MCP.Market

TaskBullet MCP server

online · 100% uptime
by GriffMurder·io.github.GriffMurder/taskbullet·v0.2.1

Place US/CA phone calls and delegate tasks an AI agent cannot finish.

A91/100grade A
What users say
No reviews yet
Be the first
Safety scan
A91/100

not scanned yet

Adoption
Growing

0 stars10 downloads/wk

Reviews

Write one

Nobody has reviewed TaskBullet yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

TaskBullet tools

Tool list not cached yet. `describe` through the gateway fetches it live.

Not scanned yet. New listings are scanned within a day or two of arriving.

How TaskBullet compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
91/100
higher than 88% of 4,460 AI and agents servers
Uptime
100%
of our recent checks; the typical remote AI and agents server answers 100%
Response time
181 ms
faster than 70% of 2,331 AI and agents servers
Downloads a week
10
more than 2% of 1,538 AI and agents servers with a package

Release history: 2 versions in the registry since 2026-10-16, latest 2026-10-21, typically one every 6 days.

Install TaskBullet in Claude Code, Cursor or VS Code

claude mcp add --transport http taskbullet https://taskbullet.com/api/agent-mcp
Add to Cursor

What the publisher says

From the TaskBullet repository's README, as published. We do not edit it. Read it on GitHub

@taskbullet/mcp-server

MCP server for AI agent → human virtual assistant handoff. When an agent hits a task it cannot finish (phone calls, 2FA, captcha, physical-world actions, subjective QA), it files the brief with a TaskBullet virtual assistant.

There are two servers:

The public site server does not see customer accounts, emails, work history, or internal docs. Task delegation is only on the agent server.

Cloud agents (Cursor cloud, Grok, hosted Claude) should use the hosted agent URL. They cannot run npx.

Tools

delegate_task arguments: title (required), description, priority (low \| normal \| high \| urgent), dueDate, webhookUrl (https), maxHours (default 0.5, max 8), idempotencyKey (optional; a key is generated when omitted). Same tool names and the same required arguments as 0.1.x.

A tblive key files the brief. The customer starts VA hours on Work. awaitingcustomerstart means the job has not started. Do not say the VA has started. Poll get_task until completed, failed, or cancelled, or pass webhookUrl. Customer cancel is cancelled and does not send the completion webhook.

maxHours is a spend cap. Tracked time is what is billed (15-minute rounding). HTTP 402 means a live read is not above zero — buy hours at the addHoursUrl (the packages page, not a new trial). HTTP 422 means the cap does not fit open caps: hours remain, lower maxHours to capRoom or wait. HTTP 503 means hours were unavailable. That is not a buy-hours error.

Never put passwords, OTP codes, recovery keys, cookies, or API keys in a brief. The server drops those locally and the API rejects them.

Quickstart

Create a key at taskbullet.com/dashboard/settings/api-keys. It is shown once. Put it in the client config or the process environment. Do not paste it into chat.

Claude Desktop (stdio)

claudedesktopconfig.json (locations):

{
  "mcpServers": {
    "taskbullet": {
      "command": "npx",
      "args": ["-y", "@taskbullet/mcp-server"],
      "env": {
        "TASKBULLET_API_KEY": "tb_live_your_key_here"
      }
    }
  }
}

Restart Claude Desktop. The four tools show up in the tools panel.

Cursor (hosted streamable HTTP)

~/.cursor/mcp.json or the project .cursor/mcp.json:

{
  "mcpServers": {
    "taskbullet": {
      "url": "https://taskbullet.com/api/agent-mcp",
      "headers": {
        "x-api-key": "tb_live_your_key_here"
      }
    }
  }
}

Laptop stdio, if you would rather run the package locally:

{
  "mcpServers": {
    "taskbullet": {
      "command": "npx",
      "args": ["-y", "@taskbullet/mcp-server"],
      "env": {
        "TASKBULLET_API_KEY": "tb_live_your_key_here"
      }
    }
  }
}

OpenClaw

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

TaskBullet: common questions

Is TaskBullet MCP server safe?
Yes, by our scan: it is graded A (91/100). Read the TaskBullet safety report
How do I install TaskBullet?
It runs remotely at taskbullet.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does TaskBullet need an API key?
Yes. The registry entry asks for TASKBULLET_API_KEY, TASKBULLET_HTTP_TOKEN, x-api-key.
Is TaskBullet maintained?
The last commit was 19 days ago (2026-10-16). The latest release is v0.2.1.
Is TaskBullet up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of TaskBullet?
Servers from other publishers that do the same job: Ausca MCP server and AKShare MCP server.
How does TaskBullet compare with other AI and agents MCP servers?
safety score 91/100 (higher than 88% of 4,460 AI and agents servers); uptime 100% (of our recent checks; the typical remote AI and agents server answers 100%); response time 181 ms (faster than 70% of 2,331 AI and agents servers). Full comparison.

Alternatives to TaskBullet

Same job from other publishers: the closest match first, then the best rated.

  • Ausca
    Pay-per-call APIs and MCP services for agents, no accounts or keys, with verifiable receipts.
    A
  • AKShare
    Let a model explore AKShare's 1000+ China market data functions on its own — search, inspect, call
    A

More from GriffMurder →