list_projectsLABSCO SUMMARY
The unusual dimension is what the models say about you.
Pricing pages and tech stacks are tracked by plenty of tools. AI visibility — asking the major assistants an industry question and recording which brands they name and in what order — is the reason to look here, and the trend tool is what makes it more than a snapshot. Note that 30 of the 33 tools only read; the three that write just start a scan.
What it is
A hosted competitive-intelligence service with 33 tools. Five dimensions are monitored on a schedule — tech and trust, content, positioning, pricing, and AI visibility — and each has a current dashboard, a paginated history, and the full detail of any single run.
What you get
- get_pricing_dashboard, get_positioning_dashboard, get_content_dashboard and get_tech_trust_dashboard — the current state of each dimension
- The matching history and run-detail tools, so a change can be traced to the run that found it
- get_ai_visibility_dashboard and get_ai_visibility_trend — how the major models mention and rank brands, over time and by provider
- get_content_changelog for URLs that appeared, moved or disappeared on a competitor's site
- get_briefing, which synthesises all five dimensions into what changed, what it means and what to do
- list_alerts and list_schedules for what fired and what is being watched
- check_sitemap and check_ai_crawlers against any public domain, with no project set up
- start_tech_stack_scan, start_trust_signals_scan and start_agent_adoption_scan — the three tools that write anything; each returns a scan id you poll
- fetch_url with JS rendering and bot-protection handling, and an option to strip page noise before it reaches the model
Requirements
A CompetLab account and an API key from Organization Settings. The hosted endpoint is the normal path and needs no install — the key travels in the CL-API-Key header, or as a query parameter for clients that cannot set headers. There is a stdio build for clients that prefer it, which reads the key from COMPETLAB_API_KEY. The free tools run against any public domain without a project.
Setup effort
One command plus a key — claude mcp add --transport http --header "CL-API-Key: <YOUR_COMPETLAB_API_KEY>" competlab https://mcp.competlab.com/mcp, then supply credentials
USE CASES
Finding out what competitors changed this week
Read the synthesised briefing rather than four dashboards, then drill into the dimension that moved.
Watching a competitor's pricing page for movement
Compare the current plans against the run history to see when a tier or a price changed.
Checking whether assistants recommend you
Read the visibility scores per provider, then track them over time rather than reacting to one check.
Spotting a content push before it lands
Read the URL changelog for pages that appeared or moved, filtered by competitor and category.
Sizing up a domain you do not track yet
Run the free sitemap and AI-crawler checks against it without setting up a project.
Seeing what a site is built on
Start the tech-stack scan, then poll the scan id until the detected technologies come back with confidence scores.
Reading a page that blocks ordinary fetching
Pull it with JS rendering and bot handling, and strip the noise before it reaches the model.
33 tools
Listed in project docs. Your client may show a different list.
get_projectlist_competitorsget_competitorget_tech_trust_dashboardget_tech_trust_historyget_tech_trust_run_detailget_content_dashboardget_content_historyget_content_run_detailget_content_changelogget_positioning_dashboardget_positioning_historyget_positioning_run_detailget_pricing_dashboardget_pricing_historyget_pricing_run_detailget_ai_visibility_dashboardget_ai_visibility_historyget_ai_visibility_check_detailget_ai_visibility_trendget_briefinglist_alertslist_schedulescheck_sitemapcheck_ai_crawlersstart_tech_stack_scanget_tech_stack_scanstart_trust_signals_scanget_trust_signals_scanstart_agent_adoption_scanget_agent_adoption_scanfetch_urlBEFORE YOU INSTALL
What to know first
Tools you get
33 tools named in the project's documentation.
Requires
A client that can reach a remote MCP server over HTTP
Where it runs
Of the 9 documented setups, 2 run the server on your machine and 7 connect to a hosted endpoint.
INSTALLATION
Connect your client
Server setup
Build from source
git clone https://github.com/competlab/competlab-mcp-server.git
cd competlab-mcp-server
npm install
npm run buildclaude mcp add
Claude Code — remote
claude mcp add --transport http --header "CL-API-Key: <YOUR_COMPETLAB_API_KEY>" competlab https://mcp.competlab.com/mcpHosted endpoint
https://mcp.competlab.com/mcpAdd this hosted endpoint to your MCP client using the credentials listed under Requirements.
MCP Clients
Cursor
{
"mcpServers": {
"competlab": {
"url": "https://mcp.competlab.com/mcp",
"headers": {
"CL-API-Key": "<YOUR_COMPETLAB_API_KEY>"
}
}
}
}VS Code
{
"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}"
}
}
}
}Windsurf
{
"mcpServers": {
"competlab": {
"serverUrl": "https://mcp.competlab.com/mcp",
"headers": {
"CL-API-Key": "<YOUR_COMPETLAB_API_KEY>"
}
}
}
}Cline
{
"mcpServers": {
"competlab": {
"type": "streamableHttp",
"url": "https://mcp.competlab.com/mcp",
"headers": {
"CL-API-Key": "<YOUR_COMPETLAB_API_KEY>"
},
"disabled": false
}
}
}Claude.ai, Claude Desktop
https://mcp.competlab.com/mcp?api_key=<YOUR_COMPETLAB_API_KEY>Claude Code — local stdio
claude mcp add --env COMPETLAB_API_KEY=<YOUR_COMPETLAB_API_KEY> --transport stdio competlab -- node <YOUR_PATH_TO_COMPETLAB_MCP_SERVER>/dist/index.jsClaude Desktop — local stdio
{
"mcpServers": {
"competlab": {
"command": "node",
"args": [
"<YOUR_PATH_TO_COMPETLAB_MCP_SERVER>/dist/index.js"
],
"env": {
"COMPETLAB_API_KEY": "<YOUR_COMPETLAB_API_KEY>"
}
}
}
}