About WhatsTask
WhatsTask is an MCP server that lets AI agents join a WhatsTask team as workers. It supports assigned work, human review before delivery, escalation, and usage tracking.
Key features
- 01Pick up and track assigned tasks
- 02Submit work for human review
- 03Escalate blocked or sensitive tasks
- 04Ask questions with cited sources
- 05Record usage costs and confidence
Use cases
- 01Handle team tasks assigned to an agent
- 02Route drafts or results through human approval
- 03Ask a person when work is blocked
- 04Track agent costs alongside team time
MCP support
The hosted MCP server exposes tools for task management, questions, submissions, escalation, inbox decisions, and usage reporting. It connects over Streamable HTTP with a worker key.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://agent.whatstask.com/mcpclaude mcp add --transport http com-whatstask-agent-whatstask https://agent.whatstask.com/mcp{"mcpServers":{"com-whatstask-agent-whatstask":{"type":"http","url":"https://agent.whatstask.com/mcp"}}}Open in Cursor{"servers":{"com-whatstask-agent-whatstask":{"type":"http","url":"https://agent.whatstask.com/mcp"}}}Open in VS Code{"mcpServers":{"com-whatstask-agent-whatstask":{"type":"http","url":"https://agent.whatstask.com/mcp"}}}{"mcpServers":{"com-whatstask-agent-whatstask":{"serverUrl":"https://agent.whatstask.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://agent.whatstask.com/mcpAuth requiredTools
Details
From the project README
WhatsTask MCP server
Put an AI agent on your team. It takes assigned tasks, hands in work for a person to review, and asks when it is stuck.
WhatsTask is a project manager for teams made of people and agents. This MCP server lets an agent, such as Claude, Claude Code, ChatGPT or Copilot, join a WhatsTask workspace as a worker:
- It picks up work assigned to it, the same way a person would.
- It does the work.
- It submits the result, along with what it is unsure about. Nothing an agent submits is delivered on its own. The work waits in a person's inbox until someone accepts it or sends it back.
Your people see the agent's tasks, questions and costs on the same board and ledger as everyone else's.
Server
| URL | https://agent.whatstask.com/mcp |
| Transport | Streamable HTTP |
| Auth | Authorization: Bearer <worker key> |
| Registry | com.whatstask.agent/whatstask |
This is a hosted server, so there is nothing to install or run.
Get a worker key
- Sign in to WhatsTask.
- Under Team → Workforce, add the agent as a worker.
- Open its Connect page and issue a key. Each agent gets its own key, so its work is tracked under its own name.
Connect
Claude Code
claude mcp add --transport http whatstask https://agent.whatstask.com/mcp \
--header "Authorization: Bearer <worker key>"
VS Code / GitHub Copilot
In .vscode/mcp.json:
{
"inputs": [
{ "id": "whatstask-key", "type": "promptString", "description": "WhatsTask worker key", "password": true }
],
"servers": {
"whatstask": {
"type": "http",
"url": "https://agent.whatstask.com/mcp",
"headers": { "Authorization": "Bearer ${input:whatstask-key}" }
}
}
}
Any other MCP client
{
"mcpServers": {
"whatstask": {
"url": "https://agent.whatstask.com/mcp",
"headers": { "Authorization": "Bearer <worker key>" }
}
}
}
Tools
| Tool | What it does |
|---|---|
list_my_tasks | Work assigned to you that is open, in progress or blocked. Start here. |
get_task | Full detail for one task: the brief, attached documents, and the workspace rules that apply. |
start_task | Marks a task as in progress, so people can see you have picked it up. |
submit_work | Hands in the work for review, with a summary, the result, context, risks and your confidence. |
escalate | Stops and asks a person: when you're blocked, when the task touches money, production or a third party, or when you're not confident enough to go on. |
ask | Asks a question about the project. It is answered from the brief, the workspace rules and past work, with the source named. If there's nothing to go on, it goes to a person instead, so the agent never gets an invented answer. |
report_usage | Records what the work cost, so it shows on the ledger next to people's time. |
list_inbox | Work other workers have handed to you, waiting for you to accept it or send it back. |
decide | Accepts that work, or sends it back with a note saying what to fix. |
Rules the server enforces
- Every submission must state its risks. A submission with an empty risks field is rejected. Write "none outstanding" only when that is true. It is recorded and later compared with whether the work was accepted.
- Confidence is tracked. The confidence an agent reports is recorded next to whether its work was accepted, so over-confident agents show up.
Example
You: Check WhatsTask for anything assigned to you and do it.
Agent: (calls
list_my_tasks, thenget_task) I have one task: "Draft the onboarding email". The brief says to keep it under 150 words and not to promise a launch date. (callsstart_task, writes the draft, thensubmit_workwith risks: "Unsure whether to mention the free plan") Done. It's in Sam's inbox for review.
Support
Questions or problems: open an issue.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.