RankReactor

io.github.flagman5v1.0.0Updated Sep 29, 2026

Hosted RankReactor MCP: SEO articles, UGC video, keywords, analytics, and site audits.

VerifiedStreamable HTTPWeb executableBusiness & CommerceData & AnalyticsMedia & Design

Overview

AI-generated overview

Lets an assistant read RankReactor SEO project metrics, list generated articles and videos, refresh metrics, and queue new SEO articles or UGC videos.

What it does
RankReactor is a hosted SEO product that reads a live website added as a project and tracks keywords, analytics, technical SEO, and site audits. Through its MCP server, an assistant can read project status and stored SEO metrics, list generated articles and videos, refresh metrics, and queue new SEO articles or UGC-style videos. Write actions such as queuing content ask for confirmation. The tool list is documented on the vendor's site rather than in this listing.
When to use it
Useful if you run one or more websites and want an assistant to check SEO performance, review generated content, or kick off new article or video generation without leaving the chat client. It fits set-and-forget SEO workflows where the site is already registered as a RankReactor project.
Requirements
A remote Streamable HTTP endpoint at the vendor's www host; no local runtime or package is needed. A RankReactor account is required (a Free plan exists), and sign-in uses OAuth 2.1 in the browser with dynamic client registration and PKCE S256. No API key belongs in client config, and no environment variables or headers are declared.
Before you install
Sign-in grants the assistant access to your RankReactor account data and lets it queue content, so review the confirmation prompts for write actions. Paid plans are billed at $39, $79, or $159 per month, and UGC video generation is limited to the higher tiers, so queuing videos can incur cost. The server is a third-party hosted service that reads your site and stores SEO metrics; check its privacy policy and terms before connecting.

Installation

In SourceWeft

  1. Open RankReactor in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "rankreactor": {
      "type": "http",
      "url": "https://www.rankreactor.ai/mcp"
    }
  }
}

README

RankReactor MCP

Config-only listing package for RankReactor's hosted Model Context Protocol server. This repository does not contain application or backend code.

RankReactor is a set-and-forget SEO product. You add a live website as a project. RankReactor reads the site, then can generate SEO articles and (on higher plans) UGC-style videos, and it tracks keywords, analytics, technical SEO, and a site audit.

MCP URL (use this exact host): https://www.rankreactor.ai/mcp

Always use www. The bare domain redirects and is not the MCP endpoint.

TransportStreamable HTTP
AuthOAuth 2.1 in the browser (dynamic client registration and CIMD, PKCE S256). No API key belongs in client config.
AccountA RankReactor account is required. A Free plan is available.
PrivacyPrivacy policy
TermsTerms of service
Support[email protected]

Plans: Free (1 lifetime article per project), Starter $39/mo, Pro $79/mo, Ultra $159/mo. UGC video is available on Pro and Ultra.

The hosted tools let an assistant read project status and stored SEO metrics, list generated articles and videos, refresh metrics, and queue new articles or UGC videos (write actions ask for confirmation). The current tool list is documented at Use RankReactor with your AI assistant.

Sign-in

Add the URL in your client. The client opens a browser so you can sign in to RankReactor and authorize the connection. Config files in this repo only contain the public URL.

Claude (claude.ai custom connector)

Remote MCP custom connectors work on Claude, Cowork, and Claude Desktop (Anthropic help). Free Claude accounts can add one custom connector.

One-click: Add RankReactor in Claude

Pro / Max

  1. Open Customize → Connectors.
  2. Click +, then Add custom connector.
  3. URL: https://www.rankreactor.ai/mcp
  4. Leave Advanced settings empty unless Claude asks for a client id.
  5. Click Add, then finish the browser sign-in.

Team / Enterprise: an Owner adds the URL under Organization settings → Connectors (Add → Custom → Web). Members then open Customize → Connectors and click Connect.

Enable the connector per conversation from + → Connectors.

Claude Code

From Claude Code MCP docs:

bash
claude mcp add --transport http rankreactor https://www.rankreactor.ai/mcp

That writes a local-scope entry. Use --scope user for every project, or --scope project to write .mcp.json in the repo.

Then run claude, type /mcp, select rankreactor, and Authenticate so the browser OAuth flow can complete.

Grok (grok.com)

From xAI Connectors:

  1. Open grok.com/connectors.
  2. Click New Connector, then Custom.
  3. Enter https://www.rankreactor.ai/mcp and finish any authentication prompt.

On Grok Business / Enterprise, a team admin may need to provision the connector first in console.x.ai (Grok Business → Connectors → Add Connector → Other).

A Grok Build marketplace listing is a separate follow-up (see the pull request for the catalog entry text). You can still point Grok Build at this repo once it is listed, or add the same URL as a custom connector.

Cursor

Install link (opens Cursor; MCP install links):

Add RankReactor in Cursor

Deeplink equivalent:

text
cursor://anysphere.cursor-deeplink/mcp/install?name=rankreactor&config=eyJ1cmwiOiJodHRwczovL3d3dy5yYW5rcmVhY3Rvci5haS9tY3AifQ==

Manual mcp.json (Cursor MCP docs): project file .cursor/mcp.json, or ~/.cursor/mcp.json for every project.

json
{  "mcpServers": {    "rankreactor": {      "url": "https://www.rankreactor.ai/mcp"    }  }}

This repo also ships a Cursor plugin manifest at .cursor-plugin/plugin.json plus mcp.json for Cursor Marketplace review, and a root .mcp.json for cursor.directory auto-detect.

Gemini CLI

From Gemini CLI extensions and the extension reference:

bash
gemini extensions install https://github.com/rankreactorai/rankreactorai-mcp

The root gemini-extension.json registers the remote server with httpUrl. After install, start a new CLI session. If the server needs sign-in, run /mcp auth rankreactor and finish in the browser.

You can also add the same server in ~/.gemini/settings.json without the extension:

json
{  "mcpServers": {    "rankreactor": {      "httpUrl": "https://www.rankreactor.ai/mcp"    }  }}

Use httpUrl (Streamable HTTP). Gemini CLI's url field is SSE.

VS Code (GitHub Copilot)

From VS Code MCP servers and the MCP configuration reference: workspace file .vscode/mcp.json, or MCP: Open User Configuration. VS Code uses a top-level servers object (not mcpServers).

json
{  "servers": {    "rankreactor": {      "type": "http",      "url": "https://www.rankreactor.ai/mcp"    }  }}

Or run MCP: Add Server from the Command Palette, choose HTTP, and paste the URL. Start the server, open Copilot Chat in Agent mode, and enable the RankReactor tools if asked.

Perplexity and Le Chat

Perplexity (custom remote connectors): add a custom connector with MCP server URL https://www.rankreactor.ai/mcp, authentication OAuth, transport Streamable HTTP.

Mistral Le Chat / Work (MCP connectors): Connectors → Add Connector → Custom MCP Connector, name rankreactor, server URL https://www.rankreactor.ai/mcp. The platform can detect OAuth 2.1 with dynamic client registration.

What this repo contains

PathPurpose
.cursor-plugin/plugin.jsonCursor Marketplace plugin manifest
mcp.jsonCursor plugin MCP config (discovered by default)
.mcp.jsoncursor.directory + Grok Build MCP config
.grok-plugin/plugin.jsonGrok Build plugin metadata
gemini-extension.jsonGemini CLI extension manifest (httpUrl)
GEMINI.mdGemini CLI extension context
server.jsonOfficial MCP Registry metadata (not published from this repo)
assets/logo.svgLogo fetched from rankreactor.ai/logo.svg
LICENSEMIT, copyright RankReactorAI

Client install docs on the product site: https://www.rankreactor.ai/docs/ai-assistants.

Source: README.md at commit 226afe5

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.0.0LatestSep 29, 2026