lazyplan MCP server
Commit Nov 14, 2026Provides a shared terminal-based plan tracker for developers and coding agents to manage tasks, milestones, and evidence in a local database.
Also known as fluxion-dev/lazyplan
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 14, 2026
- License
- MIT
What is lazyplan MCP?
lazyplan provides a shared terminal-based plan tracker for developers and coding agents to manage tasks, milestones, and evidence in a local database.
Summary generated from the project's README
About lazyplan MCP server
Managing development tasks and milestones alongside coding agents is what lazyplan enables through a shared terminal-based tracking system. Developers use a fast keyboard-driven interface called lpui to monitor progress, while agents interact with the same data via a command line. This setup ensures that plans, milestones, and evidence remain in a local database instead of getting lost in chat history.
Users install the tool via pipx and can choose to store plans directly within a repository using the setup command. The system operates locally without requiring any cloud accounts or external logins, providing data portability through export and import functions. Agents access the plan using specific flags like --porcelain for terse output or --json for high fidelity, allowing them to read context and apply updates directly to the shared workflow.
This tool distinguishes itself by treating criteria, evidence, and pull requests as selectable hubs rather than unstructured text. It maintains focus by loading large branches on demand and keeping plans as one-line summaries until they are opened. By using the lpui command, teams can move tasks between states, edit criteria, and view recent activity through a dedicated feed.
What you can do with it
- 1Synchronize agent tasksAn AI agent can read the current project context and apply updates to the plan using JSON files.
- 2Track development progressA developer can move specific tasks through different workflow stages like doing or done.
- 3Maintain project provenanceUsers can link tasks to specific git commits and pull requests to show where work landed.
- 4Manage acceptance criteriaA developer can mark specific acceptance items as completed within a plan.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablefluxion-dev/lazyplan is public and reachablegithub.com/fluxion-dev/lazyplan ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-14github.com/fluxion-dev/lazyplan ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHublazyplan (lpui) — v0.43.0
Plan work with your coding agent, in the terminal.
lazyplan is one shared plan for you and your agent. You get a fast keyboard screen; the agent gets a plain command line. Plans, milestones, and tasks live in one local database instead of disappearing into chat, and read-only git and pull-request provenance shows where each one landed.
Install
pipx install lazyplan-tui
lpui --help
On Windows, use the pip backend:
pipx install --backend pip lazyplan-tui
lpui --version
Upgrading from 0.30.1 or earlier? Reinstall with force, because the package
layout changed: pipx install --force lazyplan-tui (or
python -m pip install --force-reinstall lazyplan-tui). See the
upgrade notes.
For system packages, the one-line installer, or installs from source, see install options.
First run
cd ~/my-plan
lpui # detects agents and creates the plan store
lpui plan add --title "my-plan" --why "reason" --what "scope"
lpui
Keep the plan in the repo with lpui setup --placement repo, or try the demo
data with lpui seed.
Why it differs
- One source of truth. The plan you see is the plan your agent reads. No copy-pasting context between chats.
- Made for focus. Plans stay as one-line summaries until you open them,
branches stay open or closed exactly as you left them, large branches load on
demand, and the timeline waits for
T. - Proof where you need it. Criteria, evidence, questions, references, claims, agents, comments, commits, and pull requests are selectable hubs, not a wall of text.
- Yours to keep. Local-first by default. Export or import any time. No account, no cloud, no lock-in.
Everyday commands
lpui list # plans and progress
lpui plan show --id 1 # why, what, criteria, milestones
lpui task move --id 1 --to doing # move work forward
lpui criterion edit --id 1 --done # mark an acceptance item done
lpui feed # recent activity
For your agent
The first run installs the agent skill. Agents read and write the same plan
through the CLI, using --porcelain for terse rows and --json for full
fidelity:
lpui --actor helper --porcelain next
lpui --actor helper --porcelain context --max-chars 4000
lpui plan recipe feature > plan.json
lpui --actor helper --porcelain plan apply --file plan.json
See the agent contract for claims, agents, evidence,
and MCP. For your data, back up with lpui export --format json and restore
with lpui import --file; see data and backup.
Learn more
- Usage and CLI reference
- Information architecture
- Changelog
- Contributing (main is protected; open a PR)
- Screenshots
- Releases · Issues
MIT licensed. This repo plans itself: run lpui list.
lazyplan MCP questions
How do I install lazyplan?
You can install it using pipx with the command pipx install lazyplan-tui. On Windows, use the pip backend.
Is my data stored in the cloud?
No, it is local-first by default with no account or cloud requirements, allowing you to export or import your data at any time.
Can coding agents use this tool?
Yes, agents can read and write the same plan through the CLI using porcelain or JSON modes.