Rampify

dev.rampifyPublished by rampify.devOfficial publisherv1.1.0Updated Nov 1, 2026

Turn your coding agent into a marketing agent: search data, specs to build, fixes verified by scan.

Overview

AI-generated overview

Remote MCP server that connects a coding agent to your site's SEO and search data, turning findings into specs the agent implements and later verifies.

What you can do
  • Crawl and scan your site for meta, schema, content and Core Web Vitals issues
  • Read Google Search Console performance and keyword data, research keywords and clusters
  • Generate titles, meta descriptions and JSON-LD
  • Create feature specs with tasks and linked commits, and track campaign status
  • Run research playbooks that test whether AI assistants name your brand
When to use it
Useful when you want a coding agent to handle SEO and content work end to end: auditing pages, researching keywords, writing specs, shipping fixes in the repo, and confirming them on the next scan.
Requirements
A remote server at rampify.dev; nothing to install. Sign-in is via OAuth, so no API keys are managed. Requires an MCP client such as Claude Code, Cursor, VS Code with Copilot, or claude.ai, and a Rampify account with a connected site and Google Search Console access.
Before you install
Signing in grants the server access to your site's Search Console data and lets it crawl your site. Specs and tasks are written into your account and commits are linked to them, so changes to your repo are made by your agent. Pricing is free to start but paid tiers exist; check the pricing page before relying on it.

Installation

In SourceWeft

  1. Open Rampify in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. 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.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/dev.rampify%2Frampify-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "rampify": {
      "type": "http",
      "url": "https://www.rampify.dev/api/mcp"
    }
  }
}

README

Rampify MCP Server

Turn your coding agent into a marketing agent. Rampify connects Claude Code, Cursor, GitHub Copilot, or any MCP client to your website's search data. It scans your site, writes what to fix or build as specs your agent ships, and confirms each fix on the next scan, across Google search and AI answers.

Website · Product · Docs · Connect

How it works

  1. Scan. Rampify crawls your site and reads your Google Search Console performance and keyword data.
  2. Spec. Each gap becomes a spec: the pages and files it affects, the tasks, and how to tell it's done.
  3. Ship. Your agent makes the change in your repo and links the commit to the spec.
  4. Verify. The next scan checks the fix and closes the spec, or reopens it if the problem comes back.

Why Rampify

  • Real data, built in. Keyword volumes (via DataForSEO), your Search Console performance, and a live crawl of your own site. No separate data servers to bolt on.
  • Specs, not suggestions. Findings arrive as work your agent can pick up, with the same paper trail as your engineering: tasks, commits, and a status you can trust.
  • Fixes are checked, not assumed. A spec is done when the next scan confirms it, not when someone says so.
  • Find your blind spots. Playbooks like the Category Visibility Check ask AI assistants the questions your buyers ask, show whether they name you, and file a spec for the biggest gap.

Connect

Rampify is a remote server at https://www.rampify.dev/api/mcp. Nothing to install or update, and you sign in with OAuth, so there are no API keys to manage.

Claude Code

bash
claude mcp add --transport http rampify https://www.rampify.dev/api/mcp

Cursor (.cursor/mcp.json), or any client that takes a URL

json
{  "mcpServers": {    "rampify": { "url": "https://www.rampify.dev/api/mcp" }  }}

VS Code and GitHub Copilot: install the Rampify extension. It connects Copilot in one click and shows your specs in the sidebar.

claude.ai: add a custom connector with the URL above.

Step-by-step for each client: Connecting guide →

Things to ask once you're connected

  • "Crawl my site and show me which pages are invisible when buyers ask AI assistants about my category."
  • "Research keywords for /pricing, then write the content spec."
  • "Audit the meta and schema on my top pages, and open a PR with the fixes."
  • "What should I work on next?"

What your agent can do

More than 50 tools: crawl and scan pages (meta, schema, content, Core Web Vitals), page-level intelligence, Search Console performance, keyword research and clusters, title, meta and JSON-LD generation, feature specs with tasks and linked commits, research playbooks, and campaign tracking. See the full tool catalog →.

Learn more

About this repo

This repo holds Rampify's public listing metadata: server.json for the official MCP Registry (dev.rampify/rampify-mcp), the Cursor plugin manifest (.cursor-plugin/, mcp.json), and glama.json. The server itself runs at rampify.dev.


Looking for the old @rampify/mcp-server npm package? It is deprecated in favor of the hosted remote server above (zero install, always current). Its source is in this repo's history, last at 9e160f0.

Source: README.md at commit 095f596

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

2
  1. v1.1.0LatestNov 1, 2026
  2. v1.0.0Sep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts