Log inSubmit server
Rivalize logo

Rivalize

Cited competitive intelligence over MCP, covering competitor strategy, pricing, ads, reviews, hiring, momentum, reports, and evidence.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Rivalize

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "rivalize": {
      "command": "npx",
      "args": [
        "-y",
        "@rivalize/mcp"
      ],
      "env": {
        "RIVALIZE_API_KEY": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

Rivalize MCP server connects MCP clients to Rivalize's collected competitive intelligence, including company profiles, competitor tracking, reports, timelines, battlecards, and source evidence. It communicates over stdio through the `@rivalize/mcp` package and returns dated, sourced data for an assistant to analyze. Reach for it when an agent needs structured competitor research or access to an existing Rivalize account. Reads are enabled by default; competitor additions, report runs, and agent-slot changes require explicit write access.

Use cases

  • Teardown a competitor's positioning, pricing, ads, reviews, and momentum
  • Search Rivalize's company universe for comparable businesses
  • Review cited evidence and source freshness before preparing market analysis
  • Track competitor moves across product, pricing, hiring, funding, and social activity
  • Generate and monitor a credit-consuming competitive report

Key features

  • Cited competitor teardowns with refresh dates
  • Company-universe search and profiles
  • Reports, timelines, landscapes, and freshness data
  • Source evidence with URLs and read dates
  • Optional write tools for competitors, reports, and Agent slots
  • Agent-plan raw collection data grouped by module

Tools19

What Rivalize lets your agent do. Expand a tool for its parameters.

Self-reported~712 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

6/6 checks healthy over the last 21d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 4d ago via OSV.dev · @rivalize/mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

npm downloads1kPackage downloads in the last 30 days.
Last commit3d agoMost recent push to the default branch.
Tools exposed19Callable tools this server registers over MCP.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How Rivalize works

What Rivalize does

Rivalize MCP server gives an MCP-compatible assistant access to Rivalize competitive intelligence. It covers competitor positioning, pricing, features, advertising, SEO and social activity, reviews, funding, hiring, rankings, signals, and momentum. Results include collection or refresh dates and, where available, source URLs and the facts those sources support.

The server can work with two kinds of Rivalize data. Account tools expose projects, tracked competitors, reports, strategic timelines, competitive landscapes, freshness details, evidence, and cited battlecards. Universe tools search Rivalize's cross-customer collection of companies and retrieve a profile for a selected domain. The service also supports an Agent plan workflow in which Rivalize collects raw competitor data and the connected assistant performs the analysis.

How it works

The package runs as an MCP process over stdin and stdout. Configure an MCP client to launch npx -y @rivalize/mcp, then provide a Rivalize API key. Account-oriented calls generally use a project ID, report ID, or competitor ID obtained from an earlier listing call; domain-based tools can inspect a company directly.

Most operations read stored intelligence. run_report is different: it can start a paid report that consumes credits and typically takes about 10 to 20 minutes. It first returns a preview unless confirmation is supplied, after which get_report_status can be used to check progress. Report polling should be no more frequent than every 30 seconds.

Setup and configuration

Node.js 22 or newer is required. Create an API key in Rivalize under Settings → API Keys; keys begin with rk_live_. Set it as RIVALIZE_API_KEY in the MCP client's environment.

Claude Desktop, Cursor, and Cline use a stdio server entry with npx and the @rivalize/mcp package. Claude Code can add the same server from its command line. On Windows, clients that cannot launch npx directly can use cmd with /c npx -y @rivalize/mcp.

The optional RIVALIZE_MCP_ALLOW_WRITES setting enables write tools when set to 1, true, or yes. Without it, those tools are not registered with the client.

Tools and capabilities

  • Produce a one-call Markdown teardown covering positioning, pricing, ads, social activity, reviews, hiring, momentum, and weaknesses.
  • Search the Rivalize company universe or retrieve a full company profile.
  • List projects and tracked competitors, including momentum and threat information where available.
  • Read reports in full, by section, or by competitor without generating a new report.
  • Retrieve cited battlecards, evidence records, freshness data, strategic timelines, and competitive landscapes.
  • Add competitor URLs, start reports, and manage Agent-plan competitor slots when write access is enabled.
  • Inspect Agent-plan raw collection groups with their sources and collection timestamps.

Limitations and notes

Plan capabilities affect what the server can return. Battlecards require Pro, while report execution is for paid dashboard plans and uses credits. The Agent plan tracks three competitors at once, refreshes them every seven days, and permits one change per slot per calendar month. Its documented allowance is 500 API and MCP calls per day, with a 250-per-hour limit.

Write operations have side effects: adding competitors queues analysis, report runs spend credits, and changing Agent-plan slots queues a collection. The server does not perform analysis for the Agent plan; it supplies Rivalize's collected JSON and sources for the connected assistant to interpret.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Rivalize

Rivalize is an MCP server that connects AI clients to Rivalize's competitive-intelligence data. Its main tools provide competitor teardowns, company-universe searches, tracked-competitor intelligence, reports, timelines, landscapes, battlecards, freshness details, and cited evidence. It runs over stdio and uses a Rivalize API key for access.

Install it through your MCP client's stdio configuration with `npx -y @rivalize/mcp` and set `RIVALIZE_API_KEY`. Node.js 22 or newer is required. The package can be configured in Claude Desktop, Cursor, or Cline, or added to Claude Code with its MCP command.

Set `RIVALIZE_MCP_ALLOW_WRITES` to `1`, `true`, or `yes`. This registers `add_competitor`, `run_report`, and `set_agent_competitor`; without the setting, the server remains read-only from the client's perspective. These operations can queue analysis or collections, and reports consume credits.

Yes, Rivalize works with Cursor through a stdio MCP entry. Add `npx -y @rivalize/mcp` to `.cursor/mcp.json` for one project or `~/.cursor/mcp.json` for all projects, and provide the `RIVALIZE_API_KEY` environment variable.

Call `get_report_status` after starting a report with `run_report`. The status can indicate processing, completion, or that there are no competitors or rivals; while processing, poll no more often than every 30 seconds. `get_report` reads the resulting report.

Related MCP servers

All in Marketing All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewRivalize AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/rivalize?style=directory)](https://allmcps.com/mcp/rivalize)
HTML Embed
<a href="https://allmcps.com/mcp/rivalize"><img src="https://allmcps.com/api/badge/rivalize?style=directory" alt="Rivalize on AllMCPs" /></a>