Skip to content
Back to search

rankbyai

MarketplaceWorks with Claude CodeGitHub

RankbyAI: AI visibility software you pay for once. AI + Google Maps grid tracking for local businesses, on your own API keys.

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 21 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/meestierolff/rankbyai 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/meestierolff/rankbyai'

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/meestierolff--rankbyai/badge.svg)](/listings/meestierolff--rankbyai)

HTML

<a href="/listings/meestierolff--rankbyai"><img src="/api/listings/meestierolff--rankbyai/badge.svg" alt="findsafeskills safety rating" /></a>

Install

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.

.claude-plugin/marketplace.json · Manifest · 17 lines
  1. {
  2. "name": "rankbyai",
  3. "owner": {
  4. "name": "RankbyAI",
  5. "url": "https://rankbyai.live"
  6. },
  7. "metadata": {
  8. "description": "The RankbyAI plugin: AI and Google Maps visibility for local businesses, as an MCP server plus a skill."
  9. },
  10. "plugins": [
  11. {
  12. "name": "rankbyai",
  13. "source": "./plugins/rankbyai",
  14. "description": "Check whether ChatGPT, Perplexity, Gemini and Google Maps recommend a local business, point by point on a map grid, and turn the results into a ranked fix plan."
  15. }
  16. ]
  17. }
README.md · README · 161 lines
  1. # RankbyAI
  2. **AI visibility software you pay for once.** RankbyAI shows whether ChatGPT, Perplexity and Gemini recommend a local business for "best {service} near me" prompts, point by point across a map grid, next to its Google Maps rank on the same grid. Scans run on the user's own API keys at cost, or on optional included-scan packs.
  3. Live site: https://rankbyai.live · Built in public for the Ship or Die $100K Hackathon (16 Nov – 16 Dec 2026).
  4. > Not affiliated with or endorsed by OpenAI, Perplexity, Google or DataForSEO. RankbyAI is not the first or only AI visibility grid tool; Local Falcon and BrightLocal also offer one. The difference is how you pay.
  5. ## MCP server
  6. RankbyAI is a remote [Model Context Protocol](https://modelcontextprotocol.io) server, so AI assistants can add businesses, run AI and Google Maps grids, audit a business and build its Fix Kit for the user.
  7. - **Endpoint:** `https://rankbyai.live/api/mcp`, Streamable HTTP, stateless (POST only; no `Mcp-Session-Id`, so `GET` answers `405`).
  8. - **Tools:** 20, plus one prompt, `fix_plan`. Every tool that costs money returns its estimate first and runs only with `confirm: true`.
  9. - **Limit:** 60 requests a minute per API key or connected app.
  10. ### Authentication
  11. Both ways use `Authorization: Bearer …`.
  12. 1. **OAuth 2.1 sign-in (for Claude, ChatGPT, Cursor, Gemini CLI and other MCP clients).** The client needs only the URL. A request without a token gets `401` with `WWW-Authenticate: Bearer resource_metadata="https://rankbyai.live/.well-known/oauth-protected-resource/api/mcp", scope="mcp"`. The client reads the [protected resource metadata](https://rankbyai.live/.well-known/oauth-protected-resource) and the [authorization server metadata](https://rankbyai.live/.well-known/oauth-authorization-server), and registers itself with dynamic client registration (`/oauth/register`) or a Client ID Metadata Document. It then opens `/oauth/authorize`, where the user signs in with their RankbyAI (Google) account and the workspace owner approves the app.
  13. - Authorization code with PKCE `S256` only, and `iss` on every authorization response (RFC 9207).
  14. - The one scope is `mcp`. Tokens are bound to `https://rankbyai.live/api/mcp` (RFC 8707) and to the approved workspace.
  15. - Access tokens last one hour. Refresh tokens last 30 days and rotate on every use; replaying an old one revokes its family.
  16. - Revocation is at `/oauth/revoke` (RFC 7009). Owners also see and disconnect apps under **API & MCP** in the app.
  17. - OAuth tokens never open the REST API, and no token or response ever contains the user's stored vendor API keys.
  18. - The OAuth endpoints are live once the deployment has `MCP_OAUTH=1` (after migration `db/migrations/0012_mcp_oauth.sql`).
  19. 2. **API key (for scripts and clients without sign-in).** Create one in the app under **API & MCP**, and send it as `Authorization: Bearer rbai_live_…`. These are the same keys as the REST API (see [/docs/api](https://rankbyai.live/docs/api)).
  20. ### Tools
  21. | Tool | What it does | Hints |
  22. |---|---|---|
  23. | `list_businesses` | List the workspace's businesses | read-only |
  24. | `add_business` | Track a business (Google Maps lookup needs `confirm`) | adds, open world |
  25. | `update_business` | Change name, address, client, map point or language | destructive (overwrites) |
  26. | `delete_business` | Delete a business with its scans, audits and reports | destructive |
  27. | `estimate_scan` | Cost of an AI or Maps scan, without running it | read-only |
  28. | `run_ai_scan` | Ask ChatGPT, Perplexity and Gemini at every grid point (paid, `confirm`) | adds, open world |
  29. | `run_maps_scan` | Google Maps rank at every grid point (paid, `confirm`) | adds, open world |
  30. | `list_scans`, `get_scan`, `compare_scans` | Scans, their points and answers, and before/after comparisons | read-only |
  31. | `run_audit` | Local AI Audit against the map pack (paid, `confirm`) | adds, open world |
  32. | `list_audits`, `get_audit` | Audits, findings P0 to P3 with evidence | read-only |
  33. | `get_fix_kit` | Copy-ready fixes for a finished audit (built once) | adds, idempotent, open world |
  34. | `create_prospect_batch` | Prospect reports for agencies (paid, `confirm`) | adds, open world |
  35. | `list_prospect_batches`, `get_prospect_batch` | Prospect batches and their report links | read-only |
  36. | `get_branding`, `update_branding` | White-label branding on reports | read-only / destructive (overwrites) |
  37. | `get_usage` | This month's own-key spend and credits left | read-only |
  38. Every tool carries MCP annotations: `title`, `readOnlyHint`, `destructiveHint` and `openWorldHint`, plus `idempotentHint` on the tools that change something. The source of truth is `MCP_TOOL_HINTS` in `src/lib/api-v1/mcp-tools.ts`.
  39. ### Connect a client
  40. **Claude (claude.ai and Claude Desktop):** Settings → Connectors → Add custom connector, paste `https://rankbyai.live/api/mcp`, then Connect and sign in.
  41. **ChatGPT:** create an app or connector in developer mode with the URL `https://rankbyai.live/api/mcp` and OAuth authentication; ChatGPT registers itself and opens the RankbyAI sign-in.
  42. **Cursor** (`~/.cursor/mcp.json`; Cursor signs in with OAuth by itself):
  43. ```json
  44. {
  45. "mcpServers": {
  46. "rankbyai": { "url": "https://rankbyai.live/api/mcp" }
  47. }
  48. }
  49. ```
  50. With an API key instead:
  51. ```json
  52. {
  53. "mcpServers": {
  54. "rankbyai": { "url": "https://rankbyai.live/api/mcp", "headers": { "Authorization": "Bearer rbai_live_YOUR_KEY" } }
  55. }
  56. }
  57. ```
  58. **Claude Code:**
  59. ```bash
  60. claude mcp add --transport http rankbyai https://rankbyai.live/api/mcp # then /mcp to sign in
  61. claude mcp add --transport http rankbyai https://rankbyai.live/api/mcp \
  62. --header "Authorization: Bearer rbai_live_YOUR_KEY" # or with an API key
  63. ```
  64. **Gemini CLI:** `gemini extensions install https://github.com/meestierolff/rankbyai` (the manifest is [`gemini-extension.json`](gemini-extension.json)).
  65. **Grok:** at grok.com/connectors → New Connector → Custom, paste `https://rankbyai.live/api/mcp`. Through the xAI API, add it as a remote MCP tool with an API key:
  66. ```json
  67. { "type": "mcp", "server_url": "https://rankbyai.live/api/mcp", "server_label": "rankbyai", "authorization": "rbai_live_YOUR_KEY" }
  68. ```
  69. **Claude Code and Codex plugin** (MCP server plus the RankbyAI skill, in [`plugins/rankbyai`](plugins/rankbyai)):
  70. ```bash
  71. claude plugin marketplace add meestierolff/rankbyai && claude plugin install rankbyai@rankbyai
  72. codex plugin marketplace add meestierolff/rankbyai
  73. ```
  74. ### Directory listings
  75. - [`server.json`](server.json): the entry for the official MCP Registry, named `live.rankbyai/rankbyai` (domain-verified: the `v=MCPv1` TXT record on rankbyai.live), with one `streamable-http` remote. To publish: `mcp-publisher login dns --domain rankbyai.live --private-key <hex key>`, then `mcp-publisher publish`.
  76. - [`gemini-extension.json`](gemini-extension.json): the Gemini CLI extension. The gallery lists repositories that carry the `gemini-cli-extension` topic.
  77. - [`plugins/rankbyai`](plugins/rankbyai): the plugin for Claude Code, the Claude directory and Grok Build (`.claude-plugin/plugin.json`, `.mcp.json`, `skills/rankbyai/SKILL.md`). Marketplaces: [`.claude-plugin/marketplace.json`](.claude-plugin/marketplace.json) (Claude Code) and [`.agents/plugins/marketplace.json`](.agents/plugins/marketplace.json) (Codex).
  78. - [`plugins/openai`](plugins/openai): the OpenAI plugin directory manifests; `node scripts/build-openai-plugin.mjs` builds the ZIP to upload; `--demo-url <recording>` overrides the walkthrough URL in `plugin.json`. The walkthrough (the 5 positive and 3 negative test cases in Codex with the reviewer account) is [public/review/rankbyai-openai-review.mp4](https://rankbyai.live/review/rankbyai-openai-review.mp4). Domain verification is served at `/.well-known/openai-apps-challenge` from `OPENAI_APPS_CHALLENGE`.
  79. - Reviewer access: directory reviewers sign in with a password at `/login/reviewer` (`REVIEWER_LOGIN_EMAILS`, see [docs/SETUP.md](docs/SETUP.md)); keep that account and its workspace working while a listing is in review.
  80. - Submitted on 20 Nov 2026: the Claude connector directory, the Grok Bot marketplace, Grok Build ([xai-org/plugin-marketplace#2200](https://github.com/xai-org/plugin-marketplace/pull/2200)) and the OpenAI plugin directory (ChatGPT and Codex). Also on 20 Nov 2026: the official MCP Registry (Glama imports from it), cursor.directory (security scan pending), the Docker MCP Catalog ([docker/mcp-registry#7456](https://github.com/docker/mcp-registry/pull/7456)) and the Gemini CLI gallery (`gemini-cli-extension` repo topic).
  81. - Support: [rankbyai.live/support](https://rankbyai.live/support) (mees@rankbyai.live). Privacy: [/privacy](https://rankbyai.live/privacy). Terms: [/terms](https://rankbyai.live/terms).
  82. ## Stack
  83. - Next.js 16 (App Router, Cache Components, TypeScript strict), Tailwind CSS v4, shadcn/ui
  84. - Neon (Postgres, Neon Auth with Google sign-in, Data API, Object Storage) with row level security on every table
  85. - Stripe Checkout (one-time payments, Stripe Tax)
  86. - Official APIs only: DataForSEO (Google Maps results), OpenAI, Perplexity, Gemini
  87. - Vitest for unit and database tests
  88. ## Repository map
  89. | Path | What it holds |
  90. |---|---|
  91. | `design/` | Design handoff (source of truth for the look) |
  92. | `src/styles/tokens.css`, `src/app/globals.css` | Design tokens and the Tailwind theme |
  93. | `src/components/ui`, `src/components/brand` | shadcn/ui primitives and the brand component library |
  94. | `src/components/marketing`, `src/app/(marketing)` | Marketing site |
  95. | `src/app/app`, `src/components/app` | The dashboard |
  96. | `src/lib/pricing-constants.ts`, `src/lib/cost` | Vendor price constants and cost maths (one source for site and app) |
  97. | `src/lib/ladder.ts`, `src/lib/checkout.ts`, `src/lib/stripe-webhook.ts` | Lifetime price ladder, checkout, webhook |
  98. | `db/migrations` | Schema, RLS policies, functions (plain Postgres SQL) |
  99. | `db/local`, `scripts/db.mjs` | Local database stack (Postgres + PostgREST in Docker) and the migration runner |
  100. | `src/lib/db` | Database clients and the short-lived tokens the server signs for the Data API |
  101. | `src/lib/api-v1`, `src/app/api/mcp` | REST API, OpenAPI document and the MCP server (tools, annotations) |
  102. | `src/lib/oauth`, `src/app/oauth`, `src/app/.well-known` | OAuth 2.1 authorization server for the MCP server: metadata, registration, consent, tokens |
  103. | `tests/unit`, `tests/db` | Unit tests and tests that run against a real local Postgres |
  104. | `docs/` | Setup, progress log, vendor API notes |
  105. ## Run it locally
  106. ```bash
  107. pnpm install
  108. cp .env.example .env.local
  109. pnpm db:setup # local Postgres + PostgREST (Docker): creates a signing key, writes the database lines to .env.local, applies db/migrations
  110. pnpm dev # http://localhost:3100
  111. ```
  112. ```bash
  113. pnpm test # unit + database tests (local database only)
  114. pnpm build && pnpm check:secrets # production build, then scan client bundles for secrets
  115. ```
  116. See [docs/SETUP.md](docs/SETUP.md) for every environment variable and the hosted setup, and [docs/PROGRESS.md](docs/PROGRESS.md) for what is built and verified.
  117. ## Rules this codebase keeps
  118. - Row level security on every table; an automated test proves it.
  119. - API keys are encrypted with AES-256-GCM, write-only, and used only on the server.
  120. - No scraping. Official APIs only. Every AI result carries the "AI answers vary" disclaimer.
  121. - No invented numbers: demo content is labelled "Sample data", estimates are labelled as estimates, competitor prices carry their source date.
  122. - No fake urgency: the price follows a public sales counter, never a timer.
  123. - Every sale is priced above its delivery cost (asserted in `tests/unit/pricing.test.ts`).

Ratings and comments

Sign in to rate this skill.

Sign in

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