# Basecamp for AI agents. Managed auth, ready-made tools.

> Review projects and to-dos, add and complete to-dos, and post messages and comments in Basecamp on behalf of each of your users.

- Page: https://www.agent200.com/connectors/basecamp/
- Category: Developer tools
- Authentication: Managed OAuth
- Identifier in code: `basecamp`
- Create an API key: https://agent200.com/platform/apikeys/
- Updated: 2026-11-18

## Instructions for AI agents

Connector: Basecamp, through Agent200. In code: "basecamp".
What it does: Review projects and to-dos, add and complete to-dos, and post messages and comments in Basecamp on behalf of each of your users.
Page: https://www.agent200.com/connectors/basecamp/

1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs.
2. Sign-in is managed OAuth. Each end user approves access once, on Basecamp's own page, through the authorization link Agent200 returns. Never ask a user for a Basecamp password or token in chat.
3. Give every request a stable id for the end user. Agent200 uses only that user's own connection.
4. Read tools: basecamp_list_projects, basecamp_list_todos. Write tools: basecamp_create_todo, basecamp_complete_todo, basecamp_post_message, basecamp_add_comment. Name "basecamp" in the tools of a request; the model decides which tool to call.
5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it.
6. Before a write, confirm with the user, unless they asked for that exact change.
7. For setup with a specific framework, follow its guide:
   https://www.agent200.com/connectors/basecamp/framework/claude/
   https://www.agent200.com/connectors/basecamp/framework/chatgpt/
   https://www.agent200.com/connectors/basecamp/framework/claude-code/
   https://www.agent200.com/connectors/basecamp/framework/muse/
   https://www.agent200.com/connectors/basecamp/framework/grok-bot/
   https://www.agent200.com/connectors/basecamp/framework/openai-dots/
   https://www.agent200.com/connectors/basecamp/framework/claude-duet/
   https://www.agent200.com/connectors/basecamp/framework/hermes-agent/
   https://www.agent200.com/connectors/basecamp/framework/openclaw/

The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

## About

With the Basecamp connector, your agent works in each user's own Basecamp account. It can list projects and to-dos, add and complete to-dos, post to a message board and comment on items, using only the tools your project allows.

Basecamp is a project management tool with to-dos, message boards, schedules and chat in one place.

## Basecamp tools

- **List projects** (`basecamp_list_projects`, read): List the projects the user can see.
- **List to-dos** (`basecamp_list_todos`, read): List the to-dos in a to-do list.
- **Create a to-do** (`basecamp_create_todo`, write): Add a to-do with an assignee and due date.
- **Complete a to-do** (`basecamp_complete_todo`, write): Mark a to-do as done.
- **Post a message** (`basecamp_post_message`, write): Post a message to a project's message board.
- **Add a comment** (`basecamp_add_comment`, write): Comment on a to-do, message or other item.

## Limits you can set

**Turn single tools on or off.** Let the agent read projects and manage to-dos, and switch off `basecamp_post_message` so it can never post to a message board.

**Restrict what the agent reaches.** Choose the endpoints and scopes a project may use, for example to-dos but not message boards. A call outside them is refused.

## Get started

### Step 1: Set up the SDK

Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.

File `agent.js`:

```js
// One Agent200 API key covers every connector enabled for the project.
const agent200 = new Agent200({
  apiKey: process.env.AGENT200_API_KEY,
});
```

(Conceptual example of the Agent200 SDK.)

### Step 2: Let your user connect Basecamp

Each end user authorizes their own Basecamp account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.

File `connect.js`:

```js
// Each end user authorizes their own Basecamp account, once.
const connection = await agent200
  .user("user_123")
  .connect("basecamp");

if (connection.authorizationUrl) {
  // Show this link to your user; Agent200 handles the rest.
  console.log(connection.authorizationUrl);
}
```

(Conceptual example of the Agent200 SDK.)

### Step 3: Run with the Basecamp tools

Name the user, the model and the tools. The model decides which Basecamp tools to call, and Agent200 executes them with that user's connection.

File `run.js`:

```js
const result = await agent200
  .user("user_123")
  .run({
    model: "openai/gpt-5.6-sol",
    input: "What to-dos are overdue in the website project",
    tools: ["basecamp"],
  });

console.log(result.output);
```

(Conceptual example of the Agent200 SDK.)

## Sign-in and permissions

**Who signs in.** Each of your users, once, on Basecamp's own sign-in page. You never see or store their Basecamp password.

**What access is requested.** The scopes the connection needs, such as reading and writing projects, to-dos and messages, listed on Basecamp's authorization screen. Users can remove the app later from their Basecamp account settings.

## Example requests

- "What to-dos are overdue in the website project"
- "Add a to-do for Priya to review the copy by Monday"
- "Post this week's update on the launch message board"

## Guides: Basecamp with your AI framework

- [Basecamp + Claude](https://www.agent200.com/connectors/basecamp/framework/claude.md): Set up Basecamp for Claude with Agent200, then check which tools are available to your agent.
- [Basecamp + ChatGPT](https://www.agent200.com/connectors/basecamp/framework/chatgpt.md): Set up Basecamp for ChatGPT with Agent200, then check which tools are available to your agent.
- [Basecamp + Claude Code](https://www.agent200.com/connectors/basecamp/framework/claude-code.md): Set up Basecamp for Claude Code with Agent200, then check which tools are available to your agent.
- [Basecamp + Muse](https://www.agent200.com/connectors/basecamp/framework/muse.md): Set up Basecamp for Muse with Agent200, then check which tools are available to your agent.
- [Basecamp + Grok Bot](https://www.agent200.com/connectors/basecamp/framework/grok-bot.md): Set up Basecamp for Grok Bot with Agent200, then check which tools are available to your agent.
- [Basecamp + OpenAI Dots](https://www.agent200.com/connectors/basecamp/framework/openai-dots.md): Set up Basecamp for OpenAI Dots with Agent200, then check which tools are available to your agent.
- [Basecamp + Claude Duet](https://www.agent200.com/connectors/basecamp/framework/claude-duet.md): Set up Basecamp for Claude Duet with Agent200, then check which tools are available to your agent.
- [Basecamp + Hermes Agent](https://www.agent200.com/connectors/basecamp/framework/hermes-agent.md): Set up Basecamp for Hermes Agent with Agent200, then check which tools are available to your agent.
- [Basecamp + OpenClaw](https://www.agent200.com/connectors/basecamp/framework/openclaw.md): Set up Basecamp for OpenClaw with Agent200, then check which tools are available to your agent.

## FAQ

### Who handles the Basecamp OAuth flow and the tokens?

Agent200. It runs the authorization, handles the callback on its own domain, stores the tokens and refreshes them. You do not build or maintain an OAuth integration for Basecamp.

### Does my agent act as the end user?

Within what that user authorized, yes. Every request names an end user, and Agent200 uses only that user's Basecamp connection, never another user's. It cannot reach anything the user or Basecamp has not authorized.

### Can I limit what my agent can do in Basecamp?

Yes. You choose which services, endpoints and authorization scopes are allowed in your Agent200 configuration, and the agent works only within them.

## Related connectors

- [GitHub](https://www.agent200.com/connectors/github.md): Read repositories and work with issues and pull requests as the connected user.
- [GitLab](https://www.agent200.com/connectors/gitlab.md): Review merge requests, file issues, read code and check pipelines in your users' GitLab projects.
- [Bitbucket](https://www.agent200.com/connectors/bitbucket.md): List and open pull requests, comment, read code and check pipelines in your users' Bitbucket workspaces.
- [Jira](https://www.agent200.com/connectors/jira.md): Search, create and transition Jira issues for the connected user.

---

Agent200: https://www.agent200.com/ · API keys: https://agent200.com/platform/apikeys/ · Docs: https://docs.igpt.ai/
