Basecamp
Read Basecamp projects and people, and create to-dos, messages, comments and Campfire lines — on the Basecamp 5 API.
About
Basecamp ships in the w6w first-party pack. It declares 11 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
- App id
io.w6w.basecamp- Version
- 0.1.3
- Author
- w6w
- Licence
- MIT
- Categories
- Project Management · Productivity
Overview
Basecamp organizes work into projects that hold to-dos, message boards, documents and a live chat called Campfire — the “recording” model where every kind of content sits under one umbrella. This app reads projects and people, creates and completes to-dos, posts messages and comments, and drops lines into a Campfire room, on the Basecamp 5 API.
Dropping a line into Campfire doubles as the closest thing to a chat webhook: a build finished, a form came in, say so in the room — a common way workflows announce themselves without a full notification system. Comments post through one action since to-dos, messages, documents and uploads are all recordings underneath, so a single action handles them all.
Authentication runs over OAuth, since Basecamp has no API keys or personal access tokens, with account discovery handled automatically for identities that reach several Basecamp accounts. Good for teams already living in Basecamp who want workflow-triggered updates — a deploy notification in Campfire, a to-do created from an external event, or messages posted without opening the app.
Build with Basecamp
Three routes to the same 11 actions. The Workflow tab is generated from Basecamp's own manifest and carries its real ids, so it is copy-pasteable; the Code and CLI examples are the same call for any action on any app, so every app-specific value in them is a blank you fill in.
Create Comment
comment-create Comment on any recording — a message, to-do, document or upload. One endpoint covers them all.
Create Message
message-create Post a message to a board. Published and notified by default — Basecamp would otherwise save it as an unseen draft.
List People
people-list List everyone on the account. Their ids are what Create To-do's assignees take — Basecamp has no assign-by-email.
List Projects
project-list List the account's projects. Each project's `dock` carries the ids of its tools — message board, to-do set, Campfire — which the other actions take.
Complete To-do
todo-complete Mark a to-do as done, or reopen it. Basecamp models completion as a sub-resource rather than a field.
List To-dos
todo-list List a to-do list's to-dos. Open ones by default — asking for completed ones returns those instead, not as well.
A workflow step names the app and the action, and the editor fills in the
connection when you pick one. This is the Step shape from the
workflow spec, carrying Basecamp's real ids.
{
"manifestVersion": "2",
"name": "basecamp-example",
"steps": [
{
"id": "campfire-line-create",
"uses": {
"app": "io.w6w.basecamp",
"action": "campfire-line-create",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"campfireId": "<campfireId>",
"content": "<content>"
}
}
]
}Here are some of the things you can do
-
Post Campfire Message
performcampfire-line-create -
Create Comment
performcomment-create -
Create Message
performmessage-create -
List Messages
searchmessage-list -
List People
searchpeople-list
+6 more actions available
Every app-specific value here is a blank you have to fill in. An
app action is reached through the connection that authenticates it, so the
address is a connection id, not the app id — and connections belong to your account,
so a public page cannot know yours. Create one for Basecamp, then fill in
the three blanks: conn_YOUR_CONNECTION_ID, the action key, and the
parameters that action declares. The call itself is real — the shape is transcribed
from the studio's own snippet builder, which prints the same kind of blanks — but
nothing in it is specific to Basecamp. The Workflow tab is where this app's
real ids are.
npm install @w6w/sdkyarn add @w6w/sdkpnpm add @w6w/sdkdeno add npm:@w6w/sdkimport { W6wClient, isActionRun } from "@w6w/sdk";
// Reads W6W_BASE_URL and W6W_TOKEN from the environment when omitted.
const client = new W6wClient();
const envelope = await client.run({
urn: "conn_YOUR_CONNECTION_ID",
action: "message-create",
payload: {
boardId: "<value>",
subject: "<value>",
// content: "<value>",
// status: "<value>",
// categoryId: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value);npm install -g @w6w/cliw6w run conn_YOUR_CONNECTION_ID --action message-create --payload '{"boardId":"<value>","subject":"<value>"}'Give an AI agent Basecamp — without giving it Basecamp's credentials. One MCP endpoint exposes every app, function and workflow the caller is entitled to, as tools it can discover and run. Access is granted per team while we onboard.
One tool call{
"name": "w6w_invoke",
"arguments": {
"ref": "app:io.w6w.basecamp#campfire-line-create",
"input": {
"campfireId": "<campfireId>",
"content": "<content>"
}
}
}
Every tool names its target with a single ref. The
app: form above doesn't name a connection at all — the
host resolves which of the caller's Basecamp connections to sign
with, and refuses rather than guesses when the answer is ambiguous.
What the agent gets
Credentials it can't read
The token is attached host-side, at the moment of the call. It is never a tool argument, never in the model's context, and never in a transcript — so a prompt injection has nothing to exfiltrate.
A tool surface scoped to the caller
Tools are derived per end user from what that person has actually connected and is entitled to — not one shared bot identity carrying the union of everyone's access.
A durable workflow in one call
Multi-step work runs on the workflow engine and returns a run handle the agent can poll — retries, branching and state survive the conversation that started them.
Health-aware discovery
Basecamp's declared health checks are on the surface too, so an agent can tell "the vendor is down" from "your credential expired" before it burns a retry on either.
The MCP surface is part of the hosted platform. Basecamp itself is MIT, and the runtime that executes it is source-available (FSL).
Health checks
Basecamp declares its own checks, so its health is a property of the app rather than something the host guesses at.
Basecamp platform status
Reads 37signals' status page and takes its verdict from the `Basecamp 5` component specifically — the page also covers HEY, Highrise and older Basecamps, which say nothing about this app.