Autonomous AI developers on your own infrastructure: assign a task, get a pull request.
online.mcptask/mcptask MCP Server
The online.mcptask/mcptask Model Context Protocol (MCP) server provides task management for people and autonomous AI developers, covering tasks, stories, work logs, and pull requests. It is intended to support workflows around tracking and coordinating work across these artifacts.
š ļø Key Features
Task management
Stories
Work logs
Pull requests
š Use Cases
Managing tasks for human users
Coordinating work for autonomous AI developers
Tracking progress via work logs
Reviewing and integrating changes through pull requests
ā” Developer Benefits
Consistent access to task-related artifacts (tasks, stories, work logs, pull requests)
Support for end-to-end workflow items tied to development activity
ā ļø Limitations
Available details specify only tasks, stories, work logs, and pull requests; no additional capabilities are described.
Released binaries of the mcptask runner ā the tool that drives Claude Code
through the tasks on mcptask.online.
This repository holds no source. It exists so the binaries can be downloaded
without a token: the runner is developed in a private repository, and a private
repository's release assets cannot be fetched anonymously, which would rule out
a one-line install. The artefacts are the public part.
Install
bash
curl -fsSL https://github.com/jchsoft/mcptask-releases/releases/latest/download/install.sh | sh
macOS and Linux, amd64 and arm64. The script detects the platform, verifies the
download against the release's checksums.txt, and installs mcptask_runner
into /usr/local/bin when that is already writable and ~/.local/bin
otherwise. It never calls sudo, and it installs the binary and stops ā it does
not run init and does not enable a scheduled job.
Read it before you run it: install.sh is the same file the
command above fetches.
Variable
Effect
MCPTASK_VERSION
install a specific tag instead of the latest release
MCPTASK_INSTALL_DIR
install somewhere else
On Windows, download the windows archive from
Releases and put
mcptask_runner.exe on PATH.
The feature catalog
catalog.yml is the runner's feature catalog in English, Czech and Slovak: one
entry per feature, subcommand, flag, config key, harness, git host and exit
code. It is generated in the private source repository and validated there by
a test that fails when the catalog and the code disagree, and every release
carries it as an asset. mcptask.online/runner
renders it. The latest one is always at
https://github.com/jchsoft/mcptask-releases/releases/latest/download/catalog.yml
and a specific version's at
https://github.com/jchsoft/mcptask-releases/releases/download/<tag>/catalog.yml.
Verifying a manual download
Every release publishes checksums.txt alongside the archives.
bash
shasum -a 256 --ignore-missing --check checksums.txt # sha256sum -c on Linux
Worth doing: the binary goes on to run your Claude sessions with your
credentials.
Getting started
bash
mcptask_runner init # in the project you want the runner to work on
mcptask_runner version
mcptask.online is itself a remote MCP server ā the runner is one client of it,
Claude Code, Claude.ai, ChatGPT and any other MCP client can connect directly.
Endpoint
https://mcptask.online/mcp (Streamable HTTP)
Authentication
Authorization: Bearer <token> or OAuth; without a token /mcp answers 401 with WWW-Authenticate