Skip to main content
MCP Server

Cross-Agent Tasks

pf-tasks

The cross-agent to-do system.

A work in progress
We've published these resources in the hope they're useful — you're welcome to copy or use anything you find on this site. We're still working through each record to optimise it for completeness and accuracy, so some entries are fuller than others for now.

What it does

The cross-agent to-do system. It wraps Google Tasks so agents can hand work to one another and track it to completion on the right, registered task list.

Where the work lands

Each agent gets its own list. This is the shared Google Tasks board the connector reads and writes — one column per agent, work handed off between them.

Tools it exposes

Connects to Google Tasks. Each tool below is a single, well-defined capability — described in plain language.

  • List_Task_ListsSee the available task lists (a verification helper).Connects to: Google Tasks
  • Get_TaskRead a single task by its ID.Connects to: Google Tasks
  • Create_TaskAdd a task with a title, notes, status, and due date.Connects to: Google Tasks
  • List_TasksBrowse tasks in a list, with optional filters.Connects to: Google Tasks
  • Update_TaskChange a task's title, notes, status, or due date.Connects to: Google Tasks

Built and maintained by the MCP agent

This server was built with FastMCP and Python by our MCP agent, to spec. In practice it takes well under thirty minutes of hands-on direction — agents are genuinely good at building these. The value is in the design: each server exposes only the endpoints we want, with clear descriptions and parameters tuned to our goals.

Meet the MCP agent

You don't need all of this to start

Most of what these agents rely on has a simpler equivalent. Anywhere we use a database, you can usually start with a spreadsheet or a document — whatever you're comfortable with. Anywhere we built a custom MCP server, you can reach for a prebuilt AI connector instead of building your own.

We go further because it's where our experience pays off. Years of hands-on database work make a custom data layer feasible for us, and purpose-built MCP servers let us hand each agent a short, sharp instruction file and exactly the tools it needs — custom descriptions, only the endpoints we want, and the occasional extra gate — instead of a long manifesto or playbook. Nothing more, nothing less.

Ready to build technology that works for your mission?

Tell us where your organisation is and what's slowing your team down. We respond personally.

FAQ — Knowledge Base

Browse frequently asked questions about Knowledge Base

Request an Invitation to the MMP

Mission Multiplier cohorts form on a rolling basis. Request an invitation and we'll reach out when a cohort that fits you is coming together. No payment until you're invited and confirm your spot.