competlab-mcp-server

<p align="center"> <img src="./assets/banner.png" alt="CompetLab MCP Server — Competitive Intelligence for AI Agents" width="100%" /> </p>

CompetLab MCP Server

   


Competitive intelligence for AI agents — see how LLMs rank your brand.

More B2B buyers are asking AI before they Google. CompetLab monitors competitors across 5 dimensions — including AI Visibility, which tracks how ChatGPT, Claude, and Gemini mention and rank brands. This MCP server gives your AI agent access to all of it: dashboards, historical data, alerts, and strategic briefings. No other CI platform does this.

Supported Clients

Works with any MCP-compatible client:

• Claude Desktop / Claude Web
• Claude Code
• Cursor
• VS Code (Copilot)
• Windsurf
• Cline

Quick Start

Two ways to connect — pick the one that fits your setup:

| | Remote Server | Local Server | | ------------- | ---------------------------------------------------------- | ------------------------------------- | | Transport | Streamable HTTP | stdio | | Setup | Zero install — just add URL | npm install && npm run build | | Best for | Most users — Claude Code, Cursor, VS Code, Windsurf, Cline | Claude Desktop, Glama, or offline use |

Get your API key: app.competlab.com > Organization Settings > API Keys

Option 1: Remote Server (recommended)

Server URL: https://mcp.competlab.com/mcp Auth: API key via CL-API-Key header (or api_key query parameter)

Claude Code

claude mcp add --transport http \
  --header "CL-API-Key: YOUR_COMPETLAB_API_KEY" \
  competlab https://mcp.competlab.com/mcp

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "competlab": {
      "url": "https://mcp.competlab.com/mcp",
      "headers": {
        "CL-API-Key": "YOUR_COMPETLAB_API_KEY"
      }
    }
  }
}

VS Code

Add to .vscode/mcp.json:

{
  "inputs": [
    {
      "type": "promptString",
      "id": "competlab-api-key",
      "description": "CompetLab API Key (starts with cl_live_)",
      "password": true
    }
  ],
  "servers": {
    "competlab": {
      "type": "http",
      "url": "https://mcp.competlab.com/mcp",
      "headers": {
        "CL-API-Key": "${input:competlab-api-key}"
      }
    }
  }
}

Note: VS Code uses "servers" (not "mcpServers") and supports secure input prompts via ${input:id}.

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "competlab": {
      "serverUrl": "https://mcp.competlab.com/mcp",
      "headers": {
        "CL-API-Key": "YOUR_COMPETLAB_API_KEY"
      }
    }
  }
}

Note: Windsurf uses "serverUrl" (not "url").

Cline

Add to cline_mcp_settings.json (or configure via Cline UI > Installed > Advanced MCP Settings):

{
  "mcpServers": {
    "competlab": {
      "url": "https://mcp.competlab.com/mcp",
      "headers": {
        "CL-API-Key": "YOUR_COMPETLAB_API_KEY"
      },
      "disabled": false
    }
  }
}

Claude Desktop / Claude Web

Claude Desktop and Claude Web only support URL-based auth (no custom headers). Use the api_key query parameter:

Go to Settings > MCP and add the server with this URL:

https://mcp.competlab.com/mcp?api_key=YOUR_COMPETLAB_API_KEY

Option 2: Local Server (stdio)

Run the server locally via stdin/stdout. Useful for Claude Desktop, Glama, or environments that prefer stdio transport.

git clone https://github.com/competlab/competlab-mcp-server.git
cd competlab-mcp-server
npm install
npm run build

Claude Code

claude mcp add --transport stdio \
  --env COMPETLAB_API_KEY=YOUR_COMPETLAB_API_KEY \
  competlab node dist/index.js

Claude Desktop

Add to your Claude Desktop config (claude_desktop_config.json):

{
  "mcpServers": {
    "competlab": {
      "command": "node",
      "args": ["dist/index.js"],
      "cwd": "/path/to/competlab-mcp-server",
      "env": {
        "COMPETLAB_API_KEY": "YOUR_COMPETLAB_API_KEY"
      }
    }
  }
}

Generic stdio

COMPETLAB_API_KEY=YOUR_COMPETLAB_API_KEY node dist/index.js

The server reads JSON-RPC from stdin and writes responses to stdout.

See examples/ for ready-to-paste config files for each client.

What is CompetLab?

Competitive intelligence for the AI era. One platform, 5 dimensions, monitored automatically:

| Dimension | What It Tracks | | ----------------- | ----------------------------------------------------------------------------------------------------------------- | | Tech & Trust | Tech stacks, security headers (grade A-F), trust signals (24 signals in 4 categories), robots.txt AI bot blocking | | Content | Sitemap analysis, content categorization (11 categories), URL changelog, content gaps | | Positioning | Homepage messaging, value props, CTAs, target audience, differentiators | | Pricing | Plans, billing models, free tiers, enterprise pricing, gap analysis | | AI Visibility | How ChatGPT, Claude, and Gemini rank your brand vs competitors (AI Visibility Score 0-100) |

AI Visibility is what makes CompetLab unique — no other CI platform tracks how LLMs recommend brands in real time.

Start free trial (14 days, no credit card) | Learn more

Available Tools

11 groups. 33 tools. 30 are read-only; 3 are async-scan starters that create a scan record (start_tech_stack_scan, start_trust_signals_scan, start_agent_adoption_scan).

Projects & Competitors

| Tool | Description | | ------------------ | ----------------------------------------------------------------------------- | | list_projects | List all projects with status, competitor count, and last monitored timestamp | | get_project | Get project details with per-dimension monitoring freshness | | list_competitors | List all monitored competitors (includes your own domain for comparison) | | get_competitor | Get competitor details including monitored page URLs |

Tech & Trust Profile

| Tool | Description | | --------------------------- | ----------------------------------------------------------------------------- | | get_tech_trust_dashboard | Latest security headers, trust signals, tech stacks, DNS, robots.txt analysis | | get_tech_trust_history | Paginated history of monitoring runs | | get_tech_trust_run_detail | Full competitor-by-competitor data for a specific run |

Content Intelligence

| Tool | Description | | ------------------------ | -------------------------------------------------------------------------------------------- | | get_content_dashboard | Latest sitemap analysis, content categorization, strategic URLs, gap analysis | | get_content_history | Paginated history of monitoring runs | | get_content_run_detail | Full data for a specific content run | | get_content_changelog | Detected URL changes over time (new, removed, moved) — filterable by competitor and category |

Positioning

| Tool | Description | | ---------------------------- | ---------------------------------------------------------------------- | | get_positioning_dashboard | Latest homepage messaging, value props, CTAs, target audience analysis | | get_positioning_history | Paginated history of monitoring runs | | get_positioning_run_detail | Full data for a specific positioning run |

Pricing Intelligence

| Tool | Description | | ------------------------ | ---------------------------------------------------------------------- | | get_pricing_dashboard | Latest pricing plans, billing options, market statistics, gap analysis | | get_pricing_history | Paginated history of monitoring runs | | get_pricing_run_detail | Full data for a specific pricing run |

AI Visibility

| Tool | Description | | -------------------------------- | ------------------------------------------------------------------------------------------------ | | get_ai_visibility_dashboard | AI Visibility Scores, mention rates, per-provider breakdowns (OpenAI, Claude, Gemini) | | get_ai_visibility_history | Paginated history of AI visibility checks | | get_ai_visibility_check_detail | Full detail for a specific check with per-competitor rankings | | get_ai_visibility_trend | Track how LLM brand perception changes over time (up to 200 data points, filterable by provider) |

Strategic Briefing, Alerts & Schedules

| Tool | Description | | ------------------------ | --------------------------------------------------------------------------------------------- | | get_briefing | Synthesized competitive briefing across all dimensions — what changed, what it means, what to do. Defaults to the hub digest; pass sections to drill into deep-<dimension> slots | | list_alerts | Competitive change alerts — filterable by dimension, severity, and competitor | | list_schedules | Monitoring schedules for all dimensions with enabled/disabled status and intervals |

Free Tools (no project setup required)

Run these against any public domain — no projectId needed. The sync tools return immediately; the async scans return a scanId you poll every 5–10 seconds.

| Tool | Description | | --------------------------- | ------------------------------------------------------------------------------------------------------------------------ | | check_sitemap | Live sitemap analysis — URL discovery, categorization by section, content gaps and depth | | check_ai_crawlers | Live AI-crawler access check via robots.txt + meta tags — GPTBot, ClaudeBot, Google-Extended, PerplexityBot, and others | | start_tech_stack_scan | Start async tech-stack detection (117 rules: tech / growth / engagement). Returns scanId | | get_tech_stack_scan | Poll a tech-stack scan by scanId — returns detected technologies with confidence scores when complete | | start_trust_signals_scan | Start async trust-signals analysis (34 signals across enterprise readiness, validation, social proof, authority, risk). Returns scanId | | get_trust_signals_scan | Poll a trust-signals scan by scanId — returns per-signal verdicts and tier verdict when complete | | start_agent_adoption_scan | Start async Agent-Adoption Check (25 checks: discoverability, access, readability, agent endpoints). Returns scanId | | get_agent_adoption_scan | Poll an Agent-Adoption Check by scanId — returns complete results when finished | | fetch_url | Fetch any URL with JS rendering and bot-protection handling. Returns body, headers, cleanStats. Optional cleanHtml strips noise for LLM token-cost savings. 60 req/min per API key |

All paginated tools accept page and limit parameters. Check pagination.hasMore in the response to fetch more pages.

Example Prompts

Once connected, try asking your AI agent:

• "What changed on my competitors' pricing pages this week?"
• "How does ChatGPT rank my brand vs competitors for [industry query]?"
• "Show me the strategic briefing — what should I fix first?"
• "Compare content strategies across all my tracked competitors"
• "What critical alerts fired in the last 7 days?"
• "Track how my AI visibility score changed over the last 3 months"
• "Which competitors have better security headers than us?"
• "Run a tech-stack scan on stripe.com — what are they using?"
• "Check if openai.com blocks AI crawlers in their robots.txt"
• "Fetch g2.com/some-listing with cleanHtml and summarize the page"

See examples/prompts.md for more prompts organized by use case.

Authentication

Getting an API key

1. Sign up at app.competlab.com/register (free 14-day trial, no credit card)
2. Go to Organization Settings > API Keys
3. Create a new key — it starts with cl_live_

Two authentication methods

| Method | When to use | Example | | ----------------------------- | ----------------------------------------------------------------- | ------------------------- | | CL-API-Key header | Claude Code, Cursor, VS Code, Windsurf, Cline | CL-API-Key: cl_live_... | | api_key query parameter | Claude Desktop, Claude Web, clients without custom header support | ?api_key=cl_live_... |

One API key covers your entire organization. Most tools are read-only; the three start_*_scan tools create scan records under your account (no edits to existing data). The fetch_url tool is rate-limited at 60 req/min per API key (tighter than the 1000/min default for other free tools).

Pricing

MCP access is included with every CompetLab subscription ($99/mo). Free trial includes full MCP access.

Troubleshooting

| Issue | Fix | | ---------------------------- | ---------------------------------------------------------------------------------------------------- | | Connection refused / timeout | Verify the URL is exactly https://mcp.competlab.com/mcp with no trailing slash | | api_key_missing error | Ensure you're passing the key as CL-API-Key header (remote) or COMPETLAB_API_KEY env var (stdio) | | api_key_invalid error | Keys must start with cl_live_ and be exactly 40 characters | | Transport not supported | Use the remote HTTP server, or switch to the local stdio server |

Links

• MCP Server Documentation
• REST API Reference
• TypeScript SDK (npm install @competlab/sdk)
• Privacy Policy
• Start Free Trial

Support

• Bug reports: GitHub Issues
• Email: support@competlab.com
• Documentation: competlab.com/developers

License

MIT (covers documentation and configs in this repo) — see LICENSE

The CompetLab MCP server and platform are commercial software. See competlab.com/terms-and-conditions.

---

Built by the CompetLab team. Competitive intelligence for the AI era.