mcpbeat Sign in

doing MCP Server

by alpic-doing-v2-d5286fe8 Your server? Claim it
answering

doing is answering right now. Last checked 13 min ago. It exposes 2 tools.

simple task manager for your LLM

Uptime history 91 days of history · worst day 98%
91 days agonow
100.0%
Uptime 24h
91 of 91 checks
2
Tools
read from the server
410 ms
Response time
average over 24h
authentication required
Access
sse

Nothing serious here today

Today is the operative word: we check doing every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 13 min ago.

run in your terminal
claude mcp add doing --transport sse https://doing-v2-d5286fe8.alpic.live
Settings → Connectors → Add custom connector, then paste this address
https://doing-v2-d5286fe8.alpic.live
~/.codex/config.toml
[mcp_servers.doing]
url = "https://doing-v2-d5286fe8.alpic.live"
.cursor/mcp.json
{
  "mcpServers": {
    "doing": {
      "url": "https://doing-v2-d5286fe8.alpic.live"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "doing": {
      "type": "sse",
      "url": "https://doing-v2-d5286fe8.alpic.live"
    }
  }
}

This endpoint answered with an authorization challenge. The server is running, but it did not say what kind of credentials it expects.

Available tools 2

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

doing
doing
Manage the doing task stack. Add a task, complete one, list tasks, or view the full stack with UI.
history
history
View all completed tasks in chronological order (from oldest to most recent)

Endpoints

URLTransportStateLatencyChecked
https://doing-v2-d5286fe8.alpic.live sse needs auth 285 ms 13 min ago

Alternatives to doing

same job, measured the same way
Tasks Example
by alpic-tasks-example-ca49f0f6

A test MCP server for task management

2 tools answering
Fizzy
by davegomez

MCP server for Fizzy task management

70 installs/wk local only
Tailscale MCP Server
by yawlabs

Tailscale MCP server for managing your tailnet from AI assistants

751 installs/wk local only
Todoist MCP
by ecfaria

MCP server for Todoist task management integration

51 installs/wk local only
Do It
by reinaldomoreira

Read and manage your do-it tasks and capture manual steps from your IDE or coding agent.

answering
Tip4serv
by tip4serv

Monetize and manage your Tip4Serv store directly from your LLM.

answering
pilotfish (managed)
by gai-ventures

Whole browser tasks done in pilotfish's cloud for any MCP agent, signed in with your saved logins.

3 032 installs/wk answering
T
Task Scheduler
by memoryapi

Schedule and manage recurring or one-shot tasks

4 tools answering

doing — questions

Answers built from our own checks of this server.

What can doing do?
It exposes 2 tools, read directly from the server on our last check. Among them: doing, history. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is doing working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 410 ms. The bar chart above shows every period we have measured.
How do I connect doing?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address. You will need your own credentials: it refuses anonymous clients.
Does doing need an API key?
Yes. Every time we knock, doing answers with an authorization challenge instead of its tool list — that is how we know it is running and gated rather than broken. Bring your own credentials and it will talk.
How fast is doing?
It answers our handshake in 410 ms on average, which is faster than 30% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.