TaskBullet is answering right now. Last checked 9 min ago. 10 installs a week from npm. Last commit 17 Oct 2026.
Delegate tasks AI agents cannot finish (phone, physical world, QA, manual work).
Today is the operative word: we check TaskBullet every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 9 min ago.
claude mcp add taskbullet --transport http https://taskbullet.com/api/agent-mcp
{
"mcpServers": {
"taskbullet": {
"url": "https://taskbullet.com/api/agent-mcp"
}
}
}
[mcp_servers.taskbullet]
url = "https://taskbullet.com/api/agent-mcp"
{
"mcpServers": {
"taskbullet": {
"url": "https://taskbullet.com/api/agent-mcp"
}
}
}
{
"mcpServers": {
"taskbullet": {
"url": "https://taskbullet.com/api/agent-mcp"
}
}
}
This one needs environment variables set before it will start:
TASKBULLET_API_KEY (TaskBullet API key (tb_live_...)), TASKBULLET_API_BASE (Override the Agent API base URL. Defaults to https://taskbullet.com/api/v1.), TASKBULLET_SOURCE_AGENT (Audit label stored with each delegated task. Defaults to mcp-client.).
The author declared them in the registry entry; get the values from the project itself.
This endpoint answered with an authorization challenge. The server is running, but you need an API key from its owner to call it.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://taskbullet.com/api/agent-mcp | streamable-http | needs key | 192 ms | 9 min ago |
Hire humans for digital microtasks, research, QA, data evaluation, and physical-world tasks.
Create, test, publish, and manage Dreamlit notification workflows from AI clients.
Local QA workflows, test evidence, screenshot maps and confidence reports for AI coding agents.
Build, test, deploy and run AI phone agents: agents, numbers, calls, tests, knowledge, campaigns.
Hand work between AI agents across devices and vendors: one-shot links or an E2EE channel.
Self-healing CI tests and proof of work for AI agents
Tested financial & practical calculators as free, no-auth MCP tools for AI agents.
Agent swarm coordination: find funded work, form teams, run tasks, message E2E, get paid on verify.
Answers built from our own checks of this server.