> For the complete documentation index, see [llms.txt](https://themochi-app.gitbook.io/mochi-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://themochi-app.gitbook.io/mochi-docs/feature-and-settings/claude-mcp.md). # Claude MCP Connect Claude (Anthropic's AI assistant) directly to your Mochi data through the Model Context Protocol for instant sales insights. ## What It Does **Claude MCP** turns Claude into your personal sales analyst by connecting it directly to your Mochi CRM data. Using the Model Context Protocol, Claude can query your sales metrics, team performance, lead lists, and funnel data in real-time through natural language. When you connect Claude to Mochi, you can ask questions like "How did Sarah do last week?" or "What are our top objections?" and Claude will pull live data from your CRM to provide detailed, accurate answers. It's like having your dashboard available inside Claude conversations. The integration exposes 26 specialized tools that let Claude access everything from setter metrics and closer performance to lead conversations and automation analytics. You can ask broad questions using natural language, or request specific data like funnel snapshots or team comparisons. Claude connects to Mochi through a robust OAuth 2.0 flow with PKCE (Proof Key for Code Exchange) for maximum security. The integration supports both Claude's web/mobile apps and other MCP-compatible clients. Your data stays secure with organization-level access controls and read-only permissions. ## Setting It Up ### Step 1: Ensure You Have Permissions Only **Creators** and **Managers** can authorize Claude to connect to your Mochi organization. If you're a Setter, Closer, or have another role, ask your team's Creator or Manager to set this up. ### Step 2: Connect Claude to Mochi 1. In Claude (web, mobile, or desktop app), look for the integrations or "work tools" section 2. Search for "Mochi" or look for CRM integrations 3. Click "Connect to Mochi" 4. You'll be redirected to authorize the connection to your Mochi organization 5. Log in to Mochi if prompted, then select your organization 6. Grant Claude read-only access to your sales data The connection uses OAuth 2.0 with PKCE (Proof Key for Code Exchange) for security. Claude gets read-only access to your CRM data — it cannot modify leads, create records, or change settings. ### Step 3: Test the Connection Once connected, try asking Claude a question about your sales data: * "Show me this week's funnel metrics" * "How are my setters performing?" * "What leads should I focus on today?" Claude will pull real data from your Mochi CRM and provide detailed answers. ## How to Use It ### Natural Language Queries The most powerful way to use Claude MCP is through natural language questions. Claude understands sales contexts and can answer questions like: * **Team Performance**: "Compare all my setters this month" or "Who's my top closer?" * **Funnel Analysis**: "Show me conversion rates by stage" or "Why are we losing deals?" * **Lead Intelligence**: "Which leads are hottest right now?" or "Show me leads tagged as 'high-value'" * **Trend Analysis**: "How did we do this week vs last week?" or "What's our booking trend?" * **Objection Patterns**: "What objections are we hearing most?" or "Which objections aren't we handling well?" ### Specific Data Tools For precise data needs, Claude can use specific tools: * **Metrics**: Get detailed setter/closer performance, funnel snapshots, response time distributions * **Comparisons**: Side-by-side team member comparisons, period-over-period trends * **Lead Management**: Ranked lead lists, leads by tag, conversation intelligence * **Analytics**: Automation performance, content effectiveness, audience insights * **Benchmarks**: Organization-specific performance benchmarks with percentiles ### Time Periods All queries support flexible time periods: * **Recent**: "today", "yesterday", "last\_7\_days", "last\_14\_days", "last\_30\_days" * **Calendar**: "this\_week", "last\_week", "this\_month", "last\_month" * **Default**: Most tools default to the last 7 days when no period is specified ### Team Member Analysis Claude can analyze specific team members by name: * "How did Sarah perform last week?" * "Show me John's closer metrics" * "Compare Emma and Mike's booking rates" The system automatically detects member roles and returns appropriate metrics. ## Tips * Start with natural language questions — Claude's `query_oracle` tool is the most powerful and understands sales terminology * Be specific about time periods for more accurate comparisons: "this week vs last week" works better than "recent performance" * Use team member names for personalized insights: "How did \[Name] do?" gives targeted feedback * Ask follow-up questions to dive deeper: "Why are we losing deals?" → "What objections aren't we handling?" * Time your analysis with your sales cycles — weekly reviews work well for most teams * Cross-reference insights with your actual dashboard to verify important decisions * Remember that Claude has read-only access — it can analyze but not modify your data --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://themochi-app.gitbook.io/mochi-docs/feature-and-settings/claude-mcp.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.