MCP server

The Model Context Protocol server for Clamp. Read-only by default, write actions on Pro, works with any MCP client.

Setup

VS Code / Copilot

Add to .vscode/mcp.json in your project:

.vscode/mcp.json
{
  "servers": {
    "clamp": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@clamp-sh/mcp"],
      "env": {
        "CLAMP_API_KEY": "sk_proj..."
      }
    }
  }
}

Claude Code

terminal
claude mcp add clamp -- npx -y @clamp-sh/mcp
export CLAMP_API_KEY="sk_proj..."

Claude Desktop

Add to claude_desktop_config.json:

claude_desktop_config.json
{
  "mcpServers": {
    "clamp": {
      "command": "npx",
      "args": ["-y", "@clamp-sh/mcp"],
      "env": {
        "CLAMP_API_KEY": "sk_proj..."
      }
    }
  }
}

Cursor

Add to .cursor/mcp.json:

.cursor/mcp.json
{
  "mcpServers": {
    "clamp": {
      "command": "npx",
      "args": ["-y", "@clamp-sh/mcp"],
      "env": {
        "CLAMP_API_KEY": "sk_proj..."
      }
    }
  }
}

API key

Get your API key from the Clamp dashboard under Settings → API Keys. Keys are scoped to a project and start with sk_proj. The MCP server auto-detects which project to query from the key — no project ID needed.

Tools

Free (all plans)

ToolWhat it does
get_overviewPageviews, visitors, sessions, bounce rate, avg duration. Period comparison included.
get_top_pagesMost visited pages ranked by pageviews.
get_top_referrersTraffic sources with channel classification (organic_search, direct, referral, paid, email, organic_social).
get_countriesVisitors by country (ISO 3166-1 alpha-2 codes).
get_citiesVisitors by city, with optional country filter.
get_devicesBreakdown by device type, browser, or OS.
get_eventsCustom event counts with property filtering and grouping.
get_timeseriesEvent counts over time with automatic granularity.

Pro Pro

ToolWhat it does
create_funnelDefine and immediately evaluate a multi-step conversion funnel.
get_funnelRetrieve a funnel with cohort filters (country, channel, device, UTM).
create_alertSet up metric alerts (e.g. "visitors drops_by 30% over 7d").

Common parameters

period"today", "yesterday", "7d", "30d", "90d", or a custom range as "YYYY-MM-DD:YYYY-MM-DD". Defaults to "30d".

limit — Max rows returned, 1–50. Defaults to 10.

Filters — Most tools accept pathname, utm_source, utm_campaign. Referrers accept channel. Funnels accept cohort filters: country, channel, device_type, utm_source, utm_campaign.

Prompts

Pre-built analytics workflows the AI can follow. Each prompt tells the model which tools to call, in what order, and how to present the results.

PromptWhat it produces
weekly_reportTraffic summary, top pages, referrers, countries, one actionable insight.
traffic_diagnosisRoot-cause analysis for traffic changes. Drills into channels, countries, devices, pages.
conversion_auditFunnel drop-off analysis with cohort segmentation.
channel_breakdownTraffic quality comparison across sources (volume vs engagement).
page_performanceDeep-dive on a single page: trends, referrers, devices, engagement vs site average.

Examples

Traffic overview

"How's my traffic this week?"

Calls get_overview with period="7d". Returns pageviews, visitors, sessions, bounce rate, avg duration, and comparison to the previous week.

"What's the bounce rate on /pricing?"

Calls get_overview with pathname="/pricing". Returns metrics for that single page, including comparison to the prior period.

"Show me traffic trends for the last 90 days"

Calls get_timeseries with period="90d". Returns daily counts over the full window.

Sources and geography

"Where are my visitors coming from?"

Calls get_top_referrers. Returns referrer hostnames with channel classification.

"Show me only organic search traffic to /blog"

Calls get_top_referrers with channel="organic_search" and pathname="/blog".

"Which countries send the most traffic?"

Calls get_countries. Returns ISO country codes with visitor and pageview counts.

Devices

"What's the mobile vs desktop split?"

Calls get_devices with group_by="device_type".

"Which browsers are my visitors using?"

Calls get_devices with group_by="browser".

Custom events

"How many signups happened this month?"

Calls get_events with name="signup" and period="30d".

"Break down signups by plan"

Calls get_events with name="signup" and group_by="plan". Returns counts per property value (e.g. free: 42, pro: 18, growth: 7).

"How many signups came from the spring campaign?"

Calls get_events with name="signup" and utm_campaign="spring-launch".

Funnels Pro

"Create a funnel from pricing page to signup to checkout"

Calls create_funnel with steps ["pageview:/pricing", "signup", "checkout_completed"]. Returns step-by-step conversion rates immediately.

"How does the pricing-to-signup funnel convert on mobile?"

Calls get_funnel with name="pricing-to-signup" and device_type="mobile".

"Compare funnel conversion for US vs Germany"

Two calls to get_funnel, one with country="US" and one with country="DE".

"What's the funnel conversion for visitors from Google?"

Calls get_funnel with channel="organic_search".

"How many mobile users from Germany signed up?"

Create a single-step funnel with steps=["signup"] and filter with country="DE" and device_type="mobile". Cohort filtering works on any funnel, including single-event funnels.

See Funnels for step syntax, cohort filters, and response shape.

Alerts Pro

"Alert me if visitors drop by 30% week over week"

Calls create_alert with metric="visitors", condition="drops_by", threshold=30, period="7d".

"Alert me if bounce rate on /pricing goes above 70%"

Calls create_alert with metric="bounce_rate", condition="above", threshold=70, pathname="/pricing".

Workflows

"Run a weekly report"

Follows the weekly_report prompt. Calls overview, top pages, referrers, countries, and timeseries, then synthesizes a structured report with trends and one actionable insight.

"Why did traffic drop last week?"

Follows the traffic_diagnosis prompt. Systematically checks channels, countries, devices, and pages to isolate the root cause.

"Audit our conversion funnel"

Follows the conversion_audit prompt. Analyzes funnel drop-offs, segments by device/country/channel, and identifies the biggest optimization opportunity.

"How is /pricing performing?"

Follows the page_performance prompt. Pulls page-specific metrics, referrers, device split, and compares engagement to the site average.