40. ---
  41. ## Connect your agent
  42. The site runs an MCP server at `https://www.growth.engineer/mcp`
  43. (Streamable HTTP, no sign-in). Its `search` tool finds workflows, tools and
  44. companies, and `get` returns a file; neither changes anything. A third tool,
  45. `submit_feedback`, sends a bug report, request or question to the
  46. maintainers. Every workflow is also an MCP prompt that
  47. takes the workflow's inputs as arguments, and three more prompts
  48. (`contribute-workflow`, `contribute-tool`, `contribute-company`) walk an agent
  49. through adding to the catalog.
  50. | Client | How to add it |
  51. | --- | --- |
  52. | Claude | Settings → Connectors → Add → Add custom connector. Name it growth.engineer, paste the URL and click Add. |
  53. | Claude Code | `claude mcp add --transport http growth-engineer --scope user https://www.growth.engineer/mcp` |
  54. | ChatGPT | Plugins in the sidebar → Add → Create MCP App. Paste the URL, pick No authentication, accept the warning and click Create. |
  55. | Codex | `codex mcp add growth-engineer --url https://www.growth.engineer/mcp` |
  56. | Cursor | In `~/.cursor/mcp.json`, add `"growth-engineer": { "url": "https://www.growth.engineer/mcp" }` under `mcpServers`. |
  57. ### Or fetch the files
  58. Every file is public. There is no key and no sign-in.
  59. | URL | Returns |
  60. | --- | --- |
  61. | `/workflows/<name>.md` | A workflow, ready to paste into an agent |
  62. | `/tools/<company>/<name>.md` | One tool |
  63. | `/companies/<handle>.md` | A company and its tools |
  64. | `/tags/<namespace>/<slug>.md` | Everything with a tag, such as `/tags/capability/enrich-contacts.md` |
  65. | `/llms.txt` | The catalog's definitions and an index of every file |
  66. | `/llms-full.txt` | Every company, tool and workflow file in one document |
  67. | `/sitemap.xml` | Every page, with the date it last changed |
  68. A company, tool or workflow page also returns its file to a request with
  69. `Accept: text/markdown`.
  70. ```bash
  71. # A workflow file
  72. curl https://www.growth.engineer/workflows/funding-signal-outbound.md
  73. # The same file, by content negotiation
  74. curl -H 'Accept: text/markdown' https://www.growth.engineer/workflows/funding-signal-outbound
  75. ```
  76. ---
  77. ## Contribute
  78. The catalog lives in this repository, and every addition or fix is a pull
  79. request.
  80. | To | Add or edit | Field reference | Agent skill |
  81. | --- | --- | --- | --- |
  82. | Share a workflow | `workflows/<name>.md` | [`workflows/README.md`](workflows/README.md) | [`add-workflow`](.agents/skills/add-workflow/SKILL.md) |
  83. | Add a company and its tools | `companies/<handle>/company.md` and `tools/<name>.md` | [`companies/README.md`](companies/README.md) | [`research-company`](.agents/skills/research-company/SKILL.md) |
  84. | Fix a fact | The file that states it | The same READMEs | |
  85. Check your work before you open the pull request. CI runs the same check.
  86. ```bash
  87. pnpm content:check # every problem in the catalog, each with its file
  88. ```
  89. [`CONTRIBUTING.md`](CONTRIBUTING.md) covers the few rules worth knowing first.
  90. ---
  91. ## How it works
  92. There is no backend and no database. At build time, a compiler in
  93. `lib/content/` reads every file, validates it against a strict schema and
  94. resolves every reference. One renderer turns each company, tool and workflow
  95. into the file agents fetch, and Next.js prerenders every page from the same
  96. data. Deploying the site publishes the catalog.
  97. ```
  98. companies/ workflows/ tags.yml
  99. │
  100. ▼
  101. lib/content/ read, validate, resolve, derive
  102. │
  103. ▼
  104. lib/catalog/render-markdown.ts one renderer, golden-tested
  105. │
  106. ├─▶ pages, prerendered at build
  107. ├─▶ .md files, /llms.txt, /llms-full.txt
  108. └─▶ /mcp, the MCP server
  109. ```
  110. The one runtime store is optional: an Upstash Redis that counts how often each
  111. workflow is copied, for its "Uses" and the Popular order. Without it, the
  112. counts are hidden. The footer's newsletter sign-up adds subscribers to Brew
  113. from a server action, with the Brew key kept on the server; without a key, it
  114. is hidden.
  115. Visits are measured with Vercel Web Analytics and Speed Insights, and AI
  116. crawlers and AI-referred visits with Notra. See
  117. [`docs/setup.md`](docs/setup.md#deploying-to-vercel).
  118. ---
  119. ## Project layout
  120. ```
  121. growth-engineer/
  122. ├─ companies/<handle>/ company.md and tools/<name>.md (logos live on the CDN)
  123. ├─ workflows/<name>.md one file per workflow
  124. ├─ tags.yml the tag vocabulary
  125. ├─ app/ Next.js routes: pages, .md files, /mcp, llms.txt, sitemap
  126. ├─ components/ layout, catalog lists, detail pages, UI primitives
  127. ├─ lib/
  128. │ ├─ content/ the build-time compiler
  129. │ ├─ catalog/ keys, the markdown renderer, search, loaders
  130. │ ├─ mcp/ the MCP server's tools and prompts
  131. │ ├─ seo/ metadata, structured data, llms.txt
  132. │ └─ usage/ the optional copy counter
  133. ├─ tests/ Vitest: golden files, the content suite, schema checks
  134. ├─ docs/ architecture, data model, file format, setup
  135. └─ .agents/skills/ add-workflow, research-company
  136. ```
  137. ---
  138. ## Local development
  139. **Prerequisites:** Node 22+ and pnpm 11 (`corepack enable` installs the pinned
  140. version).
  141. ```bash
  142. pnpm install
  143. pnpm dev # http://localhost:3000
  144. ```
  145. Edits to `companies/`, `workflows/` and `tags.yml` show on the next refresh.
  146. Add `.md` to a company, tool or workflow URL to see the file an agent gets.
  147. Nothing needs configuring. [`.env.example`](.env.example) lists the optional
  148. variables:
  149. | Variable | Used for |
  150. | --- | --- |
  151. | `NEXT_PUBLIC_SITE_URL` | The origin printed in `/llms.txt` and page metadata. On Vercel it defaults to the deployment's hostname. |
  152. | `KV_REST_API_URL`, `KV_REST_API_TOKEN`, `KV_REST_API_READ_ONLY_TOKEN` | The copy counter. Without them, the counts are hidden. |
  153. | `GITHUB_TOKEN` | The star count in the header. Without it, GitHub allows 60 unauthenticated requests an hour. |
  154. | `NOTRA_GEO_TOKEN` | AI-traffic analytics: the proxy reports AI crawlers and AI-referred visits to Notra. Without it, nothing is sent. |
  155. | `BREW_API_KEY`, `BREW_BRAND_ID`, `BREW_WELCOME_TRIGGER_ID` | The footer's newsletter sign-up, sent to Brew, and the trigger whose automation sends the welcome email. Without a key, the sign-up is hidden; without a trigger, no welcome is sent. |
  156. ### Scripts
  157. | Script | Does |
  158. | --- | --- |
  159. | `pnpm dev` | Starts the dev server |
  160. | `pnpm content:check` | Parses, validates and renders the whole catalog |
  161. | `pnpm check` | Biome and a fast typecheck |
  162. | `pnpm test:run` | The unit suite, including the content checks |
  163. | `pnpm tsc` / `pnpm lint` | The full typecheck and lint |
  164. | `pnpm build` | Production build |
  165. | `pnpm validate` | Lint, typecheck and tests together |
  166. | `pnpm hygiene` | Docs links, the content tree, unused code, duplicate dependencies |
  167. Heavy commands wait their turn behind a lock, so several worktrees can run
  168. checks without running out of memory. See
  169. [`docs/maintainers/validation.md`](docs/maintainers/validation.md).
  170. ---
  171. ## Deploy
  172. The site runs on Vercel with the settings in [`vercel.json`](vercel.json).
  173. Every page and file is generated at build time, so merging to `main` publishes
  174. the catalog. [`docs/setup.md`](docs/setup.md) has the details.
  175. ---
  176. ## Docs
  177. - [`AGENTS.md`](AGENTS.md): the rules for changing the site, for people and coding agents
  178. - [`docs/architecture.md`](docs/architecture.md): the request path and what prerenders
  179. - [`docs/data-model.md`](docs/data-model.md): what the build derives and every rule it enforces
  180. - [`docs/markdown-files.md`](docs/markdown-files.md): the format of a rendered file
  181. - [`docs/vision.md`](docs/vision.md): why the catalog exists and where it is going
  182. ---
  183. ## License
  184. [MIT](LICENSE) © Brew

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.