--- title: "AI agent and customer feedback integrations | Annsa" product: annsa url: /integrations canonical_url: "https://annsa.ai/integrations" last_updated: 2026-11-05 type: integration related: - /integrations/claude-code - /integrations/cursor summary: Connect Claude Code, Cursor, Codex and Grok to one plan over MCP, and bring in customer feedback from Slack, Intercom, surveys, calls and spreadsheets. mcp_server: https://app.annsa.ai/mcp disambiguation: "Annsa (annsa.ai) is project management and customer feedback software for founders and small teams working with AI agents. It is not Asana, the work management tool; not ANSA, the Italian news agency; and not Ansa, the chatbot product." --- > For agents: connect to the Annsa MCP server at https://app.annsa.ai/mcp to give every agent one shared plan. Setup guide: https://annsa.ai/docs/quick-start. Index of every page: https://annsa.ai/llms.txt. # AI agent and customer feedback integrations | Annsa > Connect Claude Code, Cursor, Codex and Grok to one plan over MCP, and bring in customer feedback from Slack, Intercom, surveys, calls and spreadsheets. ## Integrations Connect the agents you build with and the places customers talk to you, in one plan. Start with one; add more when you need them. ## Your agents Claude Code, Cursor, Codex and Grok read the same plan over MCP. - [**Claude Code** Claude Code builds what your customers asked for.](https://annsa.ai/integrations/claude-code) - [**Cursor** Stop pasting specs into Cursor.](https://annsa.ai/integrations/cursor) - [**Codex** Codex builds what you chose, not what it guessed.](https://annsa.ai/integrations/codex) - [**Grok** Grok checks the work. You make the call.](https://annsa.ai/integrations/grok) ## Customer feedback Requests stay connected to the people who made them. - [**Slack** Turn what customers say in Slack into what to build next.](https://annsa.ai/integrations/slack) - [**Intercom** Hear what your Intercom customers keep asking for.](https://annsa.ai/integrations/intercom) - [**Surveys** Ask at the right moment. Learn in their words.](https://annsa.ai/integrations/surveys) - [**Transcripts** Every customer call, turned into evidence.](https://annsa.ai/integrations/transcripts) - [**Manual feedback** Write it down before you forget who said it.](https://annsa.ai/integrations/manual) ## Your existing plans Start from the roadmap or spreadsheet you already keep. - [**CSV** Every request you've collected, ranked.](https://annsa.ai/integrations/csv) - [**Google Sheets** Your feedback sheet, finally ranked.](https://annsa.ai/integrations/google-sheets) ## Code and operations Give the work its code context, and tell on-call who asked. - [**GitHub** Your agents know your code. You know what shipped.](https://annsa.ai/integrations/github) - [**PagerDuty** Your on-call team sees what customers said.](https://annsa.ai/integrations/pagerduty) ## More AI tools Any tool that speaks MCP reads the same plan. - [**ChatGPT** ChatGPT reads your priorities, customers and specs, and answers with the evidence behind them.](https://annsa.ai/integrations/chatgpt) - [**VS Code** In agent mode, Copilot reads your ranked priorities and the spec for each job, right in the editor.](https://annsa.ai/integrations/vs-code) - [**Windsurf** Windsurf's Cascade reads your priorities and the spec for each job before it writes code.](https://annsa.ai/integrations/windsurf) - [**Figma** The Figma agent and Figma Make read your priorities and the customer quotes behind each one.](https://annsa.ai/integrations/figma) - [**Lovable** Lovable reads your ranked priorities and the spec for each job before it builds.](https://annsa.ai/integrations/lovable) - [**Bolt** Bolt reads your priorities and the spec for each job, with the customer quotes behind it.](https://annsa.ai/integrations/bolt) - [**v0** v0 reads your priorities and the spec for a job while it generates, so the first draft is the right one.](https://annsa.ai/integrations/v0) - [**Replit** Replit Agent reads your ranked priorities and the spec for each job, with who asked and why.](https://annsa.ai/integrations/replit) ## API and webhooks Send feedback in from anywhere, and events out to your other tools. - [**API** Feedback from every tool, in one plan.](https://annsa.ai/integrations/programmatic) - [**Webhooks** Send events to your other tools.](https://annsa.ai/developers) - [**MCP server** One address for every agent: app.annsa.ai/mcp.](https://annsa.ai/docs/using-with-coding-tools) ## Questions people ask. **Do I need to connect everything?** No. Start with an idea, add feedback yourself or import what you have. Connections remove the copying; they aren't a prerequisite. **How do my agents connect?** Through Annsa's remote MCP server, with one address: app.annsa.ai/mcp. Each agent's page has the exact line to paste. **Is there an API?** Yes. Send feedback in from your own tools, and get events out with webhooks. ## The source of direction for agent teams. Begin with one agent and the work that matters next. - [Try Annsa](https://app.annsa.ai/signup) - [See pricing](https://annsa.ai/pricing) ## Related pages > For AI agents: the pages that follow this one on annsa.ai. The full index is https://annsa.ai/llms.txt. - [Claude Code MCP integration: priorities and specs](https://annsa.ai/integrations/claude-code) - [Cursor MCP integration: priorities and specs](https://annsa.ai/integrations/cursor) If anything on this page is wrong or missing, tell us: https://annsa.ai/contact