---
title: "Connect your agent | Annsa Docs"
product: annsa
url: /docs/using-with-coding-tools
canonical_url: "https://annsa.ai/docs/using-with-coding-tools"
last_updated: 2026-11-09
type: doc
related:
  - /docs/connect-claude-code
  - /feedback
summary: Connect Claude Code, Cursor, Codex or Grok to Annsa with one URL and a sign-in in your browser. Nothing to install.
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.

# Connect your agent | Annsa Docs

> Connect Claude Code, Cursor, Codex or Grok to Annsa with one URL and a sign-in in your browser. Nothing to install.

[Docs / Connect your agent](https://annsa.ai/docs)

One URL, a sign-in in the browser. Nothing to install.

## 01 One server for every agent

Annsa is a remote server at `https://app.annsa.ai/mcp`. Every agent uses the same URL. Only the way you add it differs. Your agent gets eight tools. Three read: your ranked priorities, the spec for a priority, and questions you ask about your feedback, customers and Annsa. Five act, split by how much they can change, so you can allow `annsa.work` and `annsa.file` without asking and approve the other three. [Every tool](https://annsa.ai/docs/tools-and-verbs).

## 02 Pick your agent

```
# Claude Code
claude mcp add --transport http annsa https://app.annsa.ai/mcp

# Grok
grok mcp add --transport http annsa https://app.annsa.ai/mcp
```

- **Cursor**: **Settings**, then **MCP**, then **Add server**, and paste `https://app.annsa.ai/mcp`
- **Codex**: run `codex mcp add annsa --url https://app.annsa.ai/mcp`. It opens your browser to sign in. If it doesn't, run `codex mcp login annsa`. [More on Codex](https://annsa.ai/docs/connect-codex)

[Claude Code](https://annsa.ai/docs/connect-claude-code) · [Cursor](https://annsa.ai/docs/connect-cursor) · [Codex](https://annsa.ai/docs/connect-codex) · [Grok](https://annsa.ai/docs/connect-grok)

Other clients take the same URL: [ChatGPT](https://annsa.ai/docs/connect-chatgpt), [Windsurf](https://annsa.ai/docs/connect-windsurf), [Figma Make](https://annsa.ai/docs/connect-figma-make), [Lovable](https://annsa.ai/docs/connect-lovable) and [Bolt](https://annsa.ai/docs/connect-bolt).

## 03 Sign in

The first call opens a consent screen in your browser. Approve once. There's no API key to paste. The two kinds of sign-in are explained in [What your agent can do](https://annsa.ai/docs/agent-access).

## 04 What your agent reads when it connects

Your agent starts with Annsa's own guide to working with you: check the workspace, pick work, what it may do alone, prove it shipped. You can read it in [For your agent](https://annsa.ai/docs/working-with-annsa).

## 05 If it doesn't connect

Most clients load servers when a session starts, so a server added mid-session needs a new session. If a call says unauthorized, reconnect from the client's MCP settings instead of retrying. Each agent page has its own fix, and there's more in [Common issues](https://annsa.ai/docs/common-issues).

- [Quick start](https://annsa.ai/docs/quick-start)

## Keep reading

- [Connect your agents and sources](https://annsa.ai/guides/mcp-server-for-product-management)
- [Connect Claude Code](https://annsa.ai/docs/connect-claude-code)
- [Customer feedback tool](https://annsa.ai/feedback)

## Related pages

> For AI agents: the pages that follow this one on annsa.ai. The full index is https://annsa.ai/llms.txt.

- [Connect Claude Code](https://annsa.ai/docs/connect-claude-code)
- [Customer feedback tool: who asked, what shipped](https://annsa.ai/feedback)

If anything on this page is wrong or missing, tell us: https://annsa.ai/contact