# Contentsquare MCP MCP Server > **Contentsquare MCP MCP Server** is a hosted, multitenant Model Context Protocol (MCP) server run by **MewCP** (https://mewcp.com), giving AI agents managed access to Contentsquare MCP. > > MewCP takes care of all MCP infrastructure for you — credential storage, OAuth flows, > token refresh, and production-grade auto-scaling — so your AI agents can connect to > third-party services and run freely without you managing any MCP server yourself. > > Server page: https://mewcp.com/mcp/contentsquare-mcp > MewCP docs: https://docs.mewcp.com > All servers: https://mewcp.com/servers (JSON: https://mewcp.com/api/servers) > About MewCP: https://mewcp.com/llms.txt --- ## About Analyze digital visitor behavior with Contentsquare to uncover actionable insights across conversion funnels, user journeys, page performance, and website errors. Explore analytics data, identify trends and bottlenecks, compare page groups, and optimize digital experiences using data-driven insights. --- ## Details - Server ID: `contentsquare-mcp` - Version: 1.0.0 - Tools: 21 - Authentication: OAuth, managed by MewCP - Transport: http --- ## Access The gateway URL below serves your **entire MewCP toolset**, not this server on its own. Pasting a config snippet is not enough — Contentsquare MCP has to be in the toolset first. In order: 1. Add Contentsquare MCP to your toolset at https://mewcp.com/mcp/contentsquare-mcp 2. Connect your Contentsquare MCP account (OAuth); MewCP stores the credential and attaches it to each call 3. Add the gateway URL to your client (see Connect below). It signs in with OAuth the first time it connects, so there is no key to copy. Once connected, an agent does **not** see this server's tools as top-level tools. It sees four meta-tools and reaches everything through them: - `search(query)` — find tools by keyword across the toolset - `get_schema(tools)` — full description and arguments for the tools you picked - `list_accounts(provider)` — only when one app has several connected accounts - `call_tool(server_maskedId, tool_name, args)` — execute So the list below is what `search` can return for this server, not a set of callable tool names on their own. --- ## Tools (21) Descriptions are truncated to 160 characters; call `get_schema` for the full text and the argument schema. Where a tool is annotated, its type is shown — treat `destructive` as irreversible. - `submitMcpFeedback` — Submit feedback about your MCP server experience. Help us improve by rating tools and sharing your thoughts! - `computeSiteMetrics` _(read)_ — Computes aggregated metrics across the entire website. Returns data grouped by specified dimensions (device, date, browser, country, etc.). Filters: time… - `getTopErrorsBySessionsWithErrors` _(read)_ — Get top errors ranked by sessions with errors. Main widget for general error analysis showing error trends, rates, and most frequent errors. USE for: general… - `getTopErrorsByImpactOnGoal` _(read)_ — Get top errors ranked by impact on conversion goals. Shows business-critical errors affecting revenue and conversions. USE for: business impact analysis,… - `getTopErrorsByMissedOpportunity` _(read)_ — Get top errors ranked by missed business opportunities (eCommerce focused). Shows revenue impact of errors. USE for: eCommerce missed revenue opportunities,… - `getTopPageGroupsByLostConversions` _(read)_ — Get page groups ranked by lost conversions due to errors. Shows business impact of errors by page groups. USE for: page group impact analysis, page-level… - `getTopPagesBySessionsWithErrors` _(read)_ — Get pages most affected by errors in a scatter plot comparing error volume with page traffic. USE for: identifying pages most affected by technical issues,… - `computeFunnel` _(read)_ — Computes funnel analysis to measure drop-offs and conversions across key steps in a user journey. Analyzes conversion rates, drop-off points, and time to… - `computeImpact` _(read)_ — Computes impact quantification analysis comparing conversion performance between segments. Provides metrics including conversion rates, bounce rates, session… - `computeJourney` _(read)_ — Computes user navigation journeys, visualizing how visitors navigate your site. Provides hierarchical tree structure showing common paths, drop-off points, and… - `computePageComparison` _(read)_ — Computes page comparison analysis comparing key performance metrics across multiple page groups (2-10). Provides metrics: views, bounce rate, exit rate, scroll… - `computePageGroupMetrics` _(read)_ — Compute page metrics, at the page group level. Use it to get an overview of the performance of the fraction of the website. - `getPageGroupsForMapping` _(read)_ — Retrieve all page groups for a specific mapping, sorted alphabetically by name. - `listProjects` _(read)_ — Returns a list of projects (id and name) accessible to the user - `searchMappings` _(read)_ — Search and retrieve mappings for a project. - `searchGoals` _(read)_ — Search and retrieve goals for a project. - `searchSegments` _(read)_ — Search and retrieve segments for a project, optionally filtered by name. - To find a segment by name, pass `text` rather than listing segments and scanning the… - `recommendMappings` _(read)_ — Recommend mappings based on user engagement and usage frequency (how often mappings are viewed, used in analyses, etc.) within the platform. - `recommendGoals` — Recommend goals based on user engagement and usage frequency (how often goals are viewed, used in analyses, etc.) within the platform. - `recommendPageGroups` _(read)_ — Recommend page groups based on user engagement and usage frequency (how often page groups are viewed, used in analyses, etc.) within the platform. - `recommendSegments` _(read)_ — Recommend segments based on user engagement and usage frequency (how often segments are viewed, used in analyses, etc.) within the platform. A project with no… --- ## Connect - URL: https://gateway.mewcp.com/personal/mcp - Transport: Streamable HTTP (remote). Nothing to install. - Sign-in: OAuth. On first connect the client opens a browser window to sign in to MewCP and approve access. No API key. - Headless clients (SDKs, servers without a browser) send an API key instead: `Authorization: Bearer `, key from https://mewcp.com/dashboard/api-keys Agents setting themselves up: follow https://mewcp.com/SKILL.md Step-by-step guide per client: - Claude Desktop: https://mewcp.com/mcp/contentsquare-mcp/connect/claude - ChatGPT: https://mewcp.com/mcp/contentsquare-mcp/connect/chatgpt - VS Code: https://mewcp.com/mcp/contentsquare-mcp/connect/vscode - Cursor: https://mewcp.com/mcp/contentsquare-mcp/connect/cursor - Codex: https://mewcp.com/mcp/contentsquare-mcp/connect/codex - Claude Code: https://mewcp.com/mcp/contentsquare-mcp/connect/claude-code - OpenCode: https://mewcp.com/mcp/contentsquare-mcp/connect/opencode - OpenClaw: https://mewcp.com/mcp/contentsquare-mcp/connect/openclaw - Antigravity: https://mewcp.com/mcp/contentsquare-mcp/connect/antigravity - Hermes: https://mewcp.com/mcp/contentsquare-mcp/connect/hermes - DeepSeek Harness: https://mewcp.com/mcp/contentsquare-mcp/connect/dsh - Python: https://mewcp.com/mcp/contentsquare-mcp/connect/python - TypeScript: https://mewcp.com/mcp/contentsquare-mcp/connect/typescript